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.
- package/.claude/agents-en/acceptance-test-generator.md +3 -2
- package/.claude/agents-en/code-reviewer.md +133 -25
- package/.claude/agents-en/design-sync.md +5 -6
- package/.claude/agents-en/integration-test-reviewer.md +2 -2
- package/.claude/agents-en/prd-creator.md +2 -4
- package/.claude/agents-en/quality-fixer-frontend.md +1 -1
- package/.claude/agents-en/quality-fixer.md +1 -1
- package/.claude/agents-en/requirement-analyzer.md +7 -7
- package/.claude/agents-en/scope-discoverer.md +2 -2
- package/.claude/agents-en/solver.md +1 -2
- package/.claude/agents-en/task-decomposer.md +2 -2
- package/.claude/agents-en/task-executor-frontend.md +1 -1
- package/.claude/agents-en/task-executor.md +1 -1
- package/.claude/agents-en/technical-designer-frontend.md +5 -5
- package/.claude/agents-en/technical-designer.md +2 -2
- package/.claude/agents-en/ui-spec-designer.md +1 -1
- package/.claude/agents-en/work-planner.md +1 -1
- package/.claude/agents-ja/acceptance-test-generator.md +3 -2
- package/.claude/agents-ja/code-reviewer.md +133 -25
- package/.claude/agents-ja/design-sync.md +5 -5
- package/.claude/agents-ja/integration-test-reviewer.md +2 -2
- package/.claude/agents-ja/prd-creator.md +2 -4
- package/.claude/agents-ja/quality-fixer-frontend.md +1 -1
- package/.claude/agents-ja/quality-fixer.md +1 -1
- package/.claude/agents-ja/requirement-analyzer.md +7 -7
- package/.claude/agents-ja/scope-discoverer.md +2 -2
- package/.claude/agents-ja/solver.md +1 -2
- package/.claude/agents-ja/task-decomposer.md +2 -2
- package/.claude/agents-ja/task-executor-frontend.md +1 -1
- package/.claude/agents-ja/task-executor.md +1 -1
- package/.claude/agents-ja/technical-designer-frontend.md +5 -5
- package/.claude/agents-ja/technical-designer.md +2 -2
- package/.claude/agents-ja/ui-spec-designer.md +1 -1
- package/.claude/agents-ja/work-planner.md +1 -1
- package/.claude/commands-en/build.md +17 -8
- package/.claude/commands-en/front-build.md +25 -41
- package/.claude/commands-en/front-design.md +49 -17
- package/.claude/commands-en/front-plan.md +17 -10
- package/.claude/commands-en/front-review.md +37 -33
- package/.claude/commands-en/review.md +10 -5
- package/.claude/commands-ja/build.md +17 -8
- package/.claude/commands-ja/front-build.md +25 -41
- package/.claude/commands-ja/front-design.md +48 -18
- package/.claude/commands-ja/front-plan.md +22 -15
- package/.claude/commands-ja/front-review.md +37 -33
- package/.claude/commands-ja/review.md +10 -5
- package/.claude/skills-en/coding-standards/references/security-checks.md +4 -2
- package/.claude/skills-en/documentation-criteria/SKILL.md +8 -28
- package/.claude/skills-en/documentation-criteria/references/adr-template.md +5 -1
- package/.claude/skills-en/documentation-criteria/references/design-template.md +7 -8
- package/.claude/skills-en/documentation-criteria/references/plan-template.md +11 -6
- package/.claude/skills-en/documentation-criteria/references/prd-template.md +32 -10
- package/.claude/skills-en/documentation-criteria/references/task-template.md +2 -2
- package/.claude/skills-en/subagents-orchestration-guide/SKILL.md +20 -37
- package/.claude/skills-en/task-analyzer/references/skills-index.yaml +0 -2
- package/.claude/skills-ja/coding-standards/references/security-checks.md +4 -2
- package/.claude/skills-ja/documentation-criteria/SKILL.md +8 -29
- package/.claude/skills-ja/documentation-criteria/references/adr-template.md +5 -1
- package/.claude/skills-ja/documentation-criteria/references/design-template.md +7 -2
- package/.claude/skills-ja/documentation-criteria/references/plan-template.md +11 -6
- package/.claude/skills-ja/documentation-criteria/references/prd-template.md +32 -10
- package/.claude/skills-ja/documentation-criteria/references/task-template.md +2 -2
- package/.claude/skills-ja/subagents-orchestration-guide/SKILL.md +20 -35
- package/.claude/skills-ja/task-analyzer/references/skills-index.yaml +0 -2
- package/CHANGELOG.md +40 -0
- package/README.ja.md +51 -30
- package/README.md +58 -34
- package/docs/guides/en/skills-editing-guide.md +10 -0
- package/docs/guides/ja/skills-editing-guide.md +12 -2
- 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
|
-
**
|
|
10
|
-
|
|
11
|
-
**Execution
|
|
12
|
-
-
|
|
13
|
-
|
|
14
|
-
-
|
|
15
|
-
-
|
|
16
|
-
|
|
17
|
-
|
|
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
|
|
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
|
|
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
|
-
|
|
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
|
-
**
|
|
9
|
+
**Core Identity**: "I am an orchestrator." (see subagents-orchestration-guide skill)
|
|
10
10
|
|
|
11
|
-
**Execution
|
|
12
|
-
-
|
|
13
|
-
|
|
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
|
-
|
|
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
|
-
|
|
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
|
-
|
|
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
|
-
##
|
|
7
|
+
## Orchestrator Definition
|
|
8
8
|
|
|
9
|
-
|
|
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
|
-
|
|
11
|
+
**First Action**: Register Steps 1-11 using TaskCreate before any execution.
|
|
17
12
|
|
|
18
|
-
|
|
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
|
-
|
|
21
|
+
Design Doc (uses most recent if omitted): $ARGUMENTS
|
|
21
22
|
|
|
22
23
|
## Execution Flow
|
|
23
24
|
|
|
24
|
-
### 1
|
|
25
|
+
### Step 1: Prerequisite Check
|
|
25
26
|
```bash
|
|
26
27
|
# Identify Design Doc
|
|
27
28
|
ls docs/design/*.md | grep -v template | tail -1
|
|
@@ -30,15 +31,15 @@ ls docs/design/*.md | grep -v template | tail -1
|
|
|
30
31
|
git diff --name-only main...HEAD
|
|
31
32
|
```
|
|
32
33
|
|
|
33
|
-
### 2
|
|
34
|
+
### Step 2: Execute code-reviewer
|
|
34
35
|
Invoke code-reviewer using Agent tool:
|
|
35
36
|
- `subagent_type`: "code-reviewer"
|
|
36
37
|
- `description`: "Code compliance review"
|
|
37
|
-
- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report
|
|
38
|
+
- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report."
|
|
38
39
|
|
|
39
40
|
**Store output as**: `$STEP_2_OUTPUT`
|
|
40
41
|
|
|
41
|
-
### 3
|
|
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
|
|
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
|
|
88
|
+
If both pass and user selects `n`: Skip Steps 5-10, proceed to Step 11.
|
|
83
89
|
|
|
84
|
-
|
|
90
|
+
### Step 5: Load Task Template
|
|
85
91
|
|
|
86
|
-
|
|
92
|
+
Read documentation-criteria skill to obtain the task file template (references/task-template.md) for Step 6.
|
|
87
93
|
|
|
88
|
-
###
|
|
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
|
-
|
|
95
|
-
|
|
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
|
|
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
|
|
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
|
|
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.
|
|
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
|
|
116
|
-
|
|
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: $STEP_3_OUTPUT. Design Doc: [path]. Implementation files: [file list]."
|
|
120
124
|
|
|
121
|
-
### Final Report
|
|
125
|
+
### Step 11: Final Report
|
|
122
126
|
```
|
|
123
127
|
Code Compliance:
|
|
124
128
|
Initial: [X]%
|
|
@@ -33,7 +33,7 @@ git diff --name-only main...HEAD
|
|
|
33
33
|
Invoke code-reviewer using Agent tool:
|
|
34
34
|
- `subagent_type`: "code-reviewer"
|
|
35
35
|
- `description`: "Code compliance review"
|
|
36
|
-
- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report
|
|
36
|
+
- `prompt`: "Design Doc: [path]. Implementation files: [git diff file list]. Review mode: full. Validate Design Doc compliance and return structured JSON report."
|
|
37
37
|
|
|
38
38
|
**Store output as**: `$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.
|
|
88
|
+
### 5. Load Task Template
|
|
84
89
|
|
|
85
|
-
|
|
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
|
-
|
|
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
|
-
##
|
|
104
|
+
## 実装後検証(全タスク完了後)
|
|
105
105
|
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
-
|
|
110
|
-
-
|
|
111
|
-
|
|
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**:
|
|
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** —
|
|
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
|
-
|
|
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)
|
|
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
|
|
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**:
|
|
112
|
-
|
|
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**:
|
|
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
|
-
##
|
|
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
|
-
|
|
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
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
-
|
|
15
|
-
-
|
|
16
|
-
|
|
17
|
-
|
|
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
|
|
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
|
-
|
|
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]
|
|
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
|
-
|
|
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
|
|
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
|
|
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)
|
|
80
|
-
|
|
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。
|