diff --git a/.claude/skills/add_platform.add_capabilities/SKILL.md b/.claude/skills/add_platform.add_capabilities/SKILL.md index 5458f672..f00fd713 100644 --- a/.claude/skills/add_platform.add_capabilities/SKILL.md +++ b/.claude/skills/add_platform.add_capabilities/SKILL.md @@ -1,6 +1,6 @@ --- name: add_platform.add_capabilities -description: "Update job schema and adapters with any new hook events the platform supports" +description: "Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system." user-invocable: false hooks: Stop: @@ -24,7 +24,7 @@ hooks: **Step 2/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Prerequisites (Verify First) @@ -33,7 +33,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Update job schema and adapters with any new hook events the platform supports +**Goal**: Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system. # Add Hook Capabilities @@ -211,6 +211,13 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - `job_schema.py` - `adapters.py` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/add_platform.implement/SKILL.md b/.claude/skills/add_platform.implement/SKILL.md index 3366001d..eceb86ef 100644 --- a/.claude/skills/add_platform.implement/SKILL.md +++ b/.claude/skills/add_platform.implement/SKILL.md @@ -1,6 +1,6 @@ --- name: add_platform.implement -description: "Add platform adapter, templates, tests with 100% coverage, and README documentation" +description: "Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities." user-invocable: false hooks: Stop: @@ -28,7 +28,7 @@ hooks: **Step 3/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Prerequisites (Verify First) @@ -38,7 +38,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Add platform adapter, templates, tests with 100% coverage, and README documentation +**Goal**: Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities. # Implement Platform Support @@ -310,6 +310,13 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - `tests/` (directory) - `README.md` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/add_platform.research/SKILL.md b/.claude/skills/add_platform.research/SKILL.md index 6aea327a..ff7e489e 100644 --- a/.claude/skills/add_platform.research/SKILL.md +++ b/.claude/skills/add_platform.research/SKILL.md @@ -1,6 +1,6 @@ --- name: add_platform.research -description: "Capture CLI configuration and hooks system documentation for the new platform" +description: "Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration." user-invocable: false hooks: Stop: @@ -25,12 +25,12 @@ hooks: **Step 1/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Instructions -**Goal**: Capture CLI configuration and hooks system documentation for the new platform +**Goal**: Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration. # Research Platform Documentation @@ -261,6 +261,13 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - `cli_configuration.md` - `hooks_system.md` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/add_platform.verify/SKILL.md b/.claude/skills/add_platform.verify/SKILL.md index ed2a06b3..67b20801 100644 --- a/.claude/skills/add_platform.verify/SKILL.md +++ b/.claude/skills/add_platform.verify/SKILL.md @@ -1,6 +1,6 @@ --- name: add_platform.verify -description: "Set up platform directories and verify deepwork install works correctly" +description: "Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration." user-invocable: false hooks: Stop: @@ -23,7 +23,7 @@ hooks: **Step 4/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Prerequisites (Verify First) @@ -32,7 +32,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Set up platform directories and verify deepwork install works correctly +**Goal**: Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration. # Verify Installation @@ -185,6 +185,13 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` **Required outputs**: - `verification_checklist.md` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/add_platform/SKILL.md b/.claude/skills/add_platform/SKILL.md index c9c5cfa9..75aa7f05 100644 --- a/.claude/skills/add_platform/SKILL.md +++ b/.claude/skills/add_platform/SKILL.md @@ -1,11 +1,11 @@ --- name: add_platform -description: "Add a new AI platform to DeepWork with adapter, templates, and tests" +description: "Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools." --- # add_platform -**Multi-step workflow**: Add a new AI platform to DeepWork with adapter, templates, and tests +**Multi-step workflow**: Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. > **CRITICAL**: Always invoke steps using the Skill tool. Never copy/paste step instructions directly. @@ -29,10 +29,10 @@ comprehensive test coverage for new functionality. ## Available Steps -1. **research** - Capture CLI configuration and hooks system documentation for the new platform -2. **add_capabilities** - Update job schema and adapters with any new hook events the platform supports (requires: research) -3. **implement** - Add platform adapter, templates, tests with 100% coverage, and README documentation (requires: research, add_capabilities) -4. **verify** - Set up platform directories and verify deepwork install works correctly (requires: implement) +1. **research** - Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration. +2. **add_capabilities** - Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system. (requires: research) +3. **implement** - Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities. (requires: research, add_capabilities) +4. **verify** - Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration. (requires: implement) ## Execution Instructions @@ -64,6 +64,13 @@ If user intent is unclear, use AskUserQuestion to clarify: - Present available steps as numbered options - Let user select the starting point +## Guardrails + +- Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps +- Do NOT skip steps in the workflow unless the user explicitly requests it +- Do NOT proceed to the next step if the current step's outputs are incomplete +- Do NOT make assumptions about user intent; ask for clarification when ambiguous + ## Context Files - Job definition: `.deepwork/jobs/add_platform/job.yml` \ No newline at end of file diff --git a/.claude/skills/commit.commit_and_push/SKILL.md b/.claude/skills/commit.commit_and_push/SKILL.md index eff060a3..e13fcf06 100644 --- a/.claude/skills/commit.commit_and_push/SKILL.md +++ b/.claude/skills/commit.commit_and_push/SKILL.md @@ -1,6 +1,6 @@ --- name: commit.commit_and_push -description: "Verify changed files, commit, and push to remote" +description: "Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes." user-invocable: false hooks: Stop: @@ -20,7 +20,7 @@ hooks: **Step 3/3** in **commit** workflow -> Run tests, lint, and commit code changes +> Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. ## Prerequisites (Verify First) @@ -29,7 +29,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Verify changed files, commit, and push to remote +**Goal**: Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes. # Commit and Push @@ -136,6 +136,13 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` **Required outputs**: - `changes_committed` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/commit.lint/SKILL.md b/.claude/skills/commit.lint/SKILL.md index 4cf371fa..4054abaa 100644 --- a/.claude/skills/commit.lint/SKILL.md +++ b/.claude/skills/commit.lint/SKILL.md @@ -1,6 +1,6 @@ --- name: commit.lint -description: "Format and lint code with ruff using a sub-agent" +description: "Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance." user-invocable: false hooks: Stop: @@ -19,7 +19,7 @@ hooks: **Step 2/3** in **commit** workflow -> Run tests, lint, and commit code changes +> Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. ## Prerequisites (Verify First) @@ -28,7 +28,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Format and lint code with ruff using a sub-agent +**Goal**: Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance. # Lint Code @@ -131,6 +131,13 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` **Required outputs**: - `code_formatted` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/commit.test/SKILL.md b/.claude/skills/commit.test/SKILL.md index 01359da5..5cfc1de9 100644 --- a/.claude/skills/commit.test/SKILL.md +++ b/.claude/skills/commit.test/SKILL.md @@ -1,6 +1,6 @@ --- name: commit.test -description: "Pull latest code and run the test suite until all tests pass" +description: "Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests." user-invocable: false hooks: Stop: @@ -20,12 +20,12 @@ hooks: **Step 1/3** in **commit** workflow -> Run tests, lint, and commit code changes +> Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. ## Instructions -**Goal**: Pull latest code and run the test suite until all tests pass +**Goal**: Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests. # Run Tests @@ -114,6 +114,13 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` **Required outputs**: - `tests_passing` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/commit/SKILL.md b/.claude/skills/commit/SKILL.md index 6e00ae7a..f7df4c7b 100644 --- a/.claude/skills/commit/SKILL.md +++ b/.claude/skills/commit/SKILL.md @@ -1,11 +1,11 @@ --- name: commit -description: "Run tests, lint, and commit code changes" +description: "Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks." --- # commit -**Multi-step workflow**: Run tests, lint, and commit code changes +**Multi-step workflow**: Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. > **CRITICAL**: Always invoke steps using the Skill tool. Never copy/paste step instructions directly. @@ -23,9 +23,9 @@ Steps: ## Available Steps -1. **test** - Pull latest code and run the test suite until all tests pass -2. **lint** - Format and lint code with ruff using a sub-agent (requires: test) -3. **commit_and_push** - Verify changed files, commit, and push to remote (requires: lint) +1. **test** - Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests. +2. **lint** - Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance. (requires: test) +3. **commit_and_push** - Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes. (requires: lint) ## Execution Instructions @@ -56,6 +56,13 @@ If user intent is unclear, use AskUserQuestion to clarify: - Present available steps as numbered options - Let user select the starting point +## Guardrails + +- Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps +- Do NOT skip steps in the workflow unless the user explicitly requests it +- Do NOT proceed to the next step if the current step's outputs are incomplete +- Do NOT make assumptions about user intent; ask for clarification when ambiguous + ## Context Files - Job definition: `.deepwork/jobs/commit/job.yml` \ No newline at end of file diff --git a/.claude/skills/deepwork_jobs.define/SKILL.md b/.claude/skills/deepwork_jobs.define/SKILL.md index e860b389..9f35d46f 100644 --- a/.claude/skills/deepwork_jobs.define/SKILL.md +++ b/.claude/skills/deepwork_jobs.define/SKILL.md @@ -1,6 +1,6 @@ --- name: deepwork_jobs.define -description: "Create the job.yml specification file by understanding workflow requirements" +description: "Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow." user-invocable: false hooks: Stop: @@ -40,12 +40,12 @@ hooks: **Step 1/4** in **deepwork_jobs** workflow -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Instructions -**Goal**: Create the job.yml specification file by understanding workflow requirements +**Goal**: Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow. # Define Job Specification @@ -659,6 +659,13 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/deepwork_jobs.implement/SKILL.md b/.claude/skills/deepwork_jobs.implement/SKILL.md index 45a57f0e..28af7b70 100644 --- a/.claude/skills/deepwork_jobs.implement/SKILL.md +++ b/.claude/skills/deepwork_jobs.implement/SKILL.md @@ -1,6 +1,6 @@ --- name: deepwork_jobs.implement -description: "Generate instruction files for each step based on the job.yml specification" +description: "Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes." user-invocable: false hooks: Stop: @@ -37,7 +37,7 @@ hooks: **Step 3/4** in **deepwork_jobs** workflow -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Prerequisites (Verify First) @@ -46,7 +46,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Generate instruction files for each step based on the job.yml specification +**Goal**: Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. # Implement Job Steps @@ -320,6 +320,13 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` **Required outputs**: - `steps/` (directory) +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/deepwork_jobs.learn/SKILL.md b/.claude/skills/deepwork_jobs.learn/SKILL.md index 9021434f..76013c97 100644 --- a/.claude/skills/deepwork_jobs.learn/SKILL.md +++ b/.claude/skills/deepwork_jobs.learn/SKILL.md @@ -1,6 +1,6 @@ --- name: deepwork_jobs.learn -description: "Reflect on conversation to improve job instructions and capture learnings" +description: "Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it." hooks: Stop: - hooks: @@ -39,12 +39,12 @@ hooks: **Standalone skill** - can be run anytime -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Instructions -**Goal**: Reflect on conversation to improve job instructions and capture learnings +**Goal**: Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it. # Learn from Job Execution @@ -436,6 +436,13 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` **Required outputs**: - `AGENTS.md` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md b/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md index 665452a4..3aa92898 100644 --- a/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md +++ b/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md @@ -1,6 +1,6 @@ --- name: deepwork_jobs.review_job_spec -description: "Use sub-agent to review job.yml against doc spec quality criteria" +description: "Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification." user-invocable: false hooks: Stop: @@ -32,7 +32,7 @@ hooks: **Step 2/4** in **deepwork_jobs** workflow -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Prerequisites (Verify First) @@ -41,7 +41,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Use sub-agent to review job.yml against doc spec quality criteria +**Goal**: Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. # Review Job Specification @@ -468,6 +468,13 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/deepwork_jobs/SKILL.md b/.claude/skills/deepwork_jobs/SKILL.md index 5212e48e..00f2bb48 100644 --- a/.claude/skills/deepwork_jobs/SKILL.md +++ b/.claude/skills/deepwork_jobs/SKILL.md @@ -1,11 +1,11 @@ --- name: deepwork_jobs -description: "DeepWork job management commands" +description: "Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs." --- # deepwork_jobs -**Multi-step workflow**: DeepWork job management commands +**Multi-step workflow**: Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. > **CRITICAL**: Always invoke steps using the Skill tool. Never copy/paste step instructions directly. @@ -23,10 +23,10 @@ learnings specific to the current run into AGENTS.md files in the working folder ## Available Steps -1. **define** - Create the job.yml specification file by understanding workflow requirements -2. **review_job_spec** - Use sub-agent to review job.yml against doc spec quality criteria (requires: define) -3. **implement** - Generate instruction files for each step based on the job.yml specification (requires: review_job_spec) -4. **learn** - Reflect on conversation to improve job instructions and capture learnings +1. **define** - Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow. +2. **review_job_spec** - Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. (requires: define) +3. **implement** - Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. (requires: review_job_spec) +4. **learn** - Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it. ## Execution Instructions @@ -58,6 +58,13 @@ If user intent is unclear, use AskUserQuestion to clarify: - Present available steps as numbered options - Let user select the starting point +## Guardrails + +- Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps +- Do NOT skip steps in the workflow unless the user explicitly requests it +- Do NOT proceed to the next step if the current step's outputs are incomplete +- Do NOT make assumptions about user intent; ask for clarification when ambiguous + ## Context Files - Job definition: `.deepwork/jobs/deepwork_jobs/job.yml` \ No newline at end of file diff --git a/.claude/skills/deepwork_rules.define/SKILL.md b/.claude/skills/deepwork_rules.define/SKILL.md index 4dfe811f..25cf1892 100644 --- a/.claude/skills/deepwork_rules.define/SKILL.md +++ b/.claude/skills/deepwork_rules.define/SKILL.md @@ -1,6 +1,6 @@ --- name: deepwork_rules.define -description: "Create a new rule file in .deepwork/rules/" +description: "Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands." user-invocable: false --- @@ -8,12 +8,12 @@ user-invocable: false **Standalone skill** - can be run anytime -> Rules enforcement for AI agent sessions +> Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers. ## Instructions -**Goal**: Create a new rule file in .deepwork/rules/ +**Goal**: Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands. # Define Rule @@ -311,6 +311,13 @@ Use branch format: `deepwork/deepwork_rules-[instance]-YYYYMMDD` **Required outputs**: - `.deepwork/rules/{rule-name}.md` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/deepwork_rules/SKILL.md b/.claude/skills/deepwork_rules/SKILL.md index 8ea6f216..cfc42720 100644 --- a/.claude/skills/deepwork_rules/SKILL.md +++ b/.claude/skills/deepwork_rules/SKILL.md @@ -1,11 +1,11 @@ --- name: deepwork_rules -description: "Rules enforcement for AI agent sessions" +description: "Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers." --- # deepwork_rules -**Multi-step workflow**: Rules enforcement for AI agent sessions +**Multi-step workflow**: Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers. > **CRITICAL**: Always invoke steps using the Skill tool. Never copy/paste step instructions directly. @@ -36,7 +36,7 @@ Example use cases: ## Available Steps -1. **define** - Create a new rule file in .deepwork/rules/ +1. **define** - Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands. ## Execution Instructions @@ -65,6 +65,13 @@ If user intent is unclear, use AskUserQuestion to clarify: - Present available steps as numbered options - Let user select the starting point +## Guardrails + +- Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps +- Do NOT skip steps in the workflow unless the user explicitly requests it +- Do NOT proceed to the next step if the current step's outputs are incomplete +- Do NOT make assumptions about user intent; ask for clarification when ambiguous + ## Context Files - Job definition: `.deepwork/jobs/deepwork_rules/job.yml` \ No newline at end of file diff --git a/.claude/skills/update.job/SKILL.md b/.claude/skills/update.job/SKILL.md index 3e972cd8..60038425 100644 --- a/.claude/skills/update.job/SKILL.md +++ b/.claude/skills/update.job/SKILL.md @@ -1,6 +1,6 @@ --- name: update.job -description: "Edit standard job source files and sync to installed locations" +description: "Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions." user-invocable: false hooks: Stop: @@ -20,12 +20,12 @@ hooks: **Standalone skill** - can be run anytime -> Update standard jobs in src/ and sync to installed locations +> Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules. ## Instructions -**Goal**: Edit standard job source files and sync to installed locations +**Goal**: Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions. # Update Standard Job @@ -137,6 +137,13 @@ Use branch format: `deepwork/update-[instance]-YYYYMMDD` **Required outputs**: - `files_synced` +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + ## Quality Validation Stop hooks will automatically validate your work. The loop continues until all criteria pass. diff --git a/.claude/skills/update/SKILL.md b/.claude/skills/update/SKILL.md index b0cf11f9..e4cbc26d 100644 --- a/.claude/skills/update/SKILL.md +++ b/.claude/skills/update/SKILL.md @@ -1,11 +1,11 @@ --- name: update -description: "Update standard jobs in src/ and sync to installed locations" +description: "Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules." --- # update -**Multi-step workflow**: Update standard jobs in src/ and sync to installed locations +**Multi-step workflow**: Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules. > **CRITICAL**: Always invoke steps using the Skill tool. Never copy/paste step instructions directly. @@ -26,7 +26,7 @@ for any standard job in the DeepWork repository. ## Available Steps -1. **job** - Edit standard job source files and sync to installed locations +1. **job** - Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions. ## Execution Instructions @@ -55,6 +55,13 @@ If user intent is unclear, use AskUserQuestion to clarify: - Present available steps as numbered options - Let user select the starting point +## Guardrails + +- Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps +- Do NOT skip steps in the workflow unless the user explicitly requests it +- Do NOT proceed to the next step if the current step's outputs are incomplete +- Do NOT make assumptions about user intent; ask for clarification when ambiguous + ## Context Files - Job definition: `.deepwork/jobs/update/job.yml` \ No newline at end of file diff --git a/.deepwork/doc_specs/claude_code_skill.md b/.deepwork/doc_specs/claude_code_skill.md new file mode 100644 index 00000000..6ba57e64 --- /dev/null +++ b/.deepwork/doc_specs/claude_code_skill.md @@ -0,0 +1,183 @@ +--- +name: "Claude Code Skill Definition" +description: "A SKILL.md file that defines a Claude Code skill with metadata, instructions, and examples" +path_patterns: + - ".claude/skills/*/SKILL.md" + - ".claude/skills/**/SKILL.md" +target_audience: "Claude Code agents auto-selecting skills based on user intent" +frequency: "Created once per skill, updated as requirements evolve" +quality_criteria: + - name: Kebab-Case Name + description: "Skill name must be lowercase with hyphens only (e.g., `github-pr-review`, `unit-test-generator`). No underscores, spaces, or reserved words like `anthropic`, `claude`, or `general`." + - name: Third-Person Description + description: "Description must be written in third person (e.g., 'Generates...' not 'I generate...'). Under 300 characters. Must clearly state WHAT the skill does and WHEN to use it." + - name: Discoverable Keywords + description: "Description must include specific technical terms a user might say (e.g., 'PostgreSQL', 'React components', 'AWS Lambda') to enable reliable auto-selection." + - name: Progressive Disclosure + description: "Main SKILL.md file must be under 500 lines. Large reference docs or schemas must be split into separate support files loaded on demand." + - name: Input Handling + description: "Must clearly define required inputs before execution begins. Instructions must tell Claude to ask the user for missing inputs rather than guessing." + - name: Output Format + description: "Must explicitly state how output should be formatted (e.g., 'Output as a JSON block' or 'Create a markdown file at path X')." + - name: Worked Example + description: "Must include at least one Input -> Output example showing the ideal result. Few-shot examples significantly reduce hallucinations." + - name: Guardrails Section + description: "Must include a section listing what Claude should NOT do (e.g., 'Do not delete existing comments', 'Do not mock database connections')." + - name: Concrete File References + description: "Instructions must use specific file paths, not vague descriptions (e.g., 'Read src/config.json' not 'Read the config file')." + - name: Plan Before Action + description: "For complex tasks, instructions must include an analysis/planning step before implementation begins." +--- + +# Claude Code Skill Definition: [skill-name] + +A `SKILL.md` file defines a skill that Claude Code can auto-select based on user intent. Unlike slash commands (invoked explicitly via `/command`), skills are discovered and triggered automatically when Claude determines they match the user's request. + +## File Structure + +``` +.claude/ +└── skills/ + ├── database-migration/ # Skill directory (kebab-case) + │ ├── SKILL.md # Entry point (required) + │ └── schema-reference.txt # Support file (loaded on demand) + └── code-reviewer/ + └── SKILL.md +``` + +## SKILL.md Format + +### Frontmatter (Required) + +```yaml +--- +name: database-migration +description: "Generates database migration files for schema changes. Use when adding, modifying, or removing database tables or columns." +--- +``` + +### Body (Instructions) + +The markdown body instructs Claude how to execute the skill once selected. + +## Example: Complete Skill Definition + +```markdown +--- +name: github-pr-review +description: "Reviews GitHub pull requests for code quality, security issues, and adherence to project conventions. Use when the user mentions reviewing a PR, code review, or asks about changes in a pull request." +--- + +# github-pr-review + +Reviews GitHub pull requests and provides structured feedback. + +## Required Inputs + +Before proceeding, ensure you have: +1. PR number or URL (ask user if not provided) +2. Review focus areas (optional: security, performance, style) + +## Execution Steps + +### Step 1: Analyze PR Context + +Fetch the PR details and understand: +- Files changed and their purposes +- Base branch and target branch +- Related issues or requirements + +### Step 2: Review Code Changes + +For each changed file: +1. Check for security vulnerabilities +2. Verify error handling +3. Assess test coverage +4. Review naming conventions +5. Identify performance concerns + +### Step 3: Generate Review + +Create a structured review with: +- Summary of changes +- Critical issues (must fix) +- Suggestions (nice to have) +- Questions for the author + +## Example + +**Input:** "Review PR #42" + +**Output:** + +## PR #42 Review: Add user authentication + +### Summary +This PR adds JWT-based authentication to the API endpoints. + +### Critical Issues +1. **Line 45 in auth.js**: Token expiration not validated before use +2. **Line 89 in middleware.js**: Missing rate limiting on login endpoint + +### Suggestions +- Consider adding refresh token rotation +- Add integration tests for the auth flow + +### Questions +- Should failed login attempts trigger account lockout? + +## Guardrails + +- Do NOT approve or merge PRs automatically +- Do NOT modify code in the PR +- Do NOT dismiss existing reviews +- Do NOT share sensitive information found in code +``` + +## Naming Conventions + +| Bad Name | Good Name | Why? | +|----------|-----------|------| +| `github` | `github-pr-review` | "github" is too broad; be specific about the action | +| `process_data` | `csv-data-processor` | Use hyphens, not underscores; specify the data type | +| `my-tool` | `unit-test-generator` | Generic names are not discoverable; describe the output | +| `claude-helper` | `api-error-analyzer` | Avoid reserved words; focus on functionality | + +## Description Best Practices + +### Good Description +> "Generates database migration files from schema changes. Use when the user needs to add columns, create tables, or modify database structure." + +### Poor Description +> "You can use this to help with database stuff." + +### What Makes a Good Description + +1. **Third person voice**: "Generates..." not "I generate..." +2. **Specific action**: "migration files" not "database stuff" +3. **Clear trigger**: "Use when..." clause +4. **Technical keywords**: Terms users actually say + +## Subagent Delegation + +For tasks requiring extensive file reading or research, delegate to a subagent to preserve context: + +```markdown +## Step 2: Analyze Codebase + +Create a subagent to: +1. Scan the `src/` directory for circular dependencies +2. Identify unused exports +3. Return only a summary, not full file contents + +This prevents the main context from being polluted with irrelevant code. +``` + +## Testing Checklist + +Before publishing, verify: + +- [ ] **Discovery Test**: Clear history, ask a vague related question. Does the skill trigger? +- [ ] **Argument Test**: Omit a required input. Does Claude ask for it? +- [ ] **Negative Test**: Ask something outside scope. Does the skill stay silent? +- [ ] **Edge Case Test**: Empty inputs, large inputs, malformed data handled? diff --git a/.deepwork/jobs/add_platform/job.yml b/.deepwork/jobs/add_platform/job.yml index f42cc5a3..ead4b005 100644 --- a/.deepwork/jobs/add_platform/job.yml +++ b/.deepwork/jobs/add_platform/job.yml @@ -1,6 +1,6 @@ name: add_platform -version: "0.2.0" -summary: "Add a new AI platform to DeepWork with adapter, templates, and tests" +version: "0.3.0" +summary: "Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools." description: | A workflow for adding support for a new AI platform (like Cursor, Windsurf, etc.) to DeepWork. @@ -25,11 +25,13 @@ changelog: changes: "Initial version" - version: "0.2.0" changes: "Added verification_checklist.md output to verify step for doc spec compliance" + - version: "0.3.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: research name: "Research Platform Documentation" - description: "Capture CLI configuration and hooks system documentation for the new platform" + description: "Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration." instructions_file: steps/research.md inputs: - name: platform_name @@ -55,7 +57,7 @@ steps: - id: add_capabilities name: "Add Hook Capabilities" - description: "Update job schema and adapters with any new hook events the platform supports" + description: "Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system." instructions_file: steps/add_capabilities.md inputs: - file: hooks_system.md @@ -81,7 +83,7 @@ steps: - id: implement name: "Implement Platform Support" - description: "Add platform adapter, templates, tests with 100% coverage, and README documentation" + description: "Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities." instructions_file: steps/implement.md inputs: - file: job_schema.py @@ -116,7 +118,7 @@ steps: - id: verify name: "Verify Installation" - description: "Set up platform directories and verify deepwork install works correctly" + description: "Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration." instructions_file: steps/verify.md inputs: - file: templates/ diff --git a/.deepwork/jobs/commit/job.yml b/.deepwork/jobs/commit/job.yml index 6ebe13b1..f57c29a6 100644 --- a/.deepwork/jobs/commit/job.yml +++ b/.deepwork/jobs/commit/job.yml @@ -1,6 +1,6 @@ name: commit -version: "1.1.0" -summary: "Run tests, lint, and commit code changes" +version: "1.2.0" +summary: "Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks." description: | A workflow for preparing and committing code changes with quality checks. @@ -20,11 +20,13 @@ changelog: changes: "Initial job creation" - version: "1.1.0" changes: "Added nominal outputs to process-oriented steps for doc spec compliance (tests_passing, code_formatted, changes_committed)" + - version: "1.2.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: test name: "Run Tests" - description: "Pull latest code and run the test suite until all tests pass" + description: "Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests." instructions_file: steps/test.md inputs: - name: test_command @@ -44,7 +46,7 @@ steps: - id: lint name: "Lint Code" - description: "Format and lint code with ruff using a sub-agent" + description: "Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance." instructions_file: steps/lint.md inputs: [] outputs: @@ -62,7 +64,7 @@ steps: - id: commit_and_push name: "Commit and Push" - description: "Verify changed files, commit, and push to remote" + description: "Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes." instructions_file: steps/commit_and_push.md inputs: [] outputs: diff --git a/.deepwork/jobs/deepwork_jobs/job.yml b/.deepwork/jobs/deepwork_jobs/job.yml index 9236540c..1c74d3f6 100644 --- a/.deepwork/jobs/deepwork_jobs/job.yml +++ b/.deepwork/jobs/deepwork_jobs/job.yml @@ -1,6 +1,6 @@ name: deepwork_jobs -version: "0.8.0" -summary: "DeepWork job management commands" +version: "0.9.0" +summary: "Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs." description: | Core commands for managing DeepWork jobs. These commands help you define new multi-step workflows and learn from running them. @@ -30,11 +30,13 @@ changelog: changes: "Added job.yml doc spec; define step now outputs job.yml with document_type reference for quality validation" - version: "0.8.0" changes: "Added review_job_spec step between define and implement for doc spec-based quality validation using sub-agent review" + - version: "0.9.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: define name: "Define Job Specification" - description: "Create the job.yml specification file by understanding workflow requirements" + description: "Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow." instructions_file: steps/define.md inputs: - name: job_purpose @@ -59,7 +61,7 @@ steps: - id: review_job_spec name: "Review Job Specification" - description: "Use sub-agent to review job.yml against doc spec quality criteria" + description: "Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification." instructions_file: steps/review_job_spec.md inputs: - file: job.yml @@ -77,7 +79,7 @@ steps: - id: implement name: "Implement Job Steps" - description: "Generate instruction files for each step based on the job.yml specification" + description: "Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes." instructions_file: steps/implement.md inputs: - file: job.yml @@ -99,7 +101,7 @@ steps: - id: learn name: "Learn from Job Execution" - description: "Reflect on conversation to improve job instructions and capture learnings" + description: "Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it." instructions_file: steps/learn.md exposed: true inputs: diff --git a/.deepwork/jobs/deepwork_rules/hooks/capture_prompt_work_tree.sh b/.deepwork/jobs/deepwork_rules/hooks/capture_prompt_work_tree.sh index c9cedd82..3f2cefad 100755 --- a/.deepwork/jobs/deepwork_rules/hooks/capture_prompt_work_tree.sh +++ b/.deepwork/jobs/deepwork_rules/hooks/capture_prompt_work_tree.sh @@ -8,20 +8,12 @@ # The baseline contains ALL tracked files (not just changed files) so that # the rules_check hook can determine which files are genuinely new vs which # files existed before and were just modified. -# -# It also captures the HEAD commit ref so that committed changes can be detected -# by comparing HEAD at Stop time to the captured ref. set -e # Ensure .deepwork directory exists mkdir -p .deepwork -# Save the current HEAD commit ref for detecting committed changes -# This is used by get_changed_files_prompt() to detect files changed since prompt, -# even if those changes were committed during the agent response. -git rev-parse HEAD > .deepwork/.last_head_ref 2>/dev/null || echo "" > .deepwork/.last_head_ref - # Save ALL tracked files (not just changed files) # This is critical for created: mode rules to distinguish between: # - Newly created files (not in baseline) -> should trigger created: rules diff --git a/.deepwork/jobs/deepwork_rules/job.yml b/.deepwork/jobs/deepwork_rules/job.yml index 56caa953..a0032b9e 100644 --- a/.deepwork/jobs/deepwork_rules/job.yml +++ b/.deepwork/jobs/deepwork_rules/job.yml @@ -1,6 +1,6 @@ name: deepwork_rules -version: "0.3.0" -summary: "Rules enforcement for AI agent sessions" +version: "0.4.0" +summary: "Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers." description: | Manages rules that automatically trigger when certain files change during an AI agent session. Rules help ensure that code changes follow team guidelines, documentation is updated, @@ -33,11 +33,13 @@ changelog: changes: "Standardized on 'ask structured questions' phrasing for user input" - version: "0.3.0" changes: "Migrated to v2 format - individual markdown files in .deepwork/rules/" + - version: "0.4.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: define name: "Define Rule" - description: "Create a new rule file in .deepwork/rules/" + description: "Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands." instructions_file: steps/define.md inputs: - name: rule_purpose diff --git a/.deepwork/jobs/update/job.yml b/.deepwork/jobs/update/job.yml index afcc1aec..98715431 100644 --- a/.deepwork/jobs/update/job.yml +++ b/.deepwork/jobs/update/job.yml @@ -1,6 +1,6 @@ name: update -version: "1.2.0" -summary: "Update standard jobs in src/ and sync to installed locations" +version: "1.3.0" +summary: "Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules." description: | A workflow for maintaining standard jobs bundled with DeepWork. Standard jobs (like `deepwork_jobs` and `deepwork_rules`) are source-controlled in @@ -23,11 +23,13 @@ changelog: changes: "Removed sync_verification.md output requirement" - version: "1.2.0" changes: "Added nominal output for doc spec compliance (files_synced)" + - version: "1.3.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: job name: "Update Standard Job" - description: "Edit standard job source files and sync to installed locations" + description: "Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions." instructions_file: steps/job.md inputs: - name: job_context diff --git a/.gemini/skills/add_platform/add_capabilities.toml b/.gemini/skills/add_platform/add_capabilities.toml index 5593e530..1860b3ea 100644 --- a/.gemini/skills/add_platform/add_capabilities.toml +++ b/.gemini/skills/add_platform/add_capabilities.toml @@ -1,17 +1,17 @@ # add_platform:add_capabilities # -# Update job schema and adapters with any new hook events the platform supports +# Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system. # # Generated by DeepWork - do not edit manually -description = "Update job schema and adapters with any new hook events the platform supports" +description = "Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system." prompt = """ # add_platform:add_capabilities **Step 2/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Prerequisites (Verify First) @@ -20,7 +20,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Update job schema and adapters with any new hook events the platform supports +**Goal**: Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system. # Add Hook Capabilities diff --git a/.gemini/skills/add_platform/implement.toml b/.gemini/skills/add_platform/implement.toml index 222f63c9..a6462592 100644 --- a/.gemini/skills/add_platform/implement.toml +++ b/.gemini/skills/add_platform/implement.toml @@ -1,17 +1,17 @@ # add_platform:implement # -# Add platform adapter, templates, tests with 100% coverage, and README documentation +# Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities. # # Generated by DeepWork - do not edit manually -description = "Add platform adapter, templates, tests with 100% coverage, and README documentation" +description = "Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities." prompt = """ # add_platform:implement **Step 3/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Prerequisites (Verify First) @@ -21,7 +21,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Add platform adapter, templates, tests with 100% coverage, and README documentation +**Goal**: Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities. # Implement Platform Support diff --git a/.gemini/skills/add_platform/index.toml b/.gemini/skills/add_platform/index.toml index ff3c4ce3..878f6600 100644 --- a/.gemini/skills/add_platform/index.toml +++ b/.gemini/skills/add_platform/index.toml @@ -1,15 +1,15 @@ # add_platform # -# Add a new AI platform to DeepWork with adapter, templates, and tests +# Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. # # Generated by DeepWork - do not edit manually -description = "Add a new AI platform to DeepWork with adapter, templates, and tests" +description = "Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools." prompt = """ # add_platform -**Multi-step workflow**: Add a new AI platform to DeepWork with adapter, templates, and tests +**Multi-step workflow**: Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. > **NOTE**: Gemini CLI requires manual command invocation. After each step, tell the user which command to run next. @@ -33,13 +33,13 @@ comprehensive test coverage for new functionality. ## Available Steps -1. **research** - Capture CLI configuration and hooks system documentation for the new platform +1. **research** - Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration. Command: `/add_platform:research` -2. **add_capabilities** - Update job schema and adapters with any new hook events the platform supports (requires: research) +2. **add_capabilities** - Updates job schema and adapters with any new hook events the platform supports. Use after research to extend DeepWork's hook system. (requires: research) Command: `/add_platform:add_capabilities` -3. **implement** - Add platform adapter, templates, tests with 100% coverage, and README documentation (requires: research, add_capabilities) +3. **implement** - Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities. (requires: research, add_capabilities) Command: `/add_platform:implement` -4. **verify** - Set up platform directories and verify deepwork install works correctly (requires: implement) +4. **verify** - Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration. (requires: implement) Command: `/add_platform:verify` ## Execution Instructions diff --git a/.gemini/skills/add_platform/research.toml b/.gemini/skills/add_platform/research.toml index 98b32d9b..0c2cd5ae 100644 --- a/.gemini/skills/add_platform/research.toml +++ b/.gemini/skills/add_platform/research.toml @@ -1,22 +1,22 @@ # add_platform:research # -# Capture CLI configuration and hooks system documentation for the new platform +# Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration. # # Generated by DeepWork - do not edit manually -description = "Capture CLI configuration and hooks system documentation for the new platform" +description = "Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration." prompt = """ # add_platform:research **Step 1/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Instructions -**Goal**: Capture CLI configuration and hooks system documentation for the new platform +**Goal**: Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration. # Research Platform Documentation diff --git a/.gemini/skills/add_platform/verify.toml b/.gemini/skills/add_platform/verify.toml index 905ac5e1..368c6dc7 100644 --- a/.gemini/skills/add_platform/verify.toml +++ b/.gemini/skills/add_platform/verify.toml @@ -1,17 +1,17 @@ # add_platform:verify # -# Set up platform directories and verify deepwork install works correctly +# Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration. # # Generated by DeepWork - do not edit manually -description = "Set up platform directories and verify deepwork install works correctly" +description = "Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration." prompt = """ # add_platform:verify **Step 4/4** in **add_platform** workflow -> Add a new AI platform to DeepWork with adapter, templates, and tests +> Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. ## Prerequisites (Verify First) @@ -20,7 +20,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Set up platform directories and verify deepwork install works correctly +**Goal**: Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration. # Verify Installation diff --git a/.gemini/skills/commit/commit_and_push.toml b/.gemini/skills/commit/commit_and_push.toml index 9178fb37..3cdaae8b 100644 --- a/.gemini/skills/commit/commit_and_push.toml +++ b/.gemini/skills/commit/commit_and_push.toml @@ -1,17 +1,17 @@ # commit:commit_and_push # -# Verify changed files, commit, and push to remote +# Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes. # # Generated by DeepWork - do not edit manually -description = "Verify changed files, commit, and push to remote" +description = "Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes." prompt = """ # commit:commit_and_push **Step 3/3** in **commit** workflow -> Run tests, lint, and commit code changes +> Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. ## Prerequisites (Verify First) @@ -20,7 +20,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Verify changed files, commit, and push to remote +**Goal**: Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes. # Commit and Push diff --git a/.gemini/skills/commit/index.toml b/.gemini/skills/commit/index.toml index 3b53e542..2d795c99 100644 --- a/.gemini/skills/commit/index.toml +++ b/.gemini/skills/commit/index.toml @@ -1,15 +1,15 @@ # commit # -# Run tests, lint, and commit code changes +# Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. # # Generated by DeepWork - do not edit manually -description = "Run tests, lint, and commit code changes" +description = "Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks." prompt = """ # commit -**Multi-step workflow**: Run tests, lint, and commit code changes +**Multi-step workflow**: Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. > **NOTE**: Gemini CLI requires manual command invocation. After each step, tell the user which command to run next. @@ -27,11 +27,11 @@ Steps: ## Available Steps -1. **test** - Pull latest code and run the test suite until all tests pass +1. **test** - Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests. Command: `/commit:test` -2. **lint** - Format and lint code with ruff using a sub-agent (requires: test) +2. **lint** - Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance. (requires: test) Command: `/commit:lint` -3. **commit_and_push** - Verify changed files, commit, and push to remote (requires: lint) +3. **commit_and_push** - Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes. (requires: lint) Command: `/commit:commit_and_push` ## Execution Instructions diff --git a/.gemini/skills/commit/lint.toml b/.gemini/skills/commit/lint.toml index c2326d26..45f57f99 100644 --- a/.gemini/skills/commit/lint.toml +++ b/.gemini/skills/commit/lint.toml @@ -1,17 +1,17 @@ # commit:lint # -# Format and lint code with ruff using a sub-agent +# Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance. # # Generated by DeepWork - do not edit manually -description = "Format and lint code with ruff using a sub-agent" +description = "Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance." prompt = """ # commit:lint **Step 2/3** in **commit** workflow -> Run tests, lint, and commit code changes +> Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. ## Prerequisites (Verify First) @@ -20,7 +20,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Format and lint code with ruff using a sub-agent +**Goal**: Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance. # Lint Code diff --git a/.gemini/skills/commit/test.toml b/.gemini/skills/commit/test.toml index d88b6911..6c4be623 100644 --- a/.gemini/skills/commit/test.toml +++ b/.gemini/skills/commit/test.toml @@ -1,22 +1,22 @@ # commit:test # -# Pull latest code and run the test suite until all tests pass +# Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests. # # Generated by DeepWork - do not edit manually -description = "Pull latest code and run the test suite until all tests pass" +description = "Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests." prompt = """ # commit:test **Step 1/3** in **commit** workflow -> Run tests, lint, and commit code changes +> Runs tests, lints code, and commits changes. Use when ready to commit work with quality checks. ## Instructions -**Goal**: Pull latest code and run the test suite until all tests pass +**Goal**: Pulls latest code and runs tests until all pass. Use when starting the commit workflow or re-running tests. # Run Tests diff --git a/.gemini/skills/deepwork_jobs/define.toml b/.gemini/skills/deepwork_jobs/define.toml index 8abbeb58..a01f9b53 100644 --- a/.gemini/skills/deepwork_jobs/define.toml +++ b/.gemini/skills/deepwork_jobs/define.toml @@ -1,22 +1,22 @@ # deepwork_jobs:define # -# Create the job.yml specification file by understanding workflow requirements +# Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow. # # Generated by DeepWork - do not edit manually -description = "Create the job.yml specification file by understanding workflow requirements" +description = "Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow." prompt = """ # deepwork_jobs:define **Step 1/4** in **deepwork_jobs** workflow -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Instructions -**Goal**: Create the job.yml specification file by understanding workflow requirements +**Goal**: Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow. # Define Job Specification diff --git a/.gemini/skills/deepwork_jobs/implement.toml b/.gemini/skills/deepwork_jobs/implement.toml index 402fde9e..f0059d3e 100644 --- a/.gemini/skills/deepwork_jobs/implement.toml +++ b/.gemini/skills/deepwork_jobs/implement.toml @@ -1,17 +1,17 @@ # deepwork_jobs:implement # -# Generate instruction files for each step based on the job.yml specification +# Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. # # Generated by DeepWork - do not edit manually -description = "Generate instruction files for each step based on the job.yml specification" +description = "Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes." prompt = """ # deepwork_jobs:implement **Step 3/4** in **deepwork_jobs** workflow -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Prerequisites (Verify First) @@ -20,7 +20,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Generate instruction files for each step based on the job.yml specification +**Goal**: Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. # Implement Job Steps diff --git a/.gemini/skills/deepwork_jobs/index.toml b/.gemini/skills/deepwork_jobs/index.toml index 890f490e..b609025d 100644 --- a/.gemini/skills/deepwork_jobs/index.toml +++ b/.gemini/skills/deepwork_jobs/index.toml @@ -1,15 +1,15 @@ # deepwork_jobs # -# DeepWork job management commands +# Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. # # Generated by DeepWork - do not edit manually -description = "DeepWork job management commands" +description = "Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs." prompt = """ # deepwork_jobs -**Multi-step workflow**: DeepWork job management commands +**Multi-step workflow**: Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. > **NOTE**: Gemini CLI requires manual command invocation. After each step, tell the user which command to run next. @@ -27,13 +27,13 @@ learnings specific to the current run into AGENTS.md files in the working folder ## Available Steps -1. **define** - Create the job.yml specification file by understanding workflow requirements +1. **define** - Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow. Command: `/deepwork_jobs:define` -2. **review_job_spec** - Use sub-agent to review job.yml against doc spec quality criteria (requires: define) +2. **review_job_spec** - Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. (requires: define) Command: `/deepwork_jobs:review_job_spec` -3. **implement** - Generate instruction files for each step based on the job.yml specification (requires: review_job_spec) +3. **implement** - Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes. (requires: review_job_spec) Command: `/deepwork_jobs:implement` -4. **learn** - Reflect on conversation to improve job instructions and capture learnings +4. **learn** - Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it. Command: `/deepwork_jobs:learn` ## Execution Instructions diff --git a/.gemini/skills/deepwork_jobs/learn.toml b/.gemini/skills/deepwork_jobs/learn.toml index 8b88ca66..7dabfff1 100644 --- a/.gemini/skills/deepwork_jobs/learn.toml +++ b/.gemini/skills/deepwork_jobs/learn.toml @@ -1,22 +1,22 @@ # deepwork_jobs:learn # -# Reflect on conversation to improve job instructions and capture learnings +# Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it. # # Generated by DeepWork - do not edit manually -description = "Reflect on conversation to improve job instructions and capture learnings" +description = "Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it." prompt = """ # deepwork_jobs:learn **Standalone command** - can be run anytime -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Instructions -**Goal**: Reflect on conversation to improve job instructions and capture learnings +**Goal**: Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it. # Learn from Job Execution diff --git a/.gemini/skills/deepwork_jobs/review_job_spec.toml b/.gemini/skills/deepwork_jobs/review_job_spec.toml index 013eddec..77923d8a 100644 --- a/.gemini/skills/deepwork_jobs/review_job_spec.toml +++ b/.gemini/skills/deepwork_jobs/review_job_spec.toml @@ -1,17 +1,17 @@ # deepwork_jobs:review_job_spec # -# Use sub-agent to review job.yml against doc spec quality criteria +# Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. # # Generated by DeepWork - do not edit manually -description = "Use sub-agent to review job.yml against doc spec quality criteria" +description = "Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification." prompt = """ # deepwork_jobs:review_job_spec **Step 2/4** in **deepwork_jobs** workflow -> DeepWork job management commands +> Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs. ## Prerequisites (Verify First) @@ -20,7 +20,7 @@ Before proceeding, confirm these steps are complete: ## Instructions -**Goal**: Use sub-agent to review job.yml against doc spec quality criteria +**Goal**: Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification. # Review Job Specification diff --git a/.gemini/skills/deepwork_rules/define.toml b/.gemini/skills/deepwork_rules/define.toml index 2e558791..980ad931 100644 --- a/.gemini/skills/deepwork_rules/define.toml +++ b/.gemini/skills/deepwork_rules/define.toml @@ -1,22 +1,22 @@ # deepwork_rules:define # -# Create a new rule file in .deepwork/rules/ +# Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands. # # Generated by DeepWork - do not edit manually -description = "Create a new rule file in .deepwork/rules/" +description = "Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands." prompt = """ # deepwork_rules:define **Standalone command** - can be run anytime -> Rules enforcement for AI agent sessions +> Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers. ## Instructions -**Goal**: Create a new rule file in .deepwork/rules/ +**Goal**: Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands. # Define Rule diff --git a/.gemini/skills/deepwork_rules/index.toml b/.gemini/skills/deepwork_rules/index.toml index a4c2ed02..51fca30e 100644 --- a/.gemini/skills/deepwork_rules/index.toml +++ b/.gemini/skills/deepwork_rules/index.toml @@ -1,15 +1,15 @@ # deepwork_rules # -# Rules enforcement for AI agent sessions +# Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers. # # Generated by DeepWork - do not edit manually -description = "Rules enforcement for AI agent sessions" +description = "Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers." prompt = """ # deepwork_rules -**Multi-step workflow**: Rules enforcement for AI agent sessions +**Multi-step workflow**: Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers. > **NOTE**: Gemini CLI requires manual command invocation. After each step, tell the user which command to run next. @@ -40,7 +40,7 @@ Example use cases: ## Available Steps -1. **define** - Create a new rule file in .deepwork/rules/ +1. **define** - Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands. Command: `/deepwork_rules:define` ## Execution Instructions diff --git a/.gemini/skills/update/index.toml b/.gemini/skills/update/index.toml index 2e2bcc0e..ebf3fa03 100644 --- a/.gemini/skills/update/index.toml +++ b/.gemini/skills/update/index.toml @@ -1,15 +1,15 @@ # update # -# Update standard jobs in src/ and sync to installed locations +# Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules. # # Generated by DeepWork - do not edit manually -description = "Update standard jobs in src/ and sync to installed locations" +description = "Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules." prompt = """ # update -**Multi-step workflow**: Update standard jobs in src/ and sync to installed locations +**Multi-step workflow**: Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules. > **NOTE**: Gemini CLI requires manual command invocation. After each step, tell the user which command to run next. @@ -30,7 +30,7 @@ for any standard job in the DeepWork repository. ## Available Steps -1. **job** - Edit standard job source files and sync to installed locations +1. **job** - Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions. Command: `/update:job` ## Execution Instructions diff --git a/.gemini/skills/update/job.toml b/.gemini/skills/update/job.toml index 4296e0e0..a42f20fb 100644 --- a/.gemini/skills/update/job.toml +++ b/.gemini/skills/update/job.toml @@ -1,22 +1,22 @@ # update:job # -# Edit standard job source files and sync to installed locations +# Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions. # # Generated by DeepWork - do not edit manually -description = "Edit standard job source files and sync to installed locations" +description = "Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions." prompt = """ # update:job **Standalone command** - can be run anytime -> Update standard jobs in src/ and sync to installed locations +> Updates DeepWork standard jobs in src/ and syncs to installed locations. Use when modifying deepwork_jobs or deepwork_rules. ## Instructions -**Goal**: Edit standard job source files and sync to installed locations +**Goal**: Edits standard job source files in src/ and runs deepwork install to sync changes. Use when updating job.yml or step instructions. # Update Standard Job diff --git a/src/deepwork/standard_jobs/deepwork_jobs/job.yml b/src/deepwork/standard_jobs/deepwork_jobs/job.yml index 9236540c..1c74d3f6 100644 --- a/src/deepwork/standard_jobs/deepwork_jobs/job.yml +++ b/src/deepwork/standard_jobs/deepwork_jobs/job.yml @@ -1,6 +1,6 @@ name: deepwork_jobs -version: "0.8.0" -summary: "DeepWork job management commands" +version: "0.9.0" +summary: "Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs." description: | Core commands for managing DeepWork jobs. These commands help you define new multi-step workflows and learn from running them. @@ -30,11 +30,13 @@ changelog: changes: "Added job.yml doc spec; define step now outputs job.yml with document_type reference for quality validation" - version: "0.8.0" changes: "Added review_job_spec step between define and implement for doc spec-based quality validation using sub-agent review" + - version: "0.9.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: define name: "Define Job Specification" - description: "Create the job.yml specification file by understanding workflow requirements" + description: "Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow." instructions_file: steps/define.md inputs: - name: job_purpose @@ -59,7 +61,7 @@ steps: - id: review_job_spec name: "Review Job Specification" - description: "Use sub-agent to review job.yml against doc spec quality criteria" + description: "Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification." instructions_file: steps/review_job_spec.md inputs: - file: job.yml @@ -77,7 +79,7 @@ steps: - id: implement name: "Implement Job Steps" - description: "Generate instruction files for each step based on the job.yml specification" + description: "Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes." instructions_file: steps/implement.md inputs: - file: job.yml @@ -99,7 +101,7 @@ steps: - id: learn name: "Learn from Job Execution" - description: "Reflect on conversation to improve job instructions and capture learnings" + description: "Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it." instructions_file: steps/learn.md exposed: true inputs: diff --git a/src/deepwork/standard_jobs/deepwork_rules/job.yml b/src/deepwork/standard_jobs/deepwork_rules/job.yml index 56caa953..a0032b9e 100644 --- a/src/deepwork/standard_jobs/deepwork_rules/job.yml +++ b/src/deepwork/standard_jobs/deepwork_rules/job.yml @@ -1,6 +1,6 @@ name: deepwork_rules -version: "0.3.0" -summary: "Rules enforcement for AI agent sessions" +version: "0.4.0" +summary: "Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers." description: | Manages rules that automatically trigger when certain files change during an AI agent session. Rules help ensure that code changes follow team guidelines, documentation is updated, @@ -33,11 +33,13 @@ changelog: changes: "Standardized on 'ask structured questions' phrasing for user input" - version: "0.3.0" changes: "Migrated to v2 format - individual markdown files in .deepwork/rules/" + - version: "0.4.0" + changes: "Improved skill descriptions with third-person voice and 'Use when...' triggers for better discoverability" steps: - id: define name: "Define Rule" - description: "Create a new rule file in .deepwork/rules/" + description: "Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requirements, or automated commands." instructions_file: steps/define.md inputs: - name: rule_purpose diff --git a/src/deepwork/templates/claude/skill-job-meta.md.jinja b/src/deepwork/templates/claude/skill-job-meta.md.jinja index 54de8fad..a45e9345 100644 --- a/src/deepwork/templates/claude/skill-job-meta.md.jinja +++ b/src/deepwork/templates/claude/skill-job-meta.md.jinja @@ -65,6 +65,13 @@ If user intent is unclear, use AskUserQuestion to clarify: - Present available steps as numbered options - Let user select the starting point +## Guardrails + +- Do NOT copy/paste step instructions directly; always use the Skill tool to invoke steps +- Do NOT skip steps in the workflow unless the user explicitly requests it +- Do NOT proceed to the next step if the current step's outputs are incomplete +- Do NOT make assumptions about user intent; ask for clarification when ambiguous + ## Context Files - Job definition: `.deepwork/jobs/{{ job_name }}/job.yml` diff --git a/src/deepwork/templates/claude/skill-job-step.md.jinja b/src/deepwork/templates/claude/skill-job-step.md.jinja index 51afd36c..f830cc80 100644 --- a/src/deepwork/templates/claude/skill-job-step.md.jinja +++ b/src/deepwork/templates/claude/skill-job-step.md.jinja @@ -181,6 +181,13 @@ Use branch format: `deepwork/{{ job_name }}-[instance]-YYYYMMDD` No specific file outputs required. {% endif %} +## Guardrails + +- Do NOT skip prerequisite verification if this step has dependencies +- Do NOT produce partial outputs; complete all required outputs before finishing +- Do NOT proceed without required inputs; ask the user if any are missing +- Do NOT modify files outside the scope of this step's defined outputs + {% if quality_criteria or stop_hooks %} ## Quality Validation