create-ai-project 1.20.2 → 1.20.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (70) hide show
  1. package/.claude/agents-en/acceptance-test-generator.md +3 -2
  2. package/.claude/agents-en/code-reviewer.md +133 -25
  3. package/.claude/agents-en/design-sync.md +5 -6
  4. package/.claude/agents-en/integration-test-reviewer.md +2 -2
  5. package/.claude/agents-en/prd-creator.md +2 -4
  6. package/.claude/agents-en/quality-fixer-frontend.md +1 -1
  7. package/.claude/agents-en/quality-fixer.md +1 -1
  8. package/.claude/agents-en/requirement-analyzer.md +7 -7
  9. package/.claude/agents-en/scope-discoverer.md +2 -2
  10. package/.claude/agents-en/solver.md +1 -2
  11. package/.claude/agents-en/task-decomposer.md +2 -2
  12. package/.claude/agents-en/task-executor-frontend.md +1 -1
  13. package/.claude/agents-en/task-executor.md +1 -1
  14. package/.claude/agents-en/technical-designer-frontend.md +5 -5
  15. package/.claude/agents-en/technical-designer.md +2 -2
  16. package/.claude/agents-en/ui-spec-designer.md +1 -1
  17. package/.claude/agents-en/work-planner.md +1 -1
  18. package/.claude/agents-ja/acceptance-test-generator.md +3 -2
  19. package/.claude/agents-ja/code-reviewer.md +133 -25
  20. package/.claude/agents-ja/design-sync.md +5 -5
  21. package/.claude/agents-ja/integration-test-reviewer.md +2 -2
  22. package/.claude/agents-ja/prd-creator.md +2 -4
  23. package/.claude/agents-ja/quality-fixer-frontend.md +1 -1
  24. package/.claude/agents-ja/quality-fixer.md +1 -1
  25. package/.claude/agents-ja/requirement-analyzer.md +7 -7
  26. package/.claude/agents-ja/scope-discoverer.md +2 -2
  27. package/.claude/agents-ja/solver.md +1 -2
  28. package/.claude/agents-ja/task-decomposer.md +2 -2
  29. package/.claude/agents-ja/task-executor-frontend.md +1 -1
  30. package/.claude/agents-ja/task-executor.md +1 -1
  31. package/.claude/agents-ja/technical-designer-frontend.md +5 -5
  32. package/.claude/agents-ja/technical-designer.md +2 -2
  33. package/.claude/agents-ja/ui-spec-designer.md +1 -1
  34. package/.claude/agents-ja/work-planner.md +1 -1
  35. package/.claude/commands-en/build.md +17 -8
  36. package/.claude/commands-en/front-build.md +25 -41
  37. package/.claude/commands-en/front-design.md +49 -17
  38. package/.claude/commands-en/front-plan.md +17 -10
  39. package/.claude/commands-en/front-review.md +37 -33
  40. package/.claude/commands-en/review.md +10 -5
  41. package/.claude/commands-ja/build.md +17 -8
  42. package/.claude/commands-ja/front-build.md +25 -41
  43. package/.claude/commands-ja/front-design.md +48 -18
  44. package/.claude/commands-ja/front-plan.md +22 -15
  45. package/.claude/commands-ja/front-review.md +37 -33
  46. package/.claude/commands-ja/review.md +10 -5
  47. package/.claude/skills-en/coding-standards/references/security-checks.md +4 -2
  48. package/.claude/skills-en/documentation-criteria/SKILL.md +8 -28
  49. package/.claude/skills-en/documentation-criteria/references/adr-template.md +5 -1
  50. package/.claude/skills-en/documentation-criteria/references/design-template.md +7 -8
  51. package/.claude/skills-en/documentation-criteria/references/plan-template.md +11 -6
  52. package/.claude/skills-en/documentation-criteria/references/prd-template.md +32 -10
  53. package/.claude/skills-en/documentation-criteria/references/task-template.md +2 -2
  54. package/.claude/skills-en/subagents-orchestration-guide/SKILL.md +20 -37
  55. package/.claude/skills-en/task-analyzer/references/skills-index.yaml +0 -2
  56. package/.claude/skills-ja/coding-standards/references/security-checks.md +4 -2
  57. package/.claude/skills-ja/documentation-criteria/SKILL.md +8 -29
  58. package/.claude/skills-ja/documentation-criteria/references/adr-template.md +5 -1
  59. package/.claude/skills-ja/documentation-criteria/references/design-template.md +7 -2
  60. package/.claude/skills-ja/documentation-criteria/references/plan-template.md +11 -6
  61. package/.claude/skills-ja/documentation-criteria/references/prd-template.md +32 -10
  62. package/.claude/skills-ja/documentation-criteria/references/task-template.md +2 -2
  63. package/.claude/skills-ja/subagents-orchestration-guide/SKILL.md +20 -35
  64. package/.claude/skills-ja/task-analyzer/references/skills-index.yaml +0 -2
  65. package/CHANGELOG.md +40 -0
  66. package/README.ja.md +51 -30
  67. package/README.md +58 -34
  68. package/docs/guides/en/skills-editing-guide.md +10 -0
  69. package/docs/guides/ja/skills-editing-guide.md +12 -2
  70. package/package.json +1 -1
@@ -6,26 +6,42 @@ description: Execute from requirement analysis to frontend design document creat
6
6
 
7
7
  ## Orchestrator Definition
8
8
 
9
- **Role**: Orchestrator
10
-
11
- **Execution Method**:
12
- - Requirement analysis performed by requirement-analyzer
13
- - UI Specification creation performed by ui-spec-designer
14
- - Design document creationperformed by technical-designer-frontend
15
- - Document reviewperformed by document-reviewer
16
-
17
- Orchestrator invokes sub-agents and passes structured JSON between them.
9
+ **Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
10
+
11
+ **Execution Protocol**:
12
+ 1. **Delegate all work** to sub-agents your role is to invoke sub-agents, pass data between them, and report results
13
+ 2. **Follow the frontend design flow below** (this command covers medium/large frontend; UI Spec is created before codebase analysis so that component structure informs the technical design):
14
+ - Execute: requirement-analyzer ui-spec-designer codebase-analyzer technical-designer-frontend → code-verifier → document-reviewer → design-sync
15
+ - **Stop at every `[Stop: ...]` marker** Wait for user approval before proceeding
16
+ 3. **Scope**: Complete when design documents receive approval
17
+
18
+ **CRITICAL**: Execute document-reviewer, design-sync, and all stopping points defined in subagents-orchestration-guide skill flows — each serves as a quality gate. Skipping any step risks undetected inconsistencies.
19
+
20
+ ## Workflow Overview
21
+
22
+ ```
23
+ Requirements → requirement-analyzer → [Stop: Scale determination]
24
+
25
+ ui-spec-designer → [Stop: UI Spec approval]
26
+
27
+ codebase-analyzer → technical-designer-frontend
28
+
29
+ code-verifier → document-reviewer
30
+
31
+ design-sync → [Stop: Design approval]
32
+ ```
18
33
 
19
34
  ## Scope Boundaries
20
35
 
21
36
  **Included in this command**:
22
37
  - Requirement analysis with requirement-analyzer
23
- - Codebase analysis with codebase-analyzer (before Design Doc creation)
38
+ - Codebase analysis with codebase-analyzer (before technical design)
24
39
  - UI Specification creation with ui-spec-designer (prototype code inquiry included)
25
40
  - ADR creation (if architecture changes, new technology, or data flow changes)
26
41
  - Design Doc creation with technical-designer-frontend
27
42
  - Design Doc verification with code-verifier (before document review)
28
43
  - Document review with document-reviewer
44
+ - Design Doc consistency verification with design-sync
29
45
 
30
46
  **Responsibility Boundary**: This command completes with frontend design document (UI Spec/ADR/Design Doc) approval. Work planning and beyond are outside scope.
31
47
 
@@ -39,7 +55,8 @@ Considering the deep impact on design, first engage in dialogue to understand th
39
55
  - Expected outcomes and success criteria
40
56
  - Relationship with existing systems
41
57
 
42
- Once requirements are moderately clarified:
58
+ Once the user has answered the three dialogue questions above, execute the process below within design scope. Follow subagents-orchestration-guide Call Examples for codebase-analyzer and code-verifier invocations.
59
+
43
60
  - Invoke **requirement-analyzer** using Agent tool
44
61
  - `subagent_type: "requirement-analyzer"`
45
62
  - `description: "Requirement analysis"`
@@ -69,15 +86,30 @@ First, analyze the existing codebase:
69
86
  - Invoke **codebase-analyzer** using Agent tool
70
87
  - `subagent_type: "codebase-analyzer"`, `description: "Codebase analysis"`, `prompt: "requirement_analysis: [JSON from Step 1]. requirements: [user requirements]. Analyze existing codebase for frontend design guidance."`
71
88
 
72
- Create appropriate design documents according to scale determination:
89
+ Create appropriate design documents according to scale determination. technical-designer-frontend presents at least two architecture alternatives (technology selection, data flow design) with trade-offs for each:
73
90
  - Invoke **technical-designer-frontend** using Agent tool
74
- - For ADR: `subagent_type: "technical-designer-frontend"`, `description: "ADR creation"`, `prompt: "Create ADR for [technical decision]"`
75
- - For Design Doc: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc creation"`, `prompt: "Create Design Doc based on requirements. Codebase analysis: [JSON from codebase-analyzer]. UI Spec is at [ui-spec path]. Inherit component structure and state design from UI Spec."`
91
+ - For ADR: `subagent_type: "technical-designer-frontend"`, `description: "ADR creation"`, `prompt: "Create ADR for [technical decision]. Present at least two alternatives with trade-offs."`
92
+ - For Design Doc: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc creation"`, `prompt: "Create Design Doc based on requirements. Codebase analysis: [JSON from codebase-analyzer]. UI Spec is at [ui-spec path]. Inherit component structure and state design from UI Spec. Present at least two architecture alternatives with trade-offs."`
76
93
  - **(Design Doc only)** Invoke **code-verifier** to verify Design Doc against existing code. Skip for ADR.
77
- - `subagent_type: "code-verifier"`, `description: "Design Doc verification"`, `prompt: "doc_type: design-doc document_path: [Design Doc path] Verify Design Doc against existing code."`
94
+ - `subagent_type: "code-verifier"`, `description: "Design Doc verification"`, `prompt: "doc_type: design-doc document_path: [Design Doc path] mode: pre-implementation (code_paths omitted — verifier discovers scope from document). Verify Design Doc against existing code."`
78
95
  - Invoke **document-reviewer** to verify consistency (pass code-verifier results for Design Doc; omit for ADR)
79
- - `subagent_type: "document-reviewer"`, `description: "Document review"`, `prompt: "doc_type: DesignDoc target: [document path] mode: composite code_verification: [JSON from code-verifier] (Design Doc only) Review for consistency and completeness."`
80
- - **[STOP]**: Present design alternatives and trade-offs, obtain user approval
96
+ - `subagent_type: "document-reviewer"`, `description: "Document review"`, `prompt: "doc_type: DesignDoc target: [document path] mode: composite code_verification: [JSON from code-verifier] (Design Doc only). Review for consistency and completeness."`
97
+
98
+ ### Step 4: Design Consistency Verification
99
+ - Invoke **design-sync** using Agent tool
100
+ - `subagent_type: "design-sync"`, `description: "Design consistency check"`, `prompt: "Check consistency across all Design Docs in docs/design/. Report conflicts and overlaps."`
101
+ - **[STOP]**: Present design documents and design-sync results, obtain user approval
102
+
103
+ ## Completion Criteria
104
+
105
+ - [ ] Executed requirement-analyzer and determined scale
106
+ - [ ] Executed codebase-analyzer and passed results to technical-designer-frontend
107
+ - [ ] Created UI Specification with ui-spec-designer (when applicable)
108
+ - [ ] Created appropriate design document (ADR or Design Doc) with technical-designer-frontend
109
+ - [ ] Executed code-verifier on Design Doc and passed results to document-reviewer (skip for ADR-only)
110
+ - [ ] Executed document-reviewer and addressed feedback
111
+ - [ ] Executed design-sync for consistency verification
112
+ - [ ] Obtained user approval for design document
81
113
 
82
114
  ## Output Example
83
115
  Frontend design phase completed.
@@ -6,13 +6,16 @@ description: Create frontend work plan from design document and obtain plan appr
6
6
 
7
7
  ## Orchestrator Definition
8
8
 
9
- **Role**: Orchestrator
9
+ **Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
10
10
 
11
- **Execution Method**:
12
- - Test skeleton generation performed by acceptance-test-generator
13
- - Work plan creation performed by work-planner
11
+ **Execution Protocol**:
12
+ 1. **Delegate all work** to sub-agents your role is to invoke sub-agents, pass data between them, and report results
13
+ 2. **Follow subagents-orchestration-guide skill planning flow**:
14
+ - Execute steps defined below
15
+ - **Stop and obtain approval** for plan content before completion
16
+ 3. **Scope**: See Scope Boundaries below
14
17
 
15
- Orchestrator invokes sub-agents and passes structured JSON between them.
18
+ **CRITICAL**: Always execute acceptance-test-generator before work-planner the test skeleton is a required input per subagents-orchestration-guide medium/large flow.
16
19
 
17
20
  ## Scope Boundaries
18
21
 
@@ -24,14 +27,14 @@ Orchestrator invokes sub-agents and passes structured JSON between them.
24
27
 
25
28
  **Responsibility Boundary**: This command completes with work plan approval.
26
29
 
27
- Create frontend work plan with the following process:
30
+ Follow the planning process below:
28
31
 
29
32
  ## Execution Process
30
33
 
31
34
  ### Step 1: Design Document Selection
32
- ! ls -la docs/design/*.md | head -10
33
- - Check for existence of design documents, notify user if none exist
34
- - Present options if multiple exist (can be specified with $ARGUMENTS)
35
+ ! ls -la docs/design/*.md | head -10
36
+ - Check for existence of design documents, notify user if none exist
37
+ - Present options if multiple exist (can be specified with $ARGUMENTS)
35
38
 
36
39
  ### Step 2: Test Skeleton Generation
37
40
  Invoke acceptance-test-generator using Agent tool:
@@ -40,13 +43,17 @@ Invoke acceptance-test-generator using Agent tool:
40
43
  - If UI Spec exists: `prompt: "Generate test skeletons from Design Doc at [path]. UI Spec at [ui-spec path]."`
41
44
  - If no UI Spec: `prompt: "Generate test skeletons from Design Doc at [path]."`
42
45
 
46
+ Pass integration test file path and E2E test file path to work-planner according to subagents-orchestration-guide "acceptance-test-generator → work-planner" section.
47
+
43
48
  ### Step 3: Work Plan Creation
44
49
  Invoke work-planner using Agent tool:
45
50
  - `subagent_type`: "work-planner"
46
51
  - `description`: "Work plan creation"
47
52
  - `prompt`: "Create work plan from Design Doc at [path]. Integration test file: [integration test path from step 2]. E2E test file: [E2E test path from step 2]. Integration tests are created simultaneously with each phase implementation, E2E tests are executed only in final phase."
48
53
 
49
- Interact with user to complete plan and obtain approval for plan content. Clarify specific implementation steps and risks.
54
+ - Follow subagents-orchestration-guide Prompt Construction Rule for additional prompt parameters
55
+ - Present work plan to user for review. If user requests changes, re-invoke work-planner with revised parameters
56
+ - Highlight steps with unclear scope or external dependencies and ask user to confirm
50
57
 
51
58
  **Scope**: Up to work plan creation and obtaining approval for plan content.
52
59
 
@@ -4,24 +4,25 @@ description: Design Doc compliance and security validation with optional auto-fi
4
4
 
5
5
  **Command Context**: Post-implementation quality assurance command for React/TypeScript frontend
6
6
 
7
- ## Execution Method
7
+ ## Orchestrator Definition
8
8
 
9
- - Compliance validation -> performed by code-reviewer
10
- - Security validation -> performed by security-reviewer
11
- - Rule analysis -> performed by rule-advisor
12
- - Fix implementation -> performed by task-executor-frontend
13
- - Quality checks -> performed by quality-fixer-frontend
14
- - Re-validation -> performed by code-reviewer / security-reviewer
9
+ **Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
15
10
 
16
- Orchestrator invokes sub-agents and passes structured JSON between them.
11
+ **First Action**: Register Steps 1-11 using TaskCreate before any execution.
17
12
 
18
- Design Doc (uses most recent if omitted): $ARGUMENTS
13
+ ## Execution Method
14
+
15
+ - Compliance validation → performed by code-reviewer
16
+ - Security validation → performed by security-reviewer
17
+ - Fix implementation → performed by task-executor-frontend
18
+ - Quality checks → performed by quality-fixer-frontend
19
+ - Re-validation → performed by code-reviewer / security-reviewer
19
20
 
20
- **Think deeply** Understand the essence of compliance validation and execute:
21
+ Design Doc (uses most recent if omitted): $ARGUMENTS
21
22
 
22
23
  ## Execution Flow
23
24
 
24
- ### 1. Prerequisite Check
25
+ ### Step 1: Prerequisite Check
25
26
  ```bash
26
27
  # Identify Design Doc
27
28
  ls docs/design/*.md | grep -v template | tail -1
@@ -30,15 +31,15 @@ ls docs/design/*.md | grep -v template | tail -1
30
31
  git diff --name-only main...HEAD
31
32
  ```
32
33
 
33
- ### 2. Execute code-reviewer
34
+ ### Step 2: Execute code-reviewer
34
35
  Invoke code-reviewer using Agent tool:
35
36
  - `subagent_type`: "code-reviewer"
36
37
  - `description`: "Code compliance review"
37
- - `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report with complianceRate, verdict, acceptanceCriteria, and qualityIssues."
38
+ - `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report."
38
39
 
39
40
  **Store output as**: `$STEP_2_OUTPUT`
40
41
 
41
- ### 3. Execute security-reviewer
42
+ ### Step 3: Execute security-reviewer
42
43
  Invoke security-reviewer using Agent tool:
43
44
  - `subagent_type`: "security-reviewer"
44
45
  - `description`: "Security review"
@@ -46,7 +47,7 @@ Invoke security-reviewer using Agent tool:
46
47
 
47
48
  **Store output as**: `$STEP_3_OUTPUT`
48
49
 
49
- ### 4. Verdict and Response
50
+ ### Step 4: Verdict and Response
50
51
 
51
52
  **If security-reviewer returned `blocked`**: Stop immediately. Report the blocked finding and escalate to user. Do not proceed to fix steps.
52
53
 
@@ -63,10 +64,15 @@ Invoke security-reviewer using Agent tool:
63
64
  ```
64
65
  Code Compliance: [complianceRate from code-reviewer]
65
66
  Verdict: [verdict from code-reviewer]
67
+ Identifier Match Rate: [identifierMatchRate from code-reviewer]
66
68
  Acceptance Criteria:
67
- - [fulfilled] [item]
69
+ - [fulfilled] [item] (confidence: [high/medium/low])
68
70
  - [partially_fulfilled] [item]: [gap] — [suggestion]
69
71
  - [unfulfilled] [item]: [gap] — [suggestion]
72
+ Identifier Mismatches:
73
+ - [identifier]: DD=[designDocValue] Code=[codeValue] at [location]
74
+ Quality Findings:
75
+ - [category] [location]: [description] — [rationale]
70
76
 
71
77
  Security Review: [status from security-reviewer]
72
78
  Findings by category:
@@ -79,46 +85,44 @@ Security Review: [status from security-reviewer]
79
85
  Execute fixes? (y/n):
80
86
  ```
81
87
 
82
- If both pass and user selects `n`: Skip fix steps, proceed to Final Report.
88
+ If both pass and user selects `n`: Skip Steps 5-10, proceed to Step 11.
83
89
 
84
- If user selects `y`:
90
+ ### Step 5: Load Task Template
85
91
 
86
- ## Pre-fix Metacognition
92
+ Read documentation-criteria skill to obtain the task file template (references/task-template.md) for Step 6.
87
93
 
88
- ### 5. Execute rule-advisor
89
- Invoke rule-advisor using Agent tool:
90
- - `subagent_type`: "rule-advisor"
91
- - `description`: "Analyze fix approach"
92
- - `prompt`: "Task: Fix review findings. Code issues: $STEP_2_OUTPUT. Security findings: $STEP_3_OUTPUT. Analyze fix essence and select appropriate rules."
94
+ ### Step 6: Create Task File
93
95
 
94
- ### 6. Create Task File
95
- Register work steps using TaskCreate. Always include: first "Confirm skill constraints", final "Verify skill fidelity". Create task file following task template (see documentation-criteria skill) -> `docs/plans/tasks/review-fixes-YYYYMMDD.md`. Include both code compliance issues and security requiredFixes.
96
+ Create task file at `docs/plans/tasks/review-fixes-YYYYMMDD.md`
97
+ Include both code compliance issues and security requiredFixes.
96
98
 
97
- ### 7. Execute Fixes
99
+ ### Step 7: Execute Fixes
98
100
  Invoke task-executor-frontend using Agent tool:
99
101
  - `subagent_type`: "task-executor-frontend"
100
102
  - `description`: "Execute review fixes"
101
103
  - `prompt`: "Task file: docs/plans/tasks/review-fixes-YYYYMMDD.md. Apply staged fixes (stops at 5 files)."
102
104
 
103
- ### 8. Quality Check
105
+ ### Step 8: Quality Check
104
106
  Invoke quality-fixer-frontend using Agent tool:
105
107
  - `subagent_type`: "quality-fixer-frontend"
106
108
  - `description`: "Quality gate check"
107
109
  - `prompt`: "Confirm quality gate passage for fixed files."
108
110
 
109
- ### 9. Re-validate code-reviewer
111
+ ### Step 9: Re-validate code-reviewer
112
+
110
113
  Invoke code-reviewer using Agent tool:
111
114
  - `subagent_type`: "code-reviewer"
112
115
  - `description`: "Re-validate compliance"
113
- - `prompt`: "Re-validate Design Doc compliance after fixes. Prior issues: $STEP_2_OUTPUT. Design Doc: [path]. Implementation files: [file list]."
116
+ - `prompt`: "Re-validate Design Doc compliance after fixes. Design Doc: [path]. Implementation files: [file list]. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved."
114
117
 
115
- ### 10. Re-validate security-reviewer (only if security fixes were applied)
116
- Invoke security-reviewer using Agent tool:
118
+ ### Step 10: Re-validate security-reviewer
119
+
120
+ Invoke security-reviewer using Agent tool (only if security fixes were applied):
117
121
  - `subagent_type`: "security-reviewer"
118
122
  - `description`: "Re-validate security"
119
123
  - `prompt`: "Re-validate security after fixes. Prior findings: $STEP_3_OUTPUT. Design Doc: [path]. Implementation files: [file list]."
120
124
 
121
- ### Final Report
125
+ ### Step 11: Final Report
122
126
  ```
123
127
  Code Compliance:
124
128
  Initial: [X]%
@@ -33,7 +33,7 @@ git diff --name-only main...HEAD
33
33
  Invoke code-reviewer using Agent tool:
34
34
  - `subagent_type`: "code-reviewer"
35
35
  - `description`: "Code compliance review"
36
- - `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report with complianceRate, verdict, acceptanceCriteria, and qualityIssues."
36
+ - `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report."
37
37
 
38
38
  **Store output as**: `$STEP_2_OUTPUT`
39
39
 
@@ -62,10 +62,15 @@ Invoke security-reviewer using Agent tool:
62
62
  ```
63
63
  Code Compliance: [complianceRate from code-reviewer]
64
64
  Verdict: [verdict from code-reviewer]
65
+ Identifier Match Rate: [identifierMatchRate from code-reviewer]
65
66
  Acceptance Criteria:
66
- - [fulfilled] [item]
67
+ - [fulfilled] [item] (confidence: [high/medium/low])
67
68
  - [partially_fulfilled] [item]: [gap] — [suggestion]
68
69
  - [unfulfilled] [item]: [gap] — [suggestion]
70
+ Identifier Mismatches:
71
+ - [identifier]: DD=[designDocValue] Code=[codeValue] at [location]
72
+ Quality Findings:
73
+ - [category] [location]: [description] — [rationale]
69
74
 
70
75
  Security Review: [status from security-reviewer]
71
76
  Findings by category:
@@ -80,9 +85,9 @@ Execute fixes? (y/n):
80
85
 
81
86
  If both pass and user selects `n`: Skip Steps 5-10, proceed to Step 11.
82
87
 
83
- ### 5. Execute Skill
88
+ ### 5. Load Task Template
84
89
 
85
- Execute Skill: documentation-criteria (for task file template)
90
+ Read documentation-criteria skill to obtain the task file template (references/task-template.md) for Step 6.
86
91
 
87
92
  ### 6. Create Task File
88
93
 
@@ -108,7 +113,7 @@ Invoke quality-fixer using Agent tool:
108
113
  Invoke code-reviewer using Agent tool:
109
114
  - `subagent_type`: "code-reviewer"
110
115
  - `description`: "Re-validate compliance"
111
- - `prompt`: "Re-validate Design Doc compliance after fixes. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved."
116
+ - `prompt`: "Re-validate Design Doc compliance after fixes. Design Doc: [path]. Implementation files: [file list]. Prior compliance issues: $STEP_2_OUTPUT. Verify each prior issue is resolved."
112
117
 
113
118
  ### 10. Re-validate security-reviewer
114
119
 
@@ -62,7 +62,7 @@ Agentツールでtask-decomposerを呼び出す:
62
62
  ! ls -la docs/plans/tasks/*.md | head -10
63
63
  ```
64
64
 
65
- **フロー**: タスク生成 → 自律実行(この順序で実行)
65
+ **フロー**: タスク生成 → 自律実行(この順序で実行)
66
66
 
67
67
  ## 実行前チェックリスト
68
68
 
@@ -101,14 +101,23 @@ Agentツールでtask-decomposerを呼び出す:
101
101
 
102
102
  承認確認後、自律実行モードを開始。要件変更を検知した場合は即座に停止。
103
103
 
104
- ## Security Review(全タスク完了後)
104
+ ## 実装後検証(全タスク完了後)
105
105
 
106
- 全タスクサイクル完了後、完了レポートの前にsecurity-reviewerを実行:
107
- 1. **Agent tool** (subagent_type: "security-reviewer") → Design Docパスと実装ファイルリストを渡す
108
- 2. レスポンスを確認:
109
- - `approved` または `approved_with_notes`完了レポートへ(notesがあれば含める)
110
- - `needs_revision` task-executorで`requiredFixes`を実行、quality-fixer実行後、security-reviewerを再実行
111
- - `blocked` → ユーザーにエスカレーション
106
+ 全タスクサイクル完了後、完了レポートの前に検証エージェントを**並列実行**:
107
+
108
+ 1. **両方を並列で実行** (Agent tool):
109
+ - code-verifier (subagent_type: "code-verifier")`doc_type: design-doc`、Design Docパス、`code_paths`: 実装ファイルリスト(`git diff --name-only main...HEAD`)
110
+ - security-reviewer (subagent_type: "security-reviewer") → Design Docパス、実装ファイルリスト
111
+
112
+ 2. **結果の統合** — 合格/不合格の基準はsubagents-orchestration-guideの実装後検証セクション参照。統合検証レポートをユーザーに提示。
113
+
114
+ 3. **修正サイクル**(いずれかの検証エージェントが不合格の場合、最大2回):
115
+ - 全ての対応可能な検出事項を1つのタスクファイルに統合
116
+ - task-executorで統合修正を実行 → quality-fixer
117
+ - 不合格の検証エージェントのみ再実行
118
+ - 2回のサイクル後も不合格が残る場合 → 残存する検出事項とともにユーザーにエスカレーション
119
+
120
+ 4. **全て合格** → 完了レポートへ
112
121
 
113
122
  ## 出力例
114
123
  実装フェーズが完了しました。
@@ -4,20 +4,13 @@ description: フロントエンド実装を自律実行モードで実行
4
4
 
5
5
  ## オーケストレーター定義
6
6
 
7
- **コアアイデンティティ**: 「私は作業者ではない。オーケストレーターである。」(subagents-orchestration-guideスキル参照)
8
-
9
- **実行方法**:
10
- - タスク分解 → task-decomposerが実行
11
- - フロントエンド実装 → task-executor-frontendが実行
12
- - 品質チェックと修正 → quality-fixer-frontendが実行
13
- - コミット → オーケストレーター(Bashツール)
14
-
15
- オーケストレーターはサブエージェントを呼び出し、構造化JSONを渡します。
7
+ **コアアイデンティティ**: 「私はオーケストレーターである。」(subagents-orchestration-guideスキル参照)
16
8
 
17
9
  **実行プロトコル**:
18
- 1. **全作業をAgentツールでサブエージェントに委譲** — サブエージェントの呼び出し、データの受け渡し、結果の報告(許可ツール: subagents-orchestration-guideスキル「オーケストレーターの許可ツール」参照)
10
+ 1. **全作業をAgentツールでサブエージェントに委譲** — サブエージェントの呼び出し、成果物パスの受け渡し、結果の報告(許可ツール: subagents-orchestration-guideスキル「オーケストレーターの許可ツール」参照)
19
11
  2. **4ステップサイクルに厳密に従う**: task-executor-frontend → エスカレーションチェック → quality-fixer-frontend → commit
20
12
  3. **自律実行モード移行**: ユーザーの実行指示とタスクファイルの存在をもってバッチ承認とする
13
+ 4. **スコープ**: 全タスクのコミット完了またはエスカレーションで責務完了
21
14
 
22
15
  **重要**: 全てのコミット前にquality-fixer-frontendを実行。
23
16
 
@@ -69,7 +62,7 @@ Agentツールでtask-decomposerを呼び出す:
69
62
  ! ls -la docs/plans/tasks/*.md | head -10
70
63
  ```
71
64
 
72
- **フロー**: タスク生成 → 自律実行(この順序で実行)
65
+ **フロー**: タスク生成 → 自律実行(この順序で実行)
73
66
 
74
67
  ## 実行前チェックリスト
75
68
 
@@ -79,40 +72,22 @@ Agentツールでtask-decomposerを呼び出す:
79
72
  - コミット機能が利用不可 → 自律実行モード前にエスカレーション
80
73
  - その他の環境(テスト、品質ツール) → サブエージェントがエスカレーション
81
74
 
82
- ## タスク実行サイクル(4ステップサイクル) - フロントエンド特化
83
-
75
+ ## タスク実行サイクル(4ステップサイクル)
84
76
  **必須実行サイクル**: `task-executor-frontend → エスカレーションチェック → quality-fixer-frontend → commit`
85
77
 
86
- ### サブエージェント呼び出し方法
87
- Agentツールを使用してサブエージェントを呼び出す:
88
- - `subagent_type`: エージェント名
89
- - `description`: タスクの簡潔な説明(3-5語)
90
- - `prompt`: 具体的な指示内容
91
-
92
- ### 構造化レスポンス仕様
93
- 各サブエージェントはJSON形式で応答:
94
- - **task-executor-frontend**: status, filesModified, testsAdded, requiresTestReview, readyForQualityCheck
95
- - **integration-test-reviewer**: status (approved/needs_revision/blocked), requiredFixes
96
- - **quality-fixer-frontend**: status, checksPerformed, fixesApplied, approved
97
-
98
- ### 各タスクの実行フロー
99
-
100
78
  各タスクで必須:
101
-
102
79
  1. **TaskCreateでタスク登録**: 作業ステップを登録。必ず含める: 最初に「スキル制約の確認」、最後に「スキル忠実度の検証」
103
- 2. **task-executor-frontend実行**: フロントエンド実装を実行
104
- - 呼び出し例: `subagent_type: "task-executor-frontend"`, `description: "タスク実行"`, `prompt: "タスクファイル: docs/plans/tasks/[ファイル名].md 実装を実行"`
80
+ 2. **Agent tool** (subagent_type: "task-executor-frontend") → タスクファイルパスをpromptに渡し、構造化レスポンスを受け取る
105
81
  3. **task-executor-frontendレスポンスチェック**:
106
82
  - `status: "escalation_needed"` または `"blocked"` → 停止してユーザーにエスカレーション
107
83
  - `requiresTestReview` が `true` → **integration-test-reviewer**を実行
108
84
  - `needs_revision` → `requiredFixes`を添えてステップ2に戻る
109
85
  - `approved` → ステップ4へ
110
86
  - `readyForQualityCheck: true` → ステップ4へ
111
- 4. **quality-fixer-frontend実行**: 全フロントエンド品質チェックと修正を実行
112
- - 呼び出し例: `subagent_type: "quality-fixer-frontend"`, `description: "品質チェック"`, `prompt: "全てのフロントエンド品質チェックと修正を実行"`
113
- 5. **コミット実行**: `approved: true`確認後、即座にgit commitを実行。`changeSummary`をコミットメッセージに使用。
87
+ 4. **quality-fixer-frontend実行**: 全品質チェックと修正を実行
88
+ 5. **承認後コミット**: quality-fixer-frontendの`approved: true`確認後 git commitを実行
114
89
 
115
- **重要**: 例外なく全ての構造化レスポンスを監視し、全ての品質ゲートが通過することを確保。
90
+ **重要**: 全てのサブエージェントレスポンスのstatusフィールドをパースし、4ステップサイクルの対応ブランチを実行。quality-fixer-frontendが`approved: true`を返すまで次のタスクに進まない。
116
91
 
117
92
  ## サブエージェント呼び出し時の制約
118
93
 
@@ -128,14 +103,23 @@ Agentツールを使用してサブエージェントを呼び出す:
128
103
 
129
104
  承認ステータスを確認してから進む。確認後、自律実行モードを開始。要件変更を検出したら即座に停止。
130
105
 
131
- ## Security Review(全タスク完了後)
106
+ ## 実装後検証(全タスク完了後)
107
+
108
+ 全タスクサイクル完了後、完了レポートの前に検証エージェントを**並列実行**:
109
+
110
+ 1. **両方を並列で実行** (Agent tool):
111
+ - code-verifier (subagent_type: "code-verifier") → `doc_type: design-doc`、Design Docパス、`code_paths`: 実装ファイルリスト(`git diff --name-only main...HEAD`)
112
+ - security-reviewer (subagent_type: "security-reviewer") → Design Docパス、実装ファイルリスト
113
+
114
+ 2. **結果の統合** — 合格/不合格の基準はsubagents-orchestration-guideの実装後検証セクション参照。統合検証レポートをユーザーに提示。
115
+
116
+ 3. **修正サイクル**(いずれかの検証エージェントが不合格の場合、最大2回):
117
+ - 全ての対応可能な検出事項を1つのタスクファイルに統合
118
+ - task-executor-frontendで統合修正を実行 → quality-fixer-frontend
119
+ - 不合格の検証エージェントのみ再実行
120
+ - 2回のサイクル後も不合格が残る場合 → 残存する検出事項とともにユーザーにエスカレーション
132
121
 
133
- 全タスクサイクル完了後、完了レポートの前にsecurity-reviewerを実行:
134
- 1. **Agent tool** (subagent_type: "security-reviewer") → Design Docパスと実装ファイルリストを渡す
135
- 2. レスポンスを確認:
136
- - `approved` または `approved_with_notes` → 完了レポートへ(notesがあれば含める)
137
- - `needs_revision` → task-executor-frontendで`requiredFixes`を実行、quality-fixer-frontend実行後、security-reviewerを再実行
138
- - `blocked` → ユーザーにエスカレーション
122
+ 4. **全て合格** → 完了レポートへ
139
123
 
140
124
  ## 出力例
141
125
  フロントエンド実装フェーズ完了。
@@ -6,26 +6,42 @@ description: 要件分析からフロントエンド設計ドキュメント作
6
6
 
7
7
  ## オーケストレーター定義
8
8
 
9
- **Role**: オーケストレーター
10
-
11
- **実行方法**:
12
- - 要件分析 requirement-analyzerが実行
13
- - UI Spec作成 ui-spec-designerが実行
14
- - 設計書作成 → technical-designer-frontendが実行
15
- - ドキュメントレビューdocument-reviewerが実行
16
-
17
- オーケストレーターはサブエージェントを呼び出し、構造化JSONを渡します。
9
+ **コアアイデンティティ**: 「私はオーケストレーターである。」(subagents-orchestration-guideスキル参照)
10
+
11
+ **実行プロトコル**:
12
+ 1. **全ての作業をサブエージェントに委譲** サブエージェントを呼び出し、データを橋渡しし、結果を報告する
13
+ 2. **以下のフロントエンド設計フローに従う**(このコマンドは中規模/大規模のフロントエンドを対象。UI Specはコードベース分析の前に作成する コンポーネント構造が技術設計に反映されるため):
14
+ - 実行: requirement-analyzer ui-spec-designer → codebase-analyzer → technical-designer-frontend → code-verifier → document-reviewer → design-sync
15
+ - **`[停止: ...]`マーカーごとに停止** ユーザー承認を待つ
16
+ 3. **スコープ**: 設計ドキュメントの承認をもって完了
17
+
18
+ **重要**: document-reviewer、design-sync、subagents-orchestration-guideスキルフローで定義された全ての停止ポイントを実行すること — 各ステップが品質ゲートとして機能する。スキップは検出されない不整合のリスクにつながる。
19
+
20
+ ## ワークフロー概要
21
+
22
+ ```
23
+ 要件 → requirement-analyzer → [停止: 規模判定]
24
+
25
+ ui-spec-designer → [停止: UI Spec承認]
26
+
27
+ codebase-analyzer → technical-designer-frontend
28
+
29
+ code-verifier → document-reviewer
30
+
31
+ design-sync → [停止: 設計承認]
32
+ ```
18
33
 
19
34
  ## スコープ境界
20
35
 
21
36
  **実行内容**:
22
37
  - requirement-analyzerによる要件分析
23
- - codebase-analyzerによるコードベース分析(Design Doc作成前に実施)
38
+ - codebase-analyzerによるコードベース分析(技術設計の前に実施)
24
39
  - ui-spec-designerによるUI Spec作成(プロトタイプコード確認を含む)
25
40
  - ADR作成(アーキテクチャ変更、新技術、データフロー変更がある場合)
26
41
  - technical-designer-frontendによるDesign Doc作成
27
42
  - code-verifierによるDesign Doc検証(ドキュメントレビューの前に実施)
28
43
  - document-reviewerによるドキュメントレビュー
44
+ - design-syncによるDesign Doc横断整合性検証
29
45
 
30
46
  **責務境界**: このコマンドはフロントエンド設計ドキュメント(UI Spec/ADR/Design Doc)の承認で責務完了。作業計画以降はスコープ外。
31
47
 
@@ -39,7 +55,7 @@ description: 要件分析からフロントエンド設計ドキュメント作
39
55
  - 期待する成果と成功基準
40
56
  - 既存システムとの関係
41
57
 
42
- 要件がある程度明確になったら:
58
+ ユーザーが上記3つの質問に回答した後、設計スコープ内で以下のプロセスを実行する。codebase-analyzerとcode-verifierの呼び出しはsubagents-orchestration-guideのCall Examplesに従う。
43
59
  - Agentツールで**requirement-analyzer**を呼び出す
44
60
  - `subagent_type: "requirement-analyzer"`
45
61
  - `description: "要件分析"`
@@ -61,7 +77,7 @@ UI Specを作成:
61
77
  - PRDあり+プロトタイプなし: `prompt: "[パス]のPRDからUI Specを作成。プロトタイプコードなし。"`
62
78
  - PRDなし(中規模): `prompt: "以下の要件に基づいてUI Specを作成: [requirement-analyzerの出力を渡す]。PRDなし。"`(プロトタイプパスがあれば追加)
63
79
  - **document-reviewer**でUI Specを検証
64
- - `subagent_type: "document-reviewer"`, `description: "UI Specレビュー"`, `prompt: "doc_type: UISpec target: [ui-specパス] 整合性と完成度をレビュー"`
80
+ - `subagent_type: "document-reviewer"`, `description: "UI Specレビュー"`, `prompt: "doc_type: UISpec target: [ui-specパス] 整合性と完全性をレビュー"`
65
81
  - **[停止]**: UI Specをユーザーに提示し承認を取得
66
82
 
67
83
  ### Step 3: 設計ドキュメント作成フェーズ
@@ -69,15 +85,29 @@ UI Specを作成:
69
85
  - Agentツールで**codebase-analyzer**を呼び出す
70
86
  - `subagent_type: "codebase-analyzer"`, `description: "コードベース分析"`, `prompt: "requirement_analysis: [Step 1のJSON]. requirements: [ユーザー要件]. フロントエンド設計ガイダンスのため既存コードベースを分析。"`
71
87
 
72
- 規模判定に応じて適切な設計ドキュメントを作成:
88
+ 規模判定に応じて適切な設計ドキュメントを作成。technical-designer-frontendは技術選択・データフロー設計について少なくとも2つの選択肢をトレードオフとともに提示:
73
89
  - Agentツールで**technical-designer-frontend**を呼び出す
74
- - ADRの場合: `subagent_type: "technical-designer-frontend"`, `description: "ADR作成"`, `prompt: "[技術決定]のADRを作成"`
75
- - Design Docの場合: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc作成"`, `prompt: "要件に基づいてDesign Docを作成。コードベース分析: [codebase-analyzerのJSON]。UI Specは[ui-specパス]。UI Specのコンポーネント構造と状態設計を継承。"`
90
+ - ADRの場合: `subagent_type: "technical-designer-frontend"`, `description: "ADR作成"`, `prompt: "[技術決定]のADRを作成。少なくとも2つの選択肢をトレードオフとともに提示。"`
91
+ - Design Docの場合: `subagent_type: "technical-designer-frontend"`, `description: "Design Doc作成"`, `prompt: "要件に基づいてDesign Docを作成。コードベース分析: [codebase-analyzerのJSON]。UI Specは[ui-specパス]。UI Specのコンポーネント構造と状態設計を継承。少なくとも2つのアーキテクチャ選択肢をトレードオフとともに提示。"`
76
92
  - **(Design Docのみ)** **code-verifier**でDesign Docを既存コードに対して検証。ADRの場合はスキップ。
77
- - `subagent_type: "code-verifier"`, `description: "Design Doc検証"`, `prompt: "doc_type: design-doc document_path: [Design Docパス] Design Docを既存コードに対して検証。"`
93
+ - `subagent_type: "code-verifier"`, `description: "Design Doc検証"`, `prompt: "doc_type: design-doc document_path: [Design Docパス] mode: pre-implementation (code_paths省略 — verifierがドキュメントからスコープを発見). Design Docを既存コードに対して検証。"`
78
94
  - **document-reviewer**で整合性検証(Design Docの場合はcode-verifier結果を渡す。ADRの場合は省略)
79
- - `subagent_type: "document-reviewer"`, `description: "ドキュメントレビュー"`, `prompt: "doc_type: DesignDoc target: [ドキュメントパス] mode: composite code_verification: [code-verifierのJSON](Design Docのみ) 整合性と完成度をレビュー。"`
80
- - **[停止]**: 設計の選択肢とトレードオフを提示し、ユーザー承認を取得
95
+ - `subagent_type: "document-reviewer"`, `description: "ドキュメントレビュー"`, `prompt: "doc_type: DesignDoc target: [ドキュメントパス] mode: composite code_verification: [code-verifierのJSON](Design Docのみ) 整合性と完全性をレビュー。"`
96
+ ### Step 4: 設計整合性検証
97
+ - Agentツールで**design-sync**を呼び出す
98
+ - `subagent_type: "design-sync"`, `description: "設計整合性チェック"`, `prompt: "docs/design/配下の全Design Doc間の整合性をチェック。矛盾と重複を報告。"`
99
+ - **[停止]**: 設計ドキュメントとdesign-sync結果を提示し、ユーザー承認を取得
100
+
101
+ ## 完了条件
102
+
103
+ - [ ] requirement-analyzerを実行し規模を判定
104
+ - [ ] codebase-analyzerを実行し結果をtechnical-designer-frontendに渡した
105
+ - [ ] ui-spec-designerでUI Specを作成(該当時)
106
+ - [ ] technical-designer-frontendで適切な設計ドキュメント(ADRまたはDesign Doc)を作成
107
+ - [ ] Design Docに対してcode-verifierを実行し結果をdocument-reviewerに渡した(ADRのみの場合はスキップ)
108
+ - [ ] document-reviewerを実行しフィードバックに対応
109
+ - [ ] design-syncで整合性検証を実行
110
+ - [ ] 設計ドキュメントのユーザー承認を取得
81
111
 
82
112
  ## 出力例
83
113
  フロントエンド設計フェーズ完了。