Fix duplicate quality criteria rendering in skill templates

.claude/skills/add_platform.add_capabilities/SKILL.md

@@ -203,9 +203,7 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "integrate step 2/4 complete, outputs: job_schema.py, adapters.py"

.claude/skills/add_platform.implement/SKILL.md

@@ -307,9 +307,7 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD`
 - 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
-
-**Validation script**: `.deepwork/jobs/add_platform/hooks/run_tests.sh` (runs automatically)
+- Do NOT modify files outside the scope of this step's defined outputs**Validation script**: `.deepwork/jobs/add_platform/hooks/run_tests.sh` (runs automatically)
 ## On Completion
 
 1. Verify outputs are created

.claude/skills/add_platform.research/SKILL.md

@@ -252,9 +252,7 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "integrate step 1/4 complete, outputs: cli_configuration.md, hooks_system.md"

.claude/skills/add_platform.verify/SKILL.md

@@ -178,9 +178,7 @@ Use branch format: `deepwork/add_platform-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "integrate step 4/4 complete, outputs: verification_checklist.md"

.claude/skills/commit.commit_and_push/SKILL.md

@@ -147,9 +147,7 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/commit.lint/SKILL.md

@@ -128,9 +128,7 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/commit.review/SKILL.md

@@ -109,9 +109,7 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/commit.test/SKILL.md

@@ -109,9 +109,7 @@ Use branch format: `deepwork/commit-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/deepwork_jobs.define/SKILL.md

@@ -637,35 +637,7 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD`
 - 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
-
-**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?
-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`?
-**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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "new_job step 1/3 complete, outputs: job.yml"

.claude/skills/deepwork_jobs.implement/SKILL.md

@@ -299,9 +299,7 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/deepwork_jobs.learn/SKILL.md

@@ -411,9 +411,7 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/deepwork_jobs.review_job_spec/SKILL.md

@@ -452,27 +452,7 @@ Use branch format: `deepwork/deepwork_jobs-[instance]-YYYYMMDD`
 - 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
-
-**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?
-**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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "new_job step 2/3 complete, outputs: job.yml"

.claude/skills/deepwork_rules.define/SKILL.md

@@ -317,9 +317,7 @@ Use branch format: `deepwork/deepwork_rules-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "define complete, outputs: .deepwork/rules/{rule-name}.md"

.claude/skills/manual_tests.infinite_block_tests/SKILL.md

@@ -222,9 +222,7 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/manual_tests.reset/SKILL.md

@@ -115,9 +115,7 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/manual_tests.run_fire_tests/SKILL.md

@@ -218,9 +218,7 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/manual_tests.run_not_fire_tests/SKILL.md

@@ -204,9 +204,7 @@ Use branch format: `deepwork/manual_tests-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
 

.claude/skills/update.job/SKILL.md

@@ -131,9 +131,7 @@ Use branch format: `deepwork/update-[instance]-YYYYMMDD`
 - 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
+- Do NOT modify files outside the scope of this step's defined outputs## On Completion
 
 1. Verify outputs are created
 2. Inform user: "job complete, outputs: files_synced"

CHANGELOG.md

@@ -22,6 +22,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - SessionStart hook now skips non-initial sessions (resume, compact/clear) by checking the `source` field in stdin JSON, reducing noise and redundant checks
 
 ### Fixed
+- Fixed duplicate quality criteria rendering in generated skill files
+  - Steps with outputs having doc_spec quality criteria no longer render a separate "Quality Validation" section
+  - Doc spec criteria are shown under outputs; step-level criteria are only shown when no doc_spec criteria exist
+  - Applies to both Claude and Gemini templates
 - Fixed skill template generating malformed YAML frontmatter with fields concatenated on single lines
   - Removed over-aggressive `{%-` whitespace stripping from Jinja template
   - Fields like `user-invocable` and `hooks` now render on proper separate lines

src/deepwork/templates/claude/skill-job-step.md.jinja

@@ -200,7 +200,15 @@ No specific file outputs required.
 - 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 %}
+{#- Check if any output has doc_spec quality criteria to avoid duplicate quality validation sections #}
+{%- set has_doc_spec_quality = namespace(value=false) -%}
+{%- for output in outputs -%}
+{%- if output.has_doc_spec and output.doc_spec and output.doc_spec.quality_criteria -%}
+{%- set has_doc_spec_quality.value = true -%}
+{%- endif -%}
+{%- endfor -%}
+{#- Only show step-level quality_criteria if no doc_spec quality criteria exist (avoids duplication) #}
+{% if quality_criteria and not has_doc_spec_quality.value %}
 ## Quality Validation
 
 **Before completing this step, you MUST have your work reviewed against the quality criteria below.**
@@ -218,7 +226,7 @@ Use a sub-agent (Haiku model) to review your work against these criteria:
 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
 
-{% endif %}{#- if quality_criteria #}
+{% endif %}{#- if quality_criteria and not has_doc_spec_quality.value #}
 {% if stop_hooks -%}
 {% for hook in stop_hooks -%}
 {% if hook.type == "script" -%}

src/deepwork/templates/gemini/skill-job-step.toml.jinja

@@ -127,7 +127,15 @@ Use branch format: `deepwork/{{ job_name }}-[instance]-YYYYMMDD`
 No specific file outputs required.
 {% endif %}
 
-{% if quality_criteria or stop_hooks %}
+{#- Check if any output has doc_spec quality criteria to avoid duplicate quality validation sections #}
+{%- set has_doc_spec_quality = namespace(value=false) -%}
+{%- for output in outputs -%}
+{%- if output.has_doc_spec and output.doc_spec and output.doc_spec.quality_criteria -%}
+{%- set has_doc_spec_quality.value = true -%}
+{%- endif -%}
+{%- endfor -%}
+{#- Only show step-level quality_criteria if no doc_spec quality criteria exist (avoids duplication) #}
+{% if (quality_criteria or stop_hooks) and not has_doc_spec_quality.value %}
 ## Quality Validation (Manual)
 
 **NOTE**: Gemini CLI does not support automated validation. Manually verify criteria before completing.