diff --git a/.claude/settings.json b/.claude/settings.json index 6df2fb93..f9c1cace 100644 --- a/.claude/settings.json +++ b/.claude/settings.json @@ -128,7 +128,8 @@ "Edit(./.deepwork/**)", "Write(./.deepwork/**)", "Bash(deepwork:*)", - "Bash(.claude/hooks/commit_job_git_commit.sh:*)" + "Bash(.claude/hooks/commit_job_git_commit.sh:*)", + "Bash(./.deepwork/jobs/deepwork_jobs/make_new_job.sh:*)" ] }, "hooks": { diff --git a/.claude/skills/add_platform.add_capabilities/SKILL.md b/.claude/skills/add_platform.add_capabilities/SKILL.md index b9d76df3..7dd71e27 100644 --- a/.claude/skills/add_platform.add_capabilities/SKILL.md +++ b/.claude/skills/add_platform.add_capabilities/SKILL.md @@ -1,39 +1,6 @@ --- name: add_platform.add_capabilities -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: - - hooks: - - type: prompt - prompt: | - Verify the capability additions meet ALL criteria: - 1. Any new hooks from the platform (for slash commands only) are added to src/deepwork/schemas/job_schema.py - 2. All existing adapters in src/deepwork/adapters.py are updated with the new hook fields - (set to None/null if the platform doesn't support that hook) - 3. Only hooks available on slash command definitions are added (not general CLI hooks) - 4. job_schema.py remains valid Python with no syntax errors - 5. adapters.py remains consistent - all adapters have the same hook fields - 6. If no new hooks are needed, document why in a comment - - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the capability additions meet ALL criteria: - 1. Any new hooks from the platform (for slash commands only) are added to src/deepwork/schemas/job_schema.py - 2. All existing adapters in src/deepwork/adapters.py are updated with the new hook fields - (set to None/null if the platform doesn't support that hook) - 3. Only hooks available on slash command definitions are added (not general CLI hooks) - 4. job_schema.py remains valid Python with no syntax errors - 5. adapters.py remains consistent - all adapters have the same hook fields - 6. If no new hooks are needed, document why in a comment - - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +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--- # add_platform.add_capabilities @@ -233,14 +200,6 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/add_platform.implement/SKILL.md b/.claude/skills/add_platform.implement/SKILL.md index 44722b65..167a6d7e 100644 --- a/.claude/skills/add_platform.implement/SKILL.md +++ b/.claude/skills/add_platform.implement/SKILL.md @@ -1,47 +1,10 @@ --- name: add_platform.implement -description: "Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities." -user-invocable: false -hooks: - Stop: - - hooks: - - type: command - command: ".deepwork/jobs/add_platform/hooks/run_tests.sh" - - type: prompt - prompt: | - Verify the implementation meets ALL criteria: - 1. Platform adapter class is added to src/deepwork/adapters.py - 2. Templates exist in src/deepwork/templates// with appropriate command structure - 3. Tests exist for all new functionality - 4. Test coverage is 100% for new code (run: uv run pytest --cov) - 5. All tests pass - 6. README.md is updated with: - - New platform listed in supported platforms - - Installation instructions for the platform - - Any platform-specific notes - - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: command - command: ".deepwork/jobs/add_platform/hooks/run_tests.sh" - - type: prompt - prompt: | - Verify the implementation meets ALL criteria: - 1. Platform adapter class is added to src/deepwork/adapters.py - 2. Templates exist in src/deepwork/templates// with appropriate command structure - 3. Tests exist for all new functionality - 4. Test coverage is 100% for new code (run: uv run pytest --cov) - 5. All tests pass - 6. README.md is updated with: - - New platform listed in supported platforms - - Installation instructions for the platform - - Any platform-specific notes - - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Creates platform adapter, templates, tests with 100% coverage, and README documentation. Use after adding hook capabilities."user-invocable: falsehooks: Stop: + - hooks: - type: command + command: ".deepwork/jobs/add_platform/hooks/run_tests.sh" SubagentStop: + - hooks: - type: command + command: ".deepwork/jobs/add_platform/hooks/run_tests.sh"--- # add_platform.implement @@ -336,15 +299,7 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - 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. - - **Validation script**: `.deepwork/jobs/add_platform/hooks/run_tests.sh` (runs automatically) - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/add_platform.research/SKILL.md b/.claude/skills/add_platform.research/SKILL.md index af44f2d3..3a3e3604 100644 --- a/.claude/skills/add_platform.research/SKILL.md +++ b/.claude/skills/add_platform.research/SKILL.md @@ -1,41 +1,6 @@ --- name: add_platform.research -description: "Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - Verify the research output meets ALL criteria: - 1. Both files exist in doc/platforms//: cli_configuration.md and hooks_system.md - 2. Each file has a comment at the top with: - - Last updated date - - Source URL where the documentation was obtained - 3. cli_configuration.md covers how the platform's CLI is configured - 4. hooks_system.md covers hooks available for slash command definitions ONLY - 5. No extraneous documentation (only these two specific topics) - 6. Documentation is comprehensive enough to implement the platform - - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the research output meets ALL criteria: - 1. Both files exist in doc/platforms//: cli_configuration.md and hooks_system.md - 2. Each file has a comment at the top with: - - Last updated date - - Source URL where the documentation was obtained - 3. cli_configuration.md covers how the platform's CLI is configured - 4. hooks_system.md covers hooks available for slash command definitions ONLY - 5. No extraneous documentation (only these two specific topics) - 6. Documentation is comprehensive enough to implement the platform - - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Captures CLI configuration and hooks system documentation for the new platform. Use when starting platform integration."user-invocable: false--- # add_platform.research @@ -284,14 +249,6 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/add_platform.verify/SKILL.md b/.claude/skills/add_platform.verify/SKILL.md index 583101f2..605d92c4 100644 --- a/.claude/skills/add_platform.verify/SKILL.md +++ b/.claude/skills/add_platform.verify/SKILL.md @@ -1,37 +1,6 @@ --- name: add_platform.verify -description: "Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - Verify the installation meets ALL criteria: - 1. Platform-specific directories/files are added to the deepwork repo as needed - 2. Running `deepwork install --platform ` completes without errors - 3. Expected command files are created in the platform's command directory - 4. Command file content matches the templates and job definitions - 5. Established DeepWork jobs (deepwork_jobs, deepwork_rules) are installed correctly - 6. The platform can be used alongside existing platforms without conflicts - - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the installation meets ALL criteria: - 1. Platform-specific directories/files are added to the deepwork repo as needed - 2. Running `deepwork install --platform ` completes without errors - 3. Expected command files are created in the platform's command directory - 4. Command file content matches the templates and job definitions - 5. Established DeepWork jobs (deepwork_jobs, deepwork_rules) are installed correctly - 6. The platform can be used alongside existing platforms without conflicts - - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Sets up platform directories and verifies deepwork install works correctly. Use after implementation to confirm integration."user-invocable: false--- # add_platform.verify @@ -206,14 +175,6 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/commit.commit_and_push/SKILL.md b/.claude/skills/commit.commit_and_push/SKILL.md index 7c96d0df..779c6e52 100644 --- a/.claude/skills/commit.commit_and_push/SKILL.md +++ b/.claude/skills/commit.commit_and_push/SKILL.md @@ -1,31 +1,6 @@ --- name: commit.commit_and_push -description: "Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - Verify the commit is ready: - 1. Changed files list was reviewed by the agent - 2. Files match what was modified during this session (or unexpected changes were investigated) - 3. Commit was created with appropriate message - 4. Changes were pushed to remote - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the commit is ready: - 1. Changed files list was reviewed by the agent - 2. Files match what was modified during this session (or unexpected changes were investigated) - 3. Commit was created with appropriate message - 4. Changes were pushed to remote - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Verifies changed files, creates commit, and pushes to remote. Use after linting passes to finalize changes."user-invocable: false--- # commit.commit_and_push @@ -68,14 +43,27 @@ Check the list of changed files against what was modified during this session, e - Are there any unexpected deleted files? - Do the line counts seem reasonable for the changes you made? - If changes match expectations, proceed to commit. + If changes match expectations, proceed to the next step. If there are unexpected changes: - Investigate why (e.g., lint auto-fixes, generated files) - If they're legitimate side effects of your work, include them - If they're unrelated or shouldn't be committed, use `git restore` to discard them -3. **Stage all appropriate changes** +3. **Update CHANGELOG.md if needed** + + If your changes include new features, bug fixes, or other notable changes: + - Add entries to the `## [Unreleased]` section of CHANGELOG.md + - Use the appropriate subsection: `### Added`, `### Changed`, `### Fixed`, or `### Removed` + - Write concise descriptions that explain the user-facing impact + + **CRITICAL: NEVER modify version numbers** + - Do NOT change the version in `pyproject.toml` + - Do NOT change version headers in CHANGELOG.md (e.g., `## [0.4.2]`) + - Do NOT rename the `## [Unreleased]` section + - Version updates are handled by the release workflow, not commits + +4. **Stage all appropriate changes** ```bash git add -A ``` @@ -93,8 +81,9 @@ Check the list of changed files against what was modified during this session, e - The style of recent commits - Conventional commit format if the project uses it + **IMPORTANT:** Use the commit job script (not `git commit` directly): ```bash - git commit -m "commit message here" + .claude/hooks/commit_job_git_commit.sh -m "commit message here" ``` 7. **Push to remote** @@ -110,6 +99,8 @@ Check the list of changed files against what was modified during this session, e - Changed files list was reviewed by the agent - Files match what was modified during this session (or unexpected changes were investigated and handled) +- CHANGELOG.md was updated with entries in the `[Unreleased]` section (if changes warrant documentation) +- Version numbers were NOT modified (in pyproject.toml or CHANGELOG.md version headers) - Commit message follows project conventions - Commit was created successfully - Changes were pushed to remote @@ -156,14 +147,6 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/commit.lint/SKILL.md b/.claude/skills/commit.lint/SKILL.md index 1caa6bf0..8bedb8b5 100644 --- a/.claude/skills/commit.lint/SKILL.md +++ b/.claude/skills/commit.lint/SKILL.md @@ -1,29 +1,6 @@ --- name: commit.lint -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: - - hooks: - - type: prompt - prompt: | - Verify the linting is complete: - 1. ruff format was run successfully - 2. ruff check was run successfully (with --fix) - 3. No remaining lint errors - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the linting is complete: - 1. ruff format was run successfully - 2. ruff check was run successfully (with --fix) - 3. No remaining lint errors - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance."user-invocable: false--- # commit.lint @@ -150,14 +127,6 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/commit.review/SKILL.md b/.claude/skills/commit.review/SKILL.md index 08ed14f4..71d4c6b3 100644 --- a/.claude/skills/commit.review/SKILL.md +++ b/.claude/skills/commit.review/SKILL.md @@ -1,29 +1,6 @@ --- name: commit.review -description: "Reviews changed code for issues, DRY opportunities, naming clarity, and test coverage using a sub-agent. Use as the first step before testing." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - Verify the code review is complete: - 1. Changed files were identified - 2. Sub-agent reviewed the code for general issues, DRY opportunities, naming clarity, and test coverage - 3. All identified issues were addressed or documented as intentional - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the code review is complete: - 1. Changed files were identified - 2. Sub-agent reviewed the code for general issues, DRY opportunities, naming clarity, and test coverage - 3. All identified issues were addressed or documented as intentional - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Reviews changed code for issues, DRY opportunities, naming clarity, and test coverage using a sub-agent. Use as the first step before testing."user-invocable: false--- # commit.review @@ -179,14 +156,6 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/commit.test/SKILL.md b/.claude/skills/commit.test/SKILL.md index 79229595..cef6a52a 100644 --- a/.claude/skills/commit.test/SKILL.md +++ b/.claude/skills/commit.test/SKILL.md @@ -1,31 +1,6 @@ --- name: commit.test -description: "Pulls latest code and runs tests until all pass. Use after code review passes to verify changes work correctly." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - Verify the tests are passing: - 1. Latest code was pulled from the branch - 2. All tests completed successfully - 3. No test failures or errors remain - 4. Test output shows passing status - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the tests are passing: - 1. Latest code was pulled from the branch - 2. All tests completed successfully - 3. No test failures or errors remain - 4. Test output shows passing status - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +description: "Pulls latest code and runs tests until all pass. Use after code review passes to verify changes work correctly."user-invocable: false--- # commit.test @@ -138,14 +113,6 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.claude/skills/deepwork_jobs.define/SKILL.md b/.claude/skills/deepwork_jobs.define/SKILL.md index 1dce7680..ef5b2407 100644 --- a/.claude/skills/deepwork_jobs.define/SKILL.md +++ b/.claude/skills/deepwork_jobs.define/SKILL.md @@ -1,71 +1,6 @@ --- name: deepwork_jobs.define -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: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **User Understanding**: Did the agent fully understand the user's workflow by asking structured questions? - 2. **Structured Questions Used**: Did the agent ask structured questions (using the AskUserQuestion tool) to gather user input? - 3. **Document Detection**: For document-oriented workflows, did the agent detect patterns and offer doc spec creation? - 4. **doc spec Created (if applicable)**: If a doc spec was needed, was it created in `.deepwork/doc_specs/[doc_spec_name].md` with proper quality criteria? - 5. **doc spec References**: Are document outputs properly linked to their doc specs using `{file, doc_spec}` format? - 6. **Valid Against doc spec**: Does the job.yml conform to the job.yml doc spec quality criteria (valid identifier, semantic version, concise summary, rich description, complete steps, valid dependencies)? - 7. **Clear Inputs/Outputs**: Does every step have clearly defined inputs and outputs? - 8. **Logical Dependencies**: Do step dependencies make sense and avoid circular references? - 9. **Concise Summary**: Is the summary under 200 characters and descriptive? - 10. **Rich Description**: Does the description provide enough context for future refinement? - 11. **Valid Schema**: Does the job.yml follow the required schema (name, version, summary, steps)? - 12. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **User Understanding**: Did the agent fully understand the user's workflow by asking structured questions? - 2. **Structured Questions Used**: Did the agent ask structured questions (using the AskUserQuestion tool) to gather user input? - 3. **Document Detection**: For document-oriented workflows, did the agent detect patterns and offer doc spec creation? - 4. **doc spec Created (if applicable)**: If a doc spec was needed, was it created in `.deepwork/doc_specs/[doc_spec_name].md` with proper quality criteria? - 5. **doc spec References**: Are document outputs properly linked to their doc specs using `{file, doc_spec}` format? - 6. **Valid Against doc spec**: Does the job.yml conform to the job.yml doc spec quality criteria (valid identifier, semantic version, concise summary, rich description, complete steps, valid dependencies)? - 7. **Clear Inputs/Outputs**: Does every step have clearly defined inputs and outputs? - 8. **Logical Dependencies**: Do step dependencies make sense and avoid circular references? - 9. **Concise Summary**: Is the summary under 200 characters and descriptive? - 10. **Rich Description**: Does the description provide enough context for future refinement? - 11. **Valid Schema**: Does the job.yml follow the required schema (name, version, summary, steps)? - 12. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new multi-step workflow."user-invocable: false--- # deepwork_jobs.define @@ -701,7 +636,9 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **User Understanding**: Did the agent fully understand the user's workflow by asking structured questions? @@ -716,9 +653,12 @@ Stop hooks will automatically validate your work. The loop continues until all c 10. **Rich Description**: Does the description provide enough context for future refinement? 11. **Valid Schema**: Does the job.yml follow the required schema (name, version, summary, steps)? 12. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`? - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/deepwork_jobs.implement/SKILL.md b/.claude/skills/deepwork_jobs.implement/SKILL.md index bb555eab..03879aa2 100644 --- a/.claude/skills/deepwork_jobs.implement/SKILL.md +++ b/.claude/skills/deepwork_jobs.implement/SKILL.md @@ -1,65 +1,6 @@ --- name: deepwork_jobs.implement -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: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Directory Structure**: Is `.deepwork/jobs/[job_name]/` created correctly? - 2. **Complete Instructions**: Are ALL step instruction files complete (not stubs or placeholders)? - 3. **Specific & Actionable**: Are instructions tailored to each step's purpose, not generic? - 4. **Output Examples**: Does each instruction file show what good output looks like? - 5. **Quality Criteria**: Does each instruction file define quality criteria for its outputs? - 6. **Ask Structured Questions**: Do step instructions that gather user input explicitly use the phrase "ask structured questions"? - 7. **Sync Complete**: Has `deepwork sync` been run successfully? - 8. **Commands Available**: Are the slash-commands generated in `.claude/commands/`? - 9. **Rules Considered**: Has the agent thought about whether rules would benefit this job? If relevant rules were identified, did they explain them and offer to run `/deepwork_rules.define`? Not every job needs rules - only suggest when genuinely helpful. - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Directory Structure**: Is `.deepwork/jobs/[job_name]/` created correctly? - 2. **Complete Instructions**: Are ALL step instruction files complete (not stubs or placeholders)? - 3. **Specific & Actionable**: Are instructions tailored to each step's purpose, not generic? - 4. **Output Examples**: Does each instruction file show what good output looks like? - 5. **Quality Criteria**: Does each instruction file define quality criteria for its outputs? - 6. **Ask Structured Questions**: Do step instructions that gather user input explicitly use the phrase "ask structured questions"? - 7. **Sync Complete**: Has `deepwork sync` been run successfully? - 8. **Commands Available**: Are the slash-commands generated in `.claude/commands/`? - 9. **Rules Considered**: Has the agent thought about whether rules would benefit this job? If relevant rules were identified, did they explain them and offer to run `/deepwork_rules.define`? Not every job needs rules - only suggest when genuinely helpful. - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes."user-invocable: false--- # deepwork_jobs.implement @@ -357,7 +298,9 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Directory Structure**: Is `.deepwork/jobs/[job_name]/` created correctly? @@ -369,9 +312,12 @@ Stop hooks will automatically validate your work. The loop continues until all c 7. **Sync Complete**: Has `deepwork sync` been run successfully? 8. **Commands Available**: Are the slash-commands generated in `.claude/commands/`? 9. **Rules Considered**: Has the agent thought about whether rules would benefit this job? If relevant rules were identified, did they explain them and offer to run `/deepwork_rules.define`? Not every job needs rules - only suggest when genuinely helpful. - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/deepwork_jobs.learn/SKILL.md b/.claude/skills/deepwork_jobs.learn/SKILL.md index fce20c29..d50ab9af 100644 --- a/.claude/skills/deepwork_jobs.learn/SKILL.md +++ b/.claude/skills/deepwork_jobs.learn/SKILL.md @@ -1,70 +1,6 @@ --- name: deepwork_jobs.learn -description: "Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it." -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Conversation Analyzed**: Did the agent review the conversation for DeepWork job executions? - 2. **Confusion Identified**: Did the agent identify points of confusion, errors, or inefficiencies? - 3. **Instructions Improved**: Were job instructions updated to address identified issues? - 4. **Instructions Concise**: Are instructions free of redundancy and unnecessary verbosity? - 5. **Shared Content Extracted**: Is lengthy/duplicated content extracted into referenced files? - 6. **doc spec Reviewed (if applicable)**: For jobs with doc spec outputs, were doc spec-related learnings identified? - 7. **doc spec Updated (if applicable)**: Were doc spec files updated with improved quality criteria or structure? - 8. **Bespoke Learnings Captured**: Were run-specific learnings added to AGENTS.md? - 9. **File References Used**: Do AGENTS.md entries reference other files where appropriate? - 10. **Working Folder Correct**: Is AGENTS.md in the correct working folder for the job? - 11. **Generalizable Separated**: Are generalizable improvements in instructions, not AGENTS.md? - 12. **Sync Complete**: Has `deepwork sync` been run if instructions were modified? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Conversation Analyzed**: Did the agent review the conversation for DeepWork job executions? - 2. **Confusion Identified**: Did the agent identify points of confusion, errors, or inefficiencies? - 3. **Instructions Improved**: Were job instructions updated to address identified issues? - 4. **Instructions Concise**: Are instructions free of redundancy and unnecessary verbosity? - 5. **Shared Content Extracted**: Is lengthy/duplicated content extracted into referenced files? - 6. **doc spec Reviewed (if applicable)**: For jobs with doc spec outputs, were doc spec-related learnings identified? - 7. **doc spec Updated (if applicable)**: Were doc spec files updated with improved quality criteria or structure? - 8. **Bespoke Learnings Captured**: Were run-specific learnings added to AGENTS.md? - 9. **File References Used**: Do AGENTS.md entries reference other files where appropriate? - 10. **Working Folder Correct**: Is AGENTS.md in the correct working folder for the job? - 11. **Generalizable Separated**: Are generalizable improvements in instructions, not AGENTS.md? - 12. **Sync Complete**: Has `deepwork sync` been run if instructions were modified? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it."--- # deepwork_jobs.learn @@ -477,7 +413,9 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Conversation Analyzed**: Did the agent review the conversation for DeepWork job executions? @@ -492,9 +430,12 @@ Stop hooks will automatically validate your work. The loop continues until all c 10. **Working Folder Correct**: Is AGENTS.md in the correct working folder for the job? 11. **Generalizable Separated**: Are generalizable improvements in instructions, not AGENTS.md? 12. **Sync Complete**: Has `deepwork sync` been run if instructions were modified? - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md b/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md index c49defb6..4e54318a 100644 --- a/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md +++ b/.claude/skills/deepwork_jobs.review_job_spec/SKILL.md @@ -1,55 +1,6 @@ --- name: deepwork_jobs.review_job_spec -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: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agent Used**: Was a sub-agent spawned to provide unbiased review? - 2. **All doc spec Criteria Evaluated**: Did the sub-agent assess all 9 quality criteria? - 3. **Findings Addressed**: Were all failed criteria addressed by the main agent? - 4. **Validation Loop Complete**: Did the review-fix cycle continue until all criteria passed? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agent Used**: Was a sub-agent spawned to provide unbiased review? - 2. **All doc spec Criteria Evaluated**: Did the sub-agent assess all 9 quality criteria? - 3. **Findings Addressed**: Were all failed criteria addressed by the main agent? - 4. **Validation Loop Complete**: Did the review-fix cycle continue until all criteria passed? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specification."user-invocable: false--- # deepwork_jobs.review_job_spec @@ -500,16 +451,21 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Sub-Agent Used**: Was a sub-agent spawned to provide unbiased review? 2. **All doc spec Criteria Evaluated**: Did the sub-agent assess all 9 quality criteria? 3. **Findings Addressed**: Were all failed criteria addressed by the main agent? 4. **Validation Loop Complete**: Did the review-fix cycle continue until all criteria passed? - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/deepwork_rules.define/SKILL.md b/.claude/skills/deepwork_rules.define/SKILL.md index 25cf1892..1ad6ebe3 100644 --- a/.claude/skills/deepwork_rules.define/SKILL.md +++ b/.claude/skills/deepwork_rules.define/SKILL.md @@ -1,8 +1,6 @@ --- name: deepwork_rules.define -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 ---- +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--- # deepwork_rules.define diff --git a/.claude/skills/manual_tests.infinite_block_tests/SKILL.md b/.claude/skills/manual_tests.infinite_block_tests/SKILL.md index ea56c5e1..5b3cb4b5 100644 --- a/.claude/skills/manual_tests.infinite_block_tests/SKILL.md +++ b/.claude/skills/manual_tests.infinite_block_tests/SKILL.md @@ -1,55 +1,6 @@ --- name: manual_tests.infinite_block_tests -description: "Runs all 4 infinite block tests serially. Tests both 'should fire' (no promise) and 'should NOT fire' (with promise) scenarios." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agents Used**: Each test run via Task tool with `model: "haiku"` and `max_turns: 5` - 2. **Serial Execution**: Sub-agents launched ONE AT A TIME with reset between each - 3. **Promise Tests**: Completed WITHOUT blocking (promise bypassed the rule) - 4. **No-Promise Tests**: Hook fired AND sub-agent returned in reasonable time (not hung) - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agents Used**: Each test run via Task tool with `model: "haiku"` and `max_turns: 5` - 2. **Serial Execution**: Sub-agents launched ONE AT A TIME with reset between each - 3. **Promise Tests**: Completed WITHOUT blocking (promise bypassed the rule) - 4. **No-Promise Tests**: Hook fired AND sub-agent returned in reasonable time (not hung) - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Runs all 4 infinite block tests serially. Tests both 'should fire' (no promise) and 'should NOT fire' (with promise) scenarios."user-invocable: false--- # manual_tests.infinite_block_tests @@ -270,16 +221,21 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Sub-Agents Used**: Each test run via Task tool with `model: "haiku"` and `max_turns: 5` 2. **Serial Execution**: Sub-agents launched ONE AT A TIME with reset between each 3. **Promise Tests**: Completed WITHOUT blocking (promise bypassed the rule) 4. **No-Promise Tests**: Hook fired AND sub-agent returned in reasonable time (not hung) - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/manual_tests.reset/SKILL.md b/.claude/skills/manual_tests.reset/SKILL.md index ceb8eb4a..1792ef69 100644 --- a/.claude/skills/manual_tests.reset/SKILL.md +++ b/.claude/skills/manual_tests.reset/SKILL.md @@ -1,49 +1,6 @@ --- name: manual_tests.reset -description: "Runs FIRST to ensure clean environment. Also called internally by other steps when they need to revert changes and clear the queue." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Environment Clean**: Git changes reverted, created files removed, and rules queue cleared - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Environment Clean**: Git changes reverted, created files removed, and rules queue cleared - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Runs FIRST to ensure clean environment. Also called internally by other steps when they need to revert changes and clear the queue."user-invocable: false--- # manual_tests.reset @@ -157,13 +114,18 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Environment Clean**: Git changes reverted, created files removed, and rules queue cleared - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/manual_tests.run_fire_tests/SKILL.md b/.claude/skills/manual_tests.run_fire_tests/SKILL.md index d6bd6c58..29199317 100644 --- a/.claude/skills/manual_tests.run_fire_tests/SKILL.md +++ b/.claude/skills/manual_tests.run_fire_tests/SKILL.md @@ -1,61 +1,6 @@ --- name: manual_tests.run_fire_tests -description: "Runs all 6 'should fire' tests serially with resets between each. Use after NOT-fire tests to verify rules fire correctly." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agents Used**: Did the main agent spawn a sub-agent (using the Task tool) for EACH test? The main agent must NOT edit the test files directly. - 2. **Sub-Agent Config**: Did all sub-agents use `model: "haiku"` and `max_turns: 5`? - 3. **Serial Execution**: Were sub-agents launched ONE AT A TIME (not in parallel) to prevent cross-contamination? - 4. **Hooks Fired Automatically**: Did the main agent observe the blocking hooks firing automatically when each sub-agent returned? The agent must NOT manually run the rules_check command. - 5. **Reset Between Tests**: Was the reset step called internally after each test to revert files and prevent cross-contamination? - 6. **Early Termination**: If 2 tests failed, did testing halt immediately with results reported? - 7. **Results Recorded**: Did the main agent track pass/fail status for each test case? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agents Used**: Did the main agent spawn a sub-agent (using the Task tool) for EACH test? The main agent must NOT edit the test files directly. - 2. **Sub-Agent Config**: Did all sub-agents use `model: "haiku"` and `max_turns: 5`? - 3. **Serial Execution**: Were sub-agents launched ONE AT A TIME (not in parallel) to prevent cross-contamination? - 4. **Hooks Fired Automatically**: Did the main agent observe the blocking hooks firing automatically when each sub-agent returned? The agent must NOT manually run the rules_check command. - 5. **Reset Between Tests**: Was the reset step called internally after each test to revert files and prevent cross-contamination? - 6. **Early Termination**: If 2 tests failed, did testing halt immediately with results reported? - 7. **Results Recorded**: Did the main agent track pass/fail status for each test case? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Runs all 6 'should fire' tests serially with resets between each. Use after NOT-fire tests to verify rules fire correctly."user-invocable: false--- # manual_tests.run_fire_tests @@ -272,7 +217,9 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Sub-Agents Used**: Did the main agent spawn a sub-agent (using the Task tool) for EACH test? The main agent must NOT edit the test files directly. @@ -282,9 +229,12 @@ Stop hooks will automatically validate your work. The loop continues until all c 5. **Reset Between Tests**: Was the reset step called internally after each test to revert files and prevent cross-contamination? 6. **Early Termination**: If 2 tests failed, did testing halt immediately with results reported? 7. **Results Recorded**: Did the main agent track pass/fail status for each test case? - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/manual_tests.run_not_fire_tests/SKILL.md b/.claude/skills/manual_tests.run_not_fire_tests/SKILL.md index 4a3380ce..65c3c899 100644 --- a/.claude/skills/manual_tests.run_not_fire_tests/SKILL.md +++ b/.claude/skills/manual_tests.run_not_fire_tests/SKILL.md @@ -1,61 +1,6 @@ --- name: manual_tests.run_not_fire_tests -description: "Runs all 6 'should NOT fire' tests in parallel sub-agents. Use to verify rules don't fire when safety conditions are met." -user-invocable: false -hooks: - Stop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agents Used**: Did the main agent spawn sub-agents (using the Task tool) to make the file edits? The main agent must NOT edit the test files directly. - 2. **Sub-Agent Config**: Did all sub-agents use `model: "haiku"` and `max_turns: 5`? - 3. **Parallel Execution**: Were all 6 sub-agents launched in parallel (in a single message with multiple Task tool calls)? - 4. **Hooks Observed**: Did the main agent observe that no blocking hooks fired when the sub-agents returned? The hooks fire AUTOMATICALLY - the agent must NOT manually run the rules_check command. - 5. **Queue Verified Empty**: After all sub-agents completed, was the rules queue checked and confirmed empty (no entries = rules did not fire)? - 6. **Early Termination**: If 2 tests failed, did testing halt immediately with results reported? - 7. **Reset Performed**: Was the reset step called internally after tests completed (or after early termination)? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. - SubagentStop: - - hooks: - - type: prompt - prompt: | - You must evaluate whether Claude has met all the below quality criteria for the request. - - ## Quality Criteria - - 1. **Sub-Agents Used**: Did the main agent spawn sub-agents (using the Task tool) to make the file edits? The main agent must NOT edit the test files directly. - 2. **Sub-Agent Config**: Did all sub-agents use `model: "haiku"` and `max_turns: 5`? - 3. **Parallel Execution**: Were all 6 sub-agents launched in parallel (in a single message with multiple Task tool calls)? - 4. **Hooks Observed**: Did the main agent observe that no blocking hooks fired when the sub-agents returned? The hooks fire AUTOMATICALLY - the agent must NOT manually run the rules_check command. - 5. **Queue Verified Empty**: After all sub-agents completed, was the rules queue checked and confirmed empty (no entries = rules did not fire)? - 6. **Early Termination**: If 2 tests failed, did testing halt immediately with results reported? - 7. **Reset Performed**: Was the reset step called internally after tests completed (or after early termination)? - - ## Instructions - - Review the conversation and determine if ALL quality criteria above have been satisfied. - Look for evidence that each criterion has been addressed. - - If the agent has included `✓ Quality Criteria Met` in their response OR - all criteria appear to be met, let the agent finish. - - If criteria are NOT met AND the promise tag is missing, have the agent keep working - until all criteria are satisfied. ---- +description: "Runs all 6 'should NOT fire' tests in parallel sub-agents. Use to verify rules don't fire when safety conditions are met."user-invocable: false--- # manual_tests.run_not_fire_tests @@ -258,7 +203,9 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD` ## Quality Validation -Stop hooks will automatically validate your work. The loop continues until all criteria pass. +**Before completing this step, you MUST have your work reviewed against the quality criteria below.** + +Use a sub-agent (Haiku model) to review your work against these criteria: **Criteria (all must be satisfied)**: 1. **Sub-Agents Used**: Did the main agent spawn sub-agents (using the Task tool) to make the file edits? The main agent must NOT edit the test files directly. @@ -268,9 +215,12 @@ Stop hooks will automatically validate your work. The loop continues until all c 5. **Queue Verified Empty**: After all sub-agents completed, was the rules queue checked and confirmed empty (no entries = rules did not fire)? 6. **Early Termination**: If 2 tests failed, did testing halt immediately with results reported? 7. **Reset Performed**: Was the reset step called internally after tests completed (or after early termination)? - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. +**Review Process**: +1. Once you believe your work is complete, spawn a sub-agent using Haiku to review your work against the quality criteria above +2. The sub-agent should examine your outputs and verify each criterion is met +3. If the sub-agent identifies valid issues, fix them +4. Have the sub-agent review again until all valid feedback has been addressed +5. Only mark the step complete when the sub-agent confirms all criteria are satisfied ## On Completion diff --git a/.claude/skills/update.job/SKILL.md b/.claude/skills/update.job/SKILL.md index 19ab7fb0..d2122d5f 100644 --- a/.claude/skills/update.job/SKILL.md +++ b/.claude/skills/update.job/SKILL.md @@ -1,31 +1,6 @@ --- name: update.job -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: - - hooks: - - type: prompt - prompt: | - Verify the update process completed successfully: - 1. Changes were made in src/deepwork/standard_jobs/[job_name]/ (NOT in .deepwork/jobs/) - 2. `deepwork install --platform claude` was run - 3. Files in .deepwork/jobs/ match the source files - 4. Command files in .claude/commands/ were regenerated - If ALL criteria are met, include `✓ Quality Criteria Met`. - - SubagentStop: - - hooks: - - type: prompt - prompt: | - Verify the update process completed successfully: - 1. Changes were made in src/deepwork/standard_jobs/[job_name]/ (NOT in .deepwork/jobs/) - 2. `deepwork install --platform claude` was run - 3. Files in .deepwork/jobs/ match the source files - 4. Command files in .claude/commands/ were regenerated - If ALL criteria are met, include `✓ Quality Criteria Met`. - ---- +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--- # update.job @@ -155,14 +130,6 @@ Use branch format: `deepwork/update-[instance]-YYYYMMDD` - 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. - - - -**To complete**: Include `✓ Quality Criteria Met` in your final response only after verifying ALL criteria are satisfied. - ## On Completion 1. Verify outputs are created diff --git a/.deepwork/jobs/commit/job.yml b/.deepwork/jobs/commit/job.yml index d153bff3..445640df 100644 --- a/.deepwork/jobs/commit/job.yml +++ b/.deepwork/jobs/commit/job.yml @@ -1,5 +1,5 @@ name: commit -version: "1.3.0" +version: "1.4.0" summary: "Reviews code, runs tests, lints, and commits changes. Use when ready to commit work with quality checks." description: | A workflow for preparing and committing code changes with quality checks. @@ -16,6 +16,8 @@ description: | 4. commit_and_push - Review changes and commit/push changelog: + - version: "1.4.0" + changes: "Added changelog guidance: entries must go in [Unreleased] section, NEVER modify version numbers in pyproject.toml or CHANGELOG.md" - version: "1.3.0" changes: "Added code review step that runs in sub-agent to check for general issues, DRY opportunities, naming clarity, and test coverage" - version: "1.0.1" @@ -99,6 +101,8 @@ steps: Verify the commit is ready: 1. Changed files list was reviewed by the agent 2. Files match what was modified during this session (or unexpected changes were investigated) - 3. Commit was created with appropriate message - 4. Changes were pushed to remote + 3. CHANGELOG.md was updated with entries in the [Unreleased] section (if changes warrant documentation) + 4. Version numbers were NOT modified (pyproject.toml version and CHANGELOG version headers must remain unchanged) + 5. Commit was created with appropriate message + 6. Changes were pushed to remote If ALL criteria are met, include `✓ Quality Criteria Met`. diff --git a/.deepwork/jobs/commit/steps/commit_and_push.md b/.deepwork/jobs/commit/steps/commit_and_push.md index cd45c43d..a1160a91 100644 --- a/.deepwork/jobs/commit/steps/commit_and_push.md +++ b/.deepwork/jobs/commit/steps/commit_and_push.md @@ -24,14 +24,27 @@ Check the list of changed files against what was modified during this session, e - Are there any unexpected deleted files? - Do the line counts seem reasonable for the changes you made? - If changes match expectations, proceed to commit. + If changes match expectations, proceed to the next step. If there are unexpected changes: - Investigate why (e.g., lint auto-fixes, generated files) - If they're legitimate side effects of your work, include them - If they're unrelated or shouldn't be committed, use `git restore` to discard them -3. **Stage all appropriate changes** +3. **Update CHANGELOG.md if needed** + + If your changes include new features, bug fixes, or other notable changes: + - Add entries to the `## [Unreleased]` section of CHANGELOG.md + - Use the appropriate subsection: `### Added`, `### Changed`, `### Fixed`, or `### Removed` + - Write concise descriptions that explain the user-facing impact + + **CRITICAL: NEVER modify version numbers** + - Do NOT change the version in `pyproject.toml` + - Do NOT change version headers in CHANGELOG.md (e.g., `## [0.4.2]`) + - Do NOT rename the `## [Unreleased]` section + - Version updates are handled by the release workflow, not commits + +4. **Stage all appropriate changes** ```bash git add -A ``` @@ -67,6 +80,8 @@ Check the list of changed files against what was modified during this session, e - Changed files list was reviewed by the agent - Files match what was modified during this session (or unexpected changes were investigated and handled) +- CHANGELOG.md was updated with entries in the `[Unreleased]` section (if changes warrant documentation) +- Version numbers were NOT modified (in pyproject.toml or CHANGELOG.md version headers) - Commit message follows project conventions - Commit was created successfully - Changes were pushed to remote diff --git a/.gemini/skills/commit/commit_and_push.toml b/.gemini/skills/commit/commit_and_push.toml index 9c42b3e5..251b9a3a 100644 --- a/.gemini/skills/commit/commit_and_push.toml +++ b/.gemini/skills/commit/commit_and_push.toml @@ -48,14 +48,27 @@ Check the list of changed files against what was modified during this session, e - Are there any unexpected deleted files? - Do the line counts seem reasonable for the changes you made? - If changes match expectations, proceed to commit. + If changes match expectations, proceed to the next step. If there are unexpected changes: - Investigate why (e.g., lint auto-fixes, generated files) - If they're legitimate side effects of your work, include them - If they're unrelated or shouldn't be committed, use `git restore` to discard them -3. **Stage all appropriate changes** +3. **Update CHANGELOG.md if needed** + + If your changes include new features, bug fixes, or other notable changes: + - Add entries to the `## [Unreleased]` section of CHANGELOG.md + - Use the appropriate subsection: `### Added`, `### Changed`, `### Fixed`, or `### Removed` + - Write concise descriptions that explain the user-facing impact + + **CRITICAL: NEVER modify version numbers** + - Do NOT change the version in `pyproject.toml` + - Do NOT change version headers in CHANGELOG.md (e.g., `## [0.4.2]`) + - Do NOT rename the `## [Unreleased]` section + - Version updates are handled by the release workflow, not commits + +4. **Stage all appropriate changes** ```bash git add -A ``` @@ -73,8 +86,9 @@ Check the list of changed files against what was modified during this session, e - The style of recent commits - Conventional commit format if the project uses it + **IMPORTANT:** Use the commit job script (not `git commit` directly): ```bash - git commit -m "commit message here" + .claude/hooks/commit_job_git_commit.sh -m "commit message here" ``` 7. **Push to remote** @@ -90,6 +104,8 @@ Check the list of changed files against what was modified during this session, e - Changed files list was reviewed by the agent - Files match what was modified during this session (or unexpected changes were investigated and handled) +- CHANGELOG.md was updated with entries in the `[Unreleased]` section (if changes warrant documentation) +- Version numbers were NOT modified (in pyproject.toml or CHANGELOG.md version headers) - Commit message follows project conventions - Commit was created successfully - Changes were pushed to remote diff --git a/.github/workflows/create-release.yml b/.github/workflows/create-release.yml new file mode 100644 index 00000000..0a81d368 --- /dev/null +++ b/.github/workflows/create-release.yml @@ -0,0 +1,168 @@ +name: Create Release + +on: + workflow_dispatch: + inputs: + version: + description: 'Version number (e.g., 0.6.0)' + required: true + type: string + +permissions: + contents: write + +jobs: + release: + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + with: + fetch-depth: 0 + token: ${{ secrets.GITHUB_TOKEN }} + + - name: Validate version format + run: | + if ! echo "${{ inputs.version }}" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+$'; then + echo "Error: Version must be in format X.Y.Z (e.g., 0.6.0)" + exit 1 + fi + + - name: Configure git + run: | + git config user.name "github-actions[bot]" + git config user.email "github-actions[bot]@users.noreply.github.com" + + - name: Update CHANGELOG.md + id: changelog + env: + GITHUB_REPOSITORY: ${{ github.repository }} + run: | + VERSION="${{ inputs.version }}" + DATE=$(date +%Y-%m-%d) + + # Create the new Unreleased section template + UNRELEASED_TEMPLATE="## [Unreleased] + +### Added + +### Changed + +### Fixed + +### Removed + +" + + # Read the current changelog + CHANGELOG=$(cat CHANGELOG.md) + + # Check if there's an existing Unreleased section + if grep -q "^## \[Unreleased\]" CHANGELOG.md; then + # Replace [Unreleased] with the new version and date + # First, extract everything after the Unreleased header until the next ## section + # Then insert the new Unreleased section at the top + + # Use awk to do the replacement + awk -v version="$VERSION" -v date="$DATE" -v template="$UNRELEASED_TEMPLATE" ' + /^## \[Unreleased\]/ { + print template + print "## [" version "] - " date + next + } + { print } + ' CHANGELOG.md > CHANGELOG.md.tmp + mv CHANGELOG.md.tmp CHANGELOG.md + else + # No Unreleased section exists - insert new version after the header + # Find the first ## line and insert before it + awk -v version="$VERSION" -v date="$DATE" -v template="$UNRELEASED_TEMPLATE" ' + BEGIN { inserted = 0 } + /^## \[/ && !inserted { + print template + print "## [" version "] - " date + print "" + inserted = 1 + } + { print } + ' CHANGELOG.md > CHANGELOG.md.tmp + mv CHANGELOG.md.tmp CHANGELOG.md + fi + + # Update the version links at the bottom of the CHANGELOG + # Update the Unreleased link to compare from the new version + sed -i "s|\[Unreleased\]: https://github.com/.*/compare/.*\.\.\.HEAD|[Unreleased]: https://github.com/${GITHUB_REPOSITORY}/compare/${VERSION}...HEAD|" CHANGELOG.md + + # Add the new version link if it doesn't exist (insert after Unreleased link) + if ! grep -q "^\[${VERSION}\]:" CHANGELOG.md; then + # Find the previous version from the changelog (first version after Unreleased) + PREV_VERSION=$(grep -oP '^\[[\d.]+\]:' CHANGELOG.md | head -1 | tr -d '[]:' || echo "") + if [ -n "$PREV_VERSION" ]; then + VERSION_LINK="[${VERSION}]: https://github.com/${GITHUB_REPOSITORY}/releases/tag/${VERSION}" + sed -i "/^\[Unreleased\]:/a ${VERSION_LINK}" CHANGELOG.md + fi + fi + + # Extract the changelog content for this version (for the release notes) + # Get everything between the version header and the next version header + RELEASE_NOTES=$(awk -v version="$VERSION" ' + BEGIN { capture = 0; found = 0 } + /^## \[/ { + if (capture) exit + if ($0 ~ "\\[" version "\\]") { + capture = 1 + found = 1 + next + } + } + capture { print } + ' CHANGELOG.md) + + # Save release notes to a file for the release step + echo "$RELEASE_NOTES" > release_notes.md + + # Output for debugging + echo "Release notes extracted:" + cat release_notes.md + + - name: Update pyproject.toml version + run: | + VERSION="${{ inputs.version }}" + sed -i "s/^version = \".*\"/version = \"$VERSION\"/" pyproject.toml + + # Verify the change + grep "^version = " pyproject.toml + + - name: Install uv + uses: astral-sh/setup-uv@v4 + with: + version: "latest" + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: "3.11" + + - name: Update lock file + run: uv sync + + - name: Commit changes + run: | + VERSION="${{ inputs.version }}" + git add CHANGELOG.md pyproject.toml uv.lock + git commit -m "Release v${VERSION}" + git push origin main + + - name: Create and push tag + run: | + VERSION="${{ inputs.version }}" + git tag -a "$VERSION" -m "Release $VERSION" + git push origin "$VERSION" + + - name: Create GitHub Release + uses: softprops/action-gh-release@v2 + with: + tag_name: ${{ inputs.version }} + name: ${{ inputs.version }} + body_path: release_notes.md + draft: false + prerelease: false diff --git a/CHANGELOG.md b/CHANGELOG.md index 55081786..4eb764da 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,8 +9,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Added - Installer now auto-adds permission for `make_new_job.sh` script, allowing Claude to run job creation without manual configuration +- Manual release workflow (`create-release.yml`) that automates version releases: + - Takes version number as input, validates format + - Updates CHANGELOG.md: converts Unreleased section to new version with date + - Adds fresh Unreleased section with placeholder categories + - Updates pyproject.toml version and runs uv sync for lock file + - Commits changes directly to main, creates tag, and publishes GitHub release ### Changed +- Commit job now requires changelog entries go to `[Unreleased]` section and explicitly prohibits modifying version numbers ### Fixed