create-ai-project 1.11.2 → 1.12.1
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 +13 -13
- package/.claude/agents-en/code-reviewer.md +8 -10
- package/.claude/agents-en/design-sync.md +6 -5
- package/.claude/agents-en/document-reviewer.md +8 -7
- package/.claude/agents-en/integration-test-reviewer.md +5 -4
- package/.claude/agents-en/prd-creator.md +7 -6
- package/.claude/agents-en/quality-fixer-frontend.md +3 -14
- package/.claude/agents-en/quality-fixer.md +9 -20
- package/.claude/agents-en/requirement-analyzer.md +8 -7
- package/.claude/agents-en/rule-advisor.md +57 -128
- package/.claude/agents-en/task-decomposer.md +4 -10
- package/.claude/agents-en/task-executor-frontend.md +4 -16
- package/.claude/agents-en/task-executor.md +5 -16
- package/.claude/agents-en/technical-designer-frontend.md +17 -15
- package/.claude/agents-en/technical-designer.md +13 -15
- package/.claude/agents-en/work-planner.md +9 -14
- package/.claude/agents-ja/acceptance-test-generator.md +9 -15
- package/.claude/agents-ja/code-reviewer.md +3 -11
- package/.claude/agents-ja/design-sync.md +2 -6
- package/.claude/agents-ja/document-reviewer.md +4 -9
- package/.claude/agents-ja/integration-test-reviewer.md +2 -5
- package/.claude/agents-ja/prd-creator.md +3 -7
- package/.claude/agents-ja/quality-fixer-frontend.md +2 -13
- package/.claude/agents-ja/quality-fixer.md +7 -18
- package/.claude/agents-ja/requirement-analyzer.md +5 -8
- package/.claude/agents-ja/rule-advisor.md +57 -128
- package/.claude/agents-ja/task-decomposer.md +4 -10
- package/.claude/agents-ja/task-executor-frontend.md +3 -15
- package/.claude/agents-ja/task-executor.md +3 -17
- package/.claude/agents-ja/technical-designer-frontend.md +17 -15
- package/.claude/agents-ja/technical-designer.md +13 -15
- package/.claude/agents-ja/work-planner.md +9 -14
- package/.claude/commands-en/build.md +2 -2
- package/.claude/commands-en/design.md +1 -1
- package/.claude/commands-en/implement.md +8 -8
- package/.claude/commands-en/plan.md +3 -3
- package/.claude/commands-en/project-inject.md +4 -4
- package/.claude/commands-en/{refine-rule.md → refine-skill.md} +47 -48
- package/.claude/commands-en/{sync-rules.md → sync-skills.md} +29 -29
- package/.claude/commands-ja/build.md +2 -2
- package/.claude/commands-ja/design.md +1 -1
- package/.claude/commands-ja/implement.md +8 -8
- package/.claude/commands-ja/plan.md +3 -3
- package/.claude/commands-ja/project-inject.md +4 -4
- package/.claude/{commands/refine-rule.md → commands-ja/refine-skill.md} +25 -25
- package/.claude/{commands/sync-rules.md → commands-ja/sync-skills.md} +28 -28
- package/{docs/rules-en/coding-standards.md → .claude/skills-en/coding-standards/SKILL.md} +21 -108
- package/{docs/rules-en/documentation-criteria.md → .claude/skills-en/documentation-criteria/SKILL.md} +40 -42
- package/{docs/adr/template-en.md → .claude/skills-en/documentation-criteria/references/adr-template.md} +1 -1
- package/{docs/design/template-en.md → .claude/skills-en/documentation-criteria/references/design-template.md} +11 -31
- package/{docs/plans/template-en.md → .claude/skills-en/documentation-criteria/references/plan-template.md} +4 -4
- package/{docs/prd/template-en.md → .claude/skills-en/documentation-criteria/references/prd-template.md} +1 -1
- package/{docs/rules-en/frontend/technical-spec.md → .claude/skills-en/frontend/technical-spec/SKILL.md} +17 -13
- package/{docs/rules-en/frontend/typescript.md → .claude/skills-en/frontend/typescript-rules/SKILL.md} +17 -12
- package/{docs/rules-en/frontend/typescript-testing.md → .claude/skills-en/frontend/typescript-testing/SKILL.md} +11 -6
- package/{docs/rules-en/architecture/implementation-approach.md → .claude/skills-en/implementation-approach/SKILL.md} +7 -2
- package/{docs/rules-en/integration-e2e-testing.md → .claude/skills-en/integration-e2e-testing/SKILL.md} +15 -18
- package/{docs/rules-en/project-context.md → .claude/skills-en/project-context/SKILL.md} +7 -3
- package/.claude/skills-en/subagents-orchestration-guide/SKILL.md +224 -0
- package/.claude/skills-en/task-analyzer/SKILL.md +131 -0
- package/{docs/rules-en/rules-index.yaml → .claude/skills-en/task-analyzer/references/skills-index.yaml} +34 -20
- package/{docs/rules-en/technical-spec.md → .claude/skills-en/technical-spec/SKILL.md} +6 -6
- package/{docs/rules-en/typescript.md → .claude/skills-en/typescript-rules/SKILL.md} +15 -10
- package/{docs/rules-en/typescript-testing.md → .claude/skills-en/typescript-testing/SKILL.md} +10 -4
- package/{docs/rules-ja/coding-standards.md → .claude/skills-ja/coding-standards/SKILL.md} +12 -99
- package/{docs/rules-ja/documentation-criteria.md → .claude/skills-ja/documentation-criteria/SKILL.md} +18 -5
- package/.claude/skills-ja/documentation-criteria/references/adr-template.md +64 -0
- package/.claude/skills-ja/documentation-criteria/references/design-template.md +261 -0
- package/{docs/plans/template-ja.md → .claude/skills-ja/documentation-criteria/references/plan-template.md} +38 -38
- package/{docs/prd/template-ja.md → .claude/skills-ja/documentation-criteria/references/prd-template.md} +33 -33
- package/{docs/rules-ja/frontend/technical-spec.md → .claude/skills-ja/frontend/technical-spec/SKILL.md} +13 -9
- package/.claude/skills-ja/frontend/typescript-rules/SKILL.md +315 -0
- package/{docs/rules-ja/frontend/typescript-testing.md → .claude/skills-ja/frontend/typescript-testing/SKILL.md} +93 -5
- package/{docs/rules/architecture/implementation-approach.md → .claude/skills-ja/implementation-approach/SKILL.md} +10 -5
- package/{docs/rules-ja/integration-e2e-testing.md → .claude/skills-ja/integration-e2e-testing/SKILL.md} +5 -8
- package/{docs/rules-ja/project-context.md → .claude/skills-ja/project-context/SKILL.md} +7 -3
- package/.claude/skills-ja/subagents-orchestration-guide/SKILL.md +212 -0
- package/.claude/skills-ja/task-analyzer/SKILL.md +131 -0
- package/{docs/rules-ja/rules-index.yaml → .claude/skills-ja/task-analyzer/references/skills-index.yaml} +34 -19
- package/{docs/rules-ja/technical-spec.md → .claude/skills-ja/technical-spec/SKILL.md} +6 -6
- package/{docs/rules-ja/typescript.md → .claude/skills-ja/typescript-rules/SKILL.md} +16 -11
- package/{docs/rules-ja/typescript-testing.md → .claude/skills-ja/typescript-testing/SKILL.md} +11 -5
- package/CLAUDE.en.md +6 -6
- package/CLAUDE.ja.md +6 -6
- package/CLAUDE.md +19 -28
- package/README.ja.md +39 -10
- package/README.md +39 -10
- package/package.json +1 -1
- package/scripts/set-language.js +35 -53
- package/scripts/setup-project.js +4 -1
- package/.claude/agents/acceptance-test-generator.md +0 -316
- package/.claude/agents/code-reviewer.md +0 -193
- package/.claude/agents/document-reviewer.md +0 -182
- package/.claude/agents/prd-creator.md +0 -186
- package/.claude/agents/quality-fixer.md +0 -295
- package/.claude/agents/requirement-analyzer.md +0 -161
- package/.claude/agents/rule-advisor.md +0 -194
- package/.claude/agents/task-decomposer.md +0 -291
- package/.claude/agents/task-executor.md +0 -270
- package/.claude/agents/technical-designer.md +0 -343
- package/.claude/agents/work-planner.md +0 -181
- package/.claude/commands/build.md +0 -78
- package/.claude/commands/design.md +0 -27
- package/.claude/commands/implement.md +0 -79
- package/.claude/commands/plan.md +0 -43
- package/.claude/commands/project-inject.md +0 -76
- package/.claude/commands/review.md +0 -78
- package/.claude/commands/task.md +0 -13
- package/.claude/commands-ja/refine-rule.md +0 -206
- package/.claude/commands-ja/sync-rules.md +0 -116
- package/.claude/settings.local.json +0 -74
- package/docs/adr/template-ja.md +0 -64
- package/docs/design/template-ja.md +0 -285
- package/docs/guides/en/sub-agents.md +0 -343
- package/docs/guides/ja/sub-agents.md +0 -343
- package/docs/guides/sub-agents.md +0 -306
- package/docs/plans/20250123-integration-test-improvement.md +0 -993
- package/docs/rules/ai-development-guide.md +0 -260
- package/docs/rules/documentation-criteria.md +0 -180
- package/docs/rules/project-context.md +0 -38
- package/docs/rules/rules-index.yaml +0 -137
- package/docs/rules/technical-spec.md +0 -47
- package/docs/rules/typescript-testing.md +0 -188
- package/docs/rules/typescript.md +0 -166
- package/docs/rules-ja/architecture/implementation-approach.md +0 -136
- package/docs/rules-ja/frontend/typescript.md +0 -131
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
---
|
|
2
|
-
description:
|
|
2
|
+
description: Implement user skill change requests with maximum precision optimization
|
|
3
3
|
---
|
|
4
4
|
|
|
5
5
|
Change request: $ARGUMENTS
|
|
6
6
|
|
|
7
|
-
**
|
|
7
|
+
**Think deeply** Extract the TRUE INTENT behind user's change request and implement with MAXIMUM PRECISION to eliminate ALL ambiguity:
|
|
8
8
|
|
|
9
9
|
## 9 Optimization Perspectives
|
|
10
10
|
1. Context efficiency vs execution accuracy - Maximum accuracy with minimal description
|
|
11
|
-
2. Deduplication - Consistency within and across
|
|
11
|
+
2. Deduplication - Consistency within and across skill files
|
|
12
12
|
3. Proper responsibility aggregation - Group related content (minimize read operations)
|
|
13
13
|
4. Clear decision criteria - Measurable standards
|
|
14
14
|
5. Transform negatives to recommendations - Recommended format (background: including NG examples)
|
|
@@ -23,13 +23,13 @@ Change request: $ARGUMENTS
|
|
|
23
23
|
|
|
24
24
|
Question template when unspecified:
|
|
25
25
|
```
|
|
26
|
-
1. Which
|
|
27
|
-
e.g.: typescript
|
|
26
|
+
1. Which skill to modify?
|
|
27
|
+
e.g.: typescript-rules / coding-standards / documentation-criteria
|
|
28
28
|
|
|
29
29
|
2. Select change type:
|
|
30
|
-
a) Add new
|
|
31
|
-
b) Modify existing
|
|
32
|
-
c) Delete
|
|
30
|
+
a) Add new criteria (add new standards)
|
|
31
|
+
b) Modify existing criteria (clarify ambiguous descriptions)
|
|
32
|
+
c) Delete criteria (remove obsolete standards)
|
|
33
33
|
|
|
34
34
|
3. Specific changes:
|
|
35
35
|
e.g.: "Add rule prohibiting 'any' type usage"
|
|
@@ -43,14 +43,14 @@ Target file identification and current state check:
|
|
|
43
43
|
|
|
44
44
|
```
|
|
45
45
|
# Tool selection criteria (measurable decisions)
|
|
46
|
-
if
|
|
47
|
-
Read:
|
|
48
|
-
else if partial
|
|
49
|
-
Glob:
|
|
46
|
+
if skill name is explicitly provided:
|
|
47
|
+
Read: .claude/skills/{skill-name}/SKILL.md direct read
|
|
48
|
+
else if partial skill name known:
|
|
49
|
+
Glob: .claude/skills/*{keyword}*/SKILL.md search
|
|
50
50
|
Read: Check identified file's current state
|
|
51
51
|
else:
|
|
52
|
-
Glob:
|
|
53
|
-
Confirm target
|
|
52
|
+
Glob: .claude/skills/*/SKILL.md for full scan
|
|
53
|
+
Confirm target skill selection with user
|
|
54
54
|
```
|
|
55
55
|
|
|
56
56
|
Design template:
|
|
@@ -81,26 +81,25 @@ Proceed with this design? (y/n)
|
|
|
81
81
|
### 3. Three-Pass Review Process
|
|
82
82
|
|
|
83
83
|
#### Pass 1: Add for Maximum Accuracy【Addition-Only Mode】
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
- CONVERT all ambiguous expressions → measurable criteria
|
|
84
|
+
Declaration: "Pass 1: Addition mode execution. Deletions are prohibited."
|
|
85
|
+
- Convert all ambiguous expressions → measurable criteria
|
|
87
86
|
Example: "large" → "100+ lines" "5+ files"
|
|
88
|
-
-
|
|
87
|
+
- Make all implicit prerequisites explicit
|
|
89
88
|
Example: "In TypeScript environment" "Within async functions"
|
|
90
|
-
-
|
|
89
|
+
- Define all exceptions and edge cases
|
|
91
90
|
Example: "When null/undefined" "For empty arrays"
|
|
92
|
-
|
|
91
|
+
Report: Count added items (minimum 5 items)
|
|
93
92
|
|
|
94
93
|
#### Pass 2: Critical Modification to Reduce Redundancy【Actual Modification Mode】
|
|
95
|
-
|
|
94
|
+
Declaration: "Pass 2: Critical modification mode execution. Actually delete and consolidate redundant parts."
|
|
96
95
|
|
|
97
|
-
|
|
98
|
-
1.
|
|
99
|
-
2.
|
|
100
|
-
- Duplicate concepts →
|
|
101
|
-
- Overly detailed explanations →
|
|
102
|
-
- Overlap with other
|
|
103
|
-
3.
|
|
96
|
+
Modification work:
|
|
97
|
+
1. Critically review all Pass 1 additions
|
|
98
|
+
2. Apply modifications using these criteria:
|
|
99
|
+
- Duplicate concepts → Consolidate
|
|
100
|
+
- Overly detailed explanations → Simplify
|
|
101
|
+
- Overlap with other skills → Replace with references
|
|
102
|
+
3. Record complete before/after diff (deletion reasons required)
|
|
104
103
|
|
|
105
104
|
Report format:
|
|
106
105
|
```
|
|
@@ -112,20 +111,20 @@ Deleted/consolidated content:
|
|
|
112
111
|
```
|
|
113
112
|
|
|
114
113
|
#### Pass 3: Accuracy Assurance via Diff Evaluation【Restoration Decision Mode】
|
|
115
|
-
|
|
114
|
+
Declaration: "Pass 3: Diff evaluation mode execution. Review all Pass 2 modifications and restore if accuracy compromised."
|
|
116
115
|
|
|
117
|
-
|
|
118
|
-
1.
|
|
119
|
-
- Does deletion create implementation ambiguity?
|
|
120
|
-
- Are
|
|
116
|
+
Verification work:
|
|
117
|
+
1. Evaluate each Pass 2 modification:
|
|
118
|
+
- Does deletion create implementation ambiguity? → Restore
|
|
119
|
+
- Are edge cases still covered? → Restore if missing
|
|
121
120
|
2. Action mapping:
|
|
122
|
-
- Deletions with accuracy risks →
|
|
123
|
-
- Valid deletions →
|
|
121
|
+
- Deletions with accuracy risks → Restore
|
|
122
|
+
- Valid deletions → Keep
|
|
124
123
|
|
|
125
|
-
|
|
126
|
-
"Are necessary and sufficient conditions present for accurate implementation of user requirements?
|
|
124
|
+
Final confirmation (required answer):
|
|
125
|
+
"Are necessary and sufficient conditions present for accurate implementation of user requirements?"
|
|
127
126
|
|
|
128
|
-
|
|
127
|
+
Report: Number of restored items and final reduction percentage
|
|
129
128
|
|
|
130
129
|
### 4. Get Approval
|
|
131
130
|
|
|
@@ -135,13 +134,13 @@ Present before/after comparison for user approval.
|
|
|
135
134
|
|
|
136
135
|
1. Apply changes with appropriate tool (after user approval)
|
|
137
136
|
2. Final verification with git diff
|
|
138
|
-
3. Suggest `/sync-
|
|
137
|
+
3. Suggest `/sync-skills` execution
|
|
139
138
|
|
|
140
139
|
## Decision Criteria Checklist
|
|
141
140
|
- [ ] Expressible in "if-then" format ("if X then Y")
|
|
142
141
|
- [ ] Measurable by numbers/counts/states (eliminate subjective judgment)
|
|
143
142
|
- [ ] Related content aggregated in single file (minimize read operations)
|
|
144
|
-
- [ ] Relationships with other
|
|
143
|
+
- [ ] Relationships with other skills specified (dependencies/references/delegation)
|
|
145
144
|
- [ ] NG examples included as background information
|
|
146
145
|
- [ ] All prerequisites explicitly stated
|
|
147
146
|
|
|
@@ -153,7 +152,7 @@ Present before/after comparison for user approval.
|
|
|
153
152
|
| Implicit prerequisites | "implement error handling" | "TypeScript async function error handling" |
|
|
154
153
|
| Unclear order | "consider: A, B, C" | "Priority: 1.A (required), 2.B (recommended), 3.C (optional)" |
|
|
155
154
|
| Redundant explanation | "ensure type safety by defining types, checking types, and preventing type errors" | "type safety (define・check・prevent errors)" |
|
|
156
|
-
| Ambiguous scope | "write tests" | "write unit tests (see
|
|
155
|
+
| Ambiguous scope | "write tests" | "write unit tests (see typescript-testing skill for E2E tests)" |
|
|
157
156
|
|
|
158
157
|
## Output Example
|
|
159
158
|
|
|
@@ -161,13 +160,13 @@ Present before/after comparison for user approval.
|
|
|
161
160
|
=== Change Implementation Complete ===
|
|
162
161
|
|
|
163
162
|
【User Request】
|
|
164
|
-
"Strengthen TypeScript error handling
|
|
163
|
+
"Strengthen TypeScript error handling criteria"
|
|
165
164
|
|
|
166
165
|
【Changes】
|
|
167
|
-
Target:
|
|
166
|
+
Target: .claude/skills/typescript-rules/SKILL.md
|
|
168
167
|
Section: ## Error Handling
|
|
169
168
|
|
|
170
|
-
Before:
|
|
169
|
+
Before:
|
|
171
170
|
"Handle errors appropriately"
|
|
172
171
|
|
|
173
172
|
After (3-pass review complete):
|
|
@@ -189,7 +188,7 @@ After (3-pass review complete):
|
|
|
189
188
|
- Ambiguous expressions: 1 → 0
|
|
190
189
|
- NG examples included as background
|
|
191
190
|
|
|
192
|
-
Run /sync-
|
|
191
|
+
Run /sync-skills for metadata synchronization.
|
|
193
192
|
```
|
|
194
193
|
|
|
195
194
|
## Execution Order
|
|
@@ -199,10 +198,10 @@ Run /sync-rules for metadata synchronization.
|
|
|
199
198
|
4. 3-pass review process
|
|
200
199
|
5. User approval
|
|
201
200
|
6. Apply changes
|
|
202
|
-
7. Suggest sync-
|
|
201
|
+
7. Suggest sync-skills
|
|
203
202
|
|
|
204
203
|
**Scope**: Understanding user change requests and implementing with maximum accuracy
|
|
205
204
|
|
|
206
205
|
## Error Handling
|
|
207
|
-
- **
|
|
208
|
-
- **Large change detected**: Suggest phased implementation for 50%+ changes
|
|
206
|
+
- **Skill not found**: Display available skill list
|
|
207
|
+
- **Large change detected**: Suggest phased implementation for 50%+ changes
|
|
@@ -1,28 +1,28 @@
|
|
|
1
1
|
---
|
|
2
|
-
description: Synchronize
|
|
2
|
+
description: Synchronize skill metadata and optimize rule-advisor precision after skill edits
|
|
3
3
|
---
|
|
4
4
|
|
|
5
|
-
**Command Context**: Post-editing maintenance workflow for
|
|
5
|
+
**Command Context**: Post-editing maintenance workflow for skill files
|
|
6
6
|
|
|
7
7
|
**Think deeply** Maximize rule-advisor execution precision through systematic synchronization:
|
|
8
8
|
|
|
9
9
|
## Execution Flow
|
|
10
10
|
|
|
11
|
-
### 1. Scan
|
|
11
|
+
### 1. Scan Skill Files
|
|
12
12
|
```bash
|
|
13
|
-
# Runtime
|
|
14
|
-
|
|
15
|
-
INDEX_FILE="
|
|
13
|
+
# Runtime skills directory
|
|
14
|
+
SKILLS_DIR=".claude/skills"
|
|
15
|
+
INDEX_FILE=".claude/skills/task-analyzer/references/skills-index.yaml"
|
|
16
16
|
|
|
17
|
-
# Analyze all
|
|
18
|
-
find "${
|
|
17
|
+
# Analyze all skill files
|
|
18
|
+
find "${SKILLS_DIR}" -name "SKILL.md" -type f | sort
|
|
19
19
|
```
|
|
20
20
|
|
|
21
21
|
### 2. Synchronize and Optimize Metadata
|
|
22
22
|
|
|
23
23
|
#### Automatic Section Synchronization
|
|
24
|
-
- Extract `## ` sections from each
|
|
25
|
-
- Update sections in
|
|
24
|
+
- Extract `## ` sections from each SKILL.md
|
|
25
|
+
- Update sections in skills-index.yaml automatically
|
|
26
26
|
|
|
27
27
|
#### Tag Optimization
|
|
28
28
|
- Analyze file content for relevant keywords
|
|
@@ -39,23 +39,23 @@ find "${RULES_DIR}" -name "*.md" -type f | sort
|
|
|
39
39
|
|
|
40
40
|
### 3. Rule-Advisor Precision Optimization
|
|
41
41
|
|
|
42
|
-
Enhance metadata quality to enable accurate
|
|
42
|
+
Enhance metadata quality to enable accurate skill selection by rule-advisor:
|
|
43
43
|
|
|
44
44
|
```
|
|
45
|
-
===
|
|
46
|
-
Target:
|
|
45
|
+
=== Skill Metadata Synchronization ===
|
|
46
|
+
Target: .claude/skills
|
|
47
47
|
|
|
48
48
|
Updates executed:
|
|
49
49
|
✅ Sections synchronized
|
|
50
|
-
- typescript-testing
|
|
51
|
-
-
|
|
50
|
+
- typescript-testing: 2 sections added
|
|
51
|
+
- coding-standards: 1 section updated
|
|
52
52
|
|
|
53
53
|
✅ Tags optimized
|
|
54
|
-
- typescript
|
|
55
|
-
- technical-spec
|
|
54
|
+
- typescript-rules: Suggest adding [functional-programming]
|
|
55
|
+
- technical-spec: Suggest removing [deprecated]
|
|
56
56
|
|
|
57
57
|
✅ Typical-use improved
|
|
58
|
-
- 3
|
|
58
|
+
- 3 skills updated with more specific descriptions
|
|
59
59
|
|
|
60
60
|
Final result: Rule-advisor precision optimization complete
|
|
61
61
|
```
|
|
@@ -64,7 +64,7 @@ Final result: Rule-advisor precision optimization complete
|
|
|
64
64
|
|
|
65
65
|
**Essential Purpose**:
|
|
66
66
|
- Not mere consistency maintenance, but rule-advisor selection accuracy enhancement
|
|
67
|
-
- Metadata optimization as the final step of
|
|
67
|
+
- Metadata optimization as the final step of skill editing workflow
|
|
68
68
|
|
|
69
69
|
**Quality Criteria**:
|
|
70
70
|
- Sections must achieve 100% synchronization
|
|
@@ -76,30 +76,30 @@ Final result: Rule-advisor precision optimization complete
|
|
|
76
76
|
|
|
77
77
|
**EVALUATION SEQUENCE**:
|
|
78
78
|
- IF sections achieve 100% synchronization → OUTPUT "Synchronization verified. No updates required." THEN TERMINATE
|
|
79
|
-
- IF content-to-tag mapping shows zero mismatches → DETERMINE no_changes_needed = true THEN TERMINATE
|
|
79
|
+
- IF content-to-tag mapping shows zero mismatches → DETERMINE no_changes_needed = true THEN TERMINATE
|
|
80
80
|
- IF AND ONLY IF measurable improvements exist → GENERATE specific modification proposals WITH exact before/after values
|
|
81
81
|
|
|
82
82
|
**NOTE**: You MUST NOT force changes. When no improvements are detected, you SHALL report "No modifications necessary" and STOP execution.
|
|
83
83
|
|
|
84
84
|
## Execution Timing
|
|
85
85
|
|
|
86
|
-
- After
|
|
87
|
-
- When adding new
|
|
88
|
-
- After major
|
|
86
|
+
- After skill file edits (mandatory)
|
|
87
|
+
- When adding new skill files
|
|
88
|
+
- After major skill revisions
|
|
89
89
|
- When rule-advisor selection accuracy appears degraded
|
|
90
90
|
|
|
91
91
|
## Example Output
|
|
92
92
|
|
|
93
93
|
```
|
|
94
|
-
===
|
|
95
|
-
Target:
|
|
94
|
+
=== Skill Metadata Synchronization Started ===
|
|
95
|
+
Target: .claude/skills (13 skills)
|
|
96
96
|
|
|
97
|
-
[1/
|
|
97
|
+
[1/13] typescript-rules
|
|
98
98
|
✅ sections: 7 synchronized
|
|
99
99
|
💡 tags proposed: +[functional-programming, dependency-injection]
|
|
100
100
|
💡 typical-use: "General TypeScript implementation" → "Type-safe implementation with modern TypeScript features"
|
|
101
101
|
|
|
102
|
-
[2/
|
|
102
|
+
[2/13] typescript-testing
|
|
103
103
|
✅ sections: 2 added (Test Granularity Principles, Mock Type Safety Enforcement)
|
|
104
104
|
✅ tags: No changes needed
|
|
105
105
|
✅ typical-use: Maintained
|
|
@@ -107,10 +107,10 @@ Target: docs/rules (9 files)
|
|
|
107
107
|
...
|
|
108
108
|
|
|
109
109
|
=== Synchronization Complete ===
|
|
110
|
-
Updated: 3
|
|
110
|
+
Updated: 3 skills
|
|
111
111
|
Proposals: 5 items (approval required)
|
|
112
112
|
|
|
113
113
|
Rule-advisor precision improvement: Estimated 15% enhancement
|
|
114
114
|
```
|
|
115
115
|
|
|
116
|
-
**Scope**: Post-edit
|
|
116
|
+
**Scope**: Post-edit skill metadata synchronization and rule-advisor precision optimization.
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
description: 分解済みタスクを自律実行モードで実装
|
|
3
3
|
---
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
subagents-orchestration-guideスキルの指針に従い、**オーケストレーター**として振る舞います。
|
|
6
6
|
|
|
7
7
|
作業計画書: $ARGUMENTS
|
|
8
8
|
|
|
@@ -57,7 +57,7 @@ description: 分解済みタスクを自律実行モードで実装
|
|
|
57
57
|
❌ **避ける**: タスク未生成のまま実装を開始
|
|
58
58
|
|
|
59
59
|
## 🧠 タスク実行フロー
|
|
60
|
-
|
|
60
|
+
subagents-orchestration-guideスキルの「自律実行中のタスク管理」に従い、TodoWriteで4ステップを管理。最初に「スキル制約の確認」、最後に「スキル忠実度の検証」を必ず含める:
|
|
61
61
|
1. task-executor実行
|
|
62
62
|
2. エスカレーション判定・フォローアップ
|
|
63
63
|
3. quality-fixer実行
|
|
@@ -4,7 +4,7 @@ description: オーケストレーターとして要件分析から実装まで
|
|
|
4
4
|
|
|
5
5
|
**コマンドコンテキスト**: 実装の完全サイクル管理(要件分析→設計→計画→実装→品質保証)
|
|
6
6
|
|
|
7
|
-
|
|
7
|
+
subagents-orchestration-guideスキルの指針に従い、オーケストレーターとして振る舞います。
|
|
8
8
|
|
|
9
9
|
## 実行判断フロー
|
|
10
10
|
|
|
@@ -16,7 +16,7 @@ description: オーケストレーターとして要件分析から実装まで
|
|
|
16
16
|
| 状況パターン | 判定基準 | 次のアクション |
|
|
17
17
|
|------------|---------|-------------|
|
|
18
18
|
| 新規要件 | 既存作業なし、新しい機能/修正依頼 | requirement-analyzerから開始 |
|
|
19
|
-
| フロー継続 | 既存ドキュメント/タスクあり、継続指示 |
|
|
19
|
+
| フロー継続 | 既存ドキュメント/タスクあり、継続指示 | subagents-orchestration-guideスキルのフローで次のステップを特定 |
|
|
20
20
|
| 品質エラー | エラー検出、テスト失敗、ビルドエラー | quality-fixer実行 |
|
|
21
21
|
| 不明瞭 | 意図が曖昧、複数の解釈が可能 | ユーザーに確認 |
|
|
22
22
|
|
|
@@ -24,26 +24,26 @@ description: オーケストレーターとして要件分析から実装まで
|
|
|
24
24
|
フロー継続の場合、以下を確認:
|
|
25
25
|
- 最新の成果物(PRD/ADR/Design Doc/作業計画書/タスク)
|
|
26
26
|
- 現在のフェーズ位置(要件/設計/計画/実装/品質保証)
|
|
27
|
-
-
|
|
27
|
+
- subagents-orchestration-guideスキルの該当フローで次のステップを特定
|
|
28
28
|
|
|
29
29
|
### 3. 規模判定後:TodoWriteにフロー全ステップを登録(必須)
|
|
30
30
|
|
|
31
|
-
規模判定完了後、**
|
|
31
|
+
規模判定完了後、**subagents-orchestration-guideスキルの該当フロー全ステップをTodoWriteに登録**。最初に「スキル制約の確認」、最後に「スキル忠実度の検証」を必ず含める。登録後、TodoWriteを参照してフローを進める。
|
|
32
32
|
|
|
33
33
|
### 4. 次のアクション実行
|
|
34
34
|
|
|
35
35
|
**TodoWriteの次のpendingタスクを実行**。
|
|
36
36
|
|
|
37
|
-
## 📋
|
|
37
|
+
## 📋 subagents-orchestration-guideスキル準拠の実行
|
|
38
38
|
|
|
39
39
|
**実行前チェック(必須)**:
|
|
40
|
-
- [ ]
|
|
40
|
+
- [ ] subagents-orchestration-guideスキルの該当フローを確認した
|
|
41
41
|
- [ ] 現在の進捗位置を特定した
|
|
42
42
|
- [ ] 次のステップを明確にした
|
|
43
43
|
- [ ] 停止ポイントを認識した
|
|
44
44
|
- [ ] タスク実行後の4ステップサイクル(task-executor → エスカレーション判定・フォローアップ → quality-fixer → commit)を理解した
|
|
45
45
|
|
|
46
|
-
**フロー厳守**:
|
|
46
|
+
**フロー厳守**: subagents-orchestration-guideスキルの「自律実行中のタスク管理」に従い、TodoWriteで4ステップを管理する
|
|
47
47
|
|
|
48
48
|
## 🚨 サブエージェント呼び出し時の制約
|
|
49
49
|
|
|
@@ -55,7 +55,7 @@ description: オーケストレーターとして要件分析から実装まで
|
|
|
55
55
|
## 🎯 オーケストレーターとしての必須責務
|
|
56
56
|
|
|
57
57
|
### タスク実行フロー
|
|
58
|
-
|
|
58
|
+
subagents-orchestration-guideスキルの「自律実行中のタスク管理」に従い、TodoWriteで以下の4ステップを管理:
|
|
59
59
|
1. task-executor実行
|
|
60
60
|
2. エスカレーション判定・フォローアップ
|
|
61
61
|
3. quality-fixer実行
|
|
@@ -4,7 +4,7 @@ description: 設計書から作業計画書を作成し計画承認を取得
|
|
|
4
4
|
|
|
5
5
|
**コマンドコンテキスト**: このコマンドは計画フェーズ専用です。
|
|
6
6
|
|
|
7
|
-
|
|
7
|
+
subagents-orchestration-guideスキルの指針に従い、以下のプロセスで作業計画書を作成します:
|
|
8
8
|
|
|
9
9
|
## 実行プロセス
|
|
10
10
|
|
|
@@ -16,11 +16,11 @@ description: 設計書から作業計画書を作成し計画承認を取得
|
|
|
16
16
|
2. **E2Eテストスケルトンの生成確認**
|
|
17
17
|
- E2Eテストスケルトンを先に生成するかユーザーに確認
|
|
18
18
|
- 生成を希望する場合: acceptance-test-generator でテストスケルトンを生成
|
|
19
|
-
- 生成結果を
|
|
19
|
+
- 生成結果を subagents-orchestration-guideスキル の連携仕様に従って次工程に引き継ぐ
|
|
20
20
|
|
|
21
21
|
3. **作業計画書の作成**
|
|
22
22
|
- work-planner で作業計画書を作成
|
|
23
|
-
- 前工程の成果物を
|
|
23
|
+
- 前工程の成果物を subagents-orchestration-guideスキル の連携仕様に従って活用
|
|
24
24
|
- ユーザーと対話して計画を完成させ、計画内容の承認を得る
|
|
25
25
|
|
|
26
26
|
**Think deeply** 選択された設計書から作業計画書を作成し、実装の具体的なステップとリスクを明確にします。
|
|
@@ -7,7 +7,7 @@ description: プロジェクト固有のコンテキストをproject-context.md
|
|
|
7
7
|
## 実行プロセス
|
|
8
8
|
|
|
9
9
|
### 1. 現状確認
|
|
10
|
-
! ls -la
|
|
10
|
+
! ls -la .claude/skills/project-context/SKILL.md
|
|
11
11
|
! cat package.json | grep -E '"name":|"description":'
|
|
12
12
|
|
|
13
13
|
### 2. プロジェクトコンテキストの収集
|
|
@@ -50,7 +50,7 @@ description: プロジェクト固有のコンテキストをproject-context.md
|
|
|
50
50
|
### 責務の境界
|
|
51
51
|
project-context.mdの単一責務は「プロジェクト固有の文脈情報」のみ:
|
|
52
52
|
- ✅ 含める: プロジェクトの目的、ターゲット、ビジネス制約
|
|
53
|
-
- ❌ 含めない: 技術スタック(→technical-spec
|
|
53
|
+
- ❌ 含めない: 技術スタック(→technical-specスキル)、実装原則(→typescript-rulesスキル)、アーキテクチャ(→technical-specスキル)
|
|
54
54
|
|
|
55
55
|
### 構造化
|
|
56
56
|
```markdown
|
|
@@ -70,7 +70,7 @@ project-context.mdの単一責務は「プロジェクト固有の文脈情報
|
|
|
70
70
|
2. [検証可能な要件]
|
|
71
71
|
```
|
|
72
72
|
|
|
73
|
-
### 4.
|
|
73
|
+
### 4. skills-index.yaml更新
|
|
74
74
|
project-contextセクションのtypical-useをプロジェクトに合わせて更新。
|
|
75
75
|
|
|
76
|
-
**スコープ**: project-context
|
|
76
|
+
**スコープ**: project-contextスキルの更新のみ。技術選択は他のスキルの責務。
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
description:
|
|
2
|
+
description: ユーザーのスキル変更要求を精度最大化して実装
|
|
3
3
|
---
|
|
4
4
|
|
|
5
5
|
変更要求: $ARGUMENTS
|
|
@@ -8,7 +8,7 @@ description: ユーザーのルール変更要求を精度最大化して実装
|
|
|
8
8
|
|
|
9
9
|
## 適用する9つの観点
|
|
10
10
|
1. コンテキスト圧迫 vs 実行精度 - 最小記述で最大精度
|
|
11
|
-
2. 重複排除 -
|
|
11
|
+
2. 重複排除 - スキルファイル内・スキルファイル間の一貫性
|
|
12
12
|
3. 責務の適切な集約 - 関連内容は1ファイルにまとめる(読み込み回数最小化)
|
|
13
13
|
4. 判断基準明確化 - 測定可能な基準
|
|
14
14
|
5. NG→推奨変換 - 推奨形式(背景:NG例を含む)
|
|
@@ -23,16 +23,16 @@ description: ユーザーのルール変更要求を精度最大化して実装
|
|
|
23
23
|
|
|
24
24
|
未指定時の質問テンプレート:
|
|
25
25
|
```
|
|
26
|
-
1.
|
|
27
|
-
例: typescript
|
|
26
|
+
1. どのスキルを変更しますか?
|
|
27
|
+
例: typescript-rules / coding-standards / documentation-criteria
|
|
28
28
|
|
|
29
29
|
2. 変更種別を選択:
|
|
30
|
-
a)
|
|
31
|
-
b)
|
|
32
|
-
c)
|
|
30
|
+
a) 新基準追加(新しい基準を追加)
|
|
31
|
+
b) 既存基準修正(曖昧な記述を明確化)
|
|
32
|
+
c) 基準削除(不要になった基準を削除)
|
|
33
33
|
|
|
34
34
|
3. 具体的な変更内容:
|
|
35
|
-
例:「any
|
|
35
|
+
例:「any型の使用を禁止する基準を追加」
|
|
36
36
|
例:「エラーハンドリングの基準を明確化」
|
|
37
37
|
[ユーザー入力]
|
|
38
38
|
```
|
|
@@ -43,14 +43,14 @@ description: ユーザーのルール変更要求を精度最大化して実装
|
|
|
43
43
|
|
|
44
44
|
```
|
|
45
45
|
# ツール選択基準(測定可能な判断)
|
|
46
|
-
if
|
|
47
|
-
Read:
|
|
48
|
-
else if
|
|
49
|
-
Glob:
|
|
46
|
+
if スキル名が明示されている:
|
|
47
|
+
Read: .claude/skills/{スキル名}/SKILL.md を直接読み込み
|
|
48
|
+
else if スキル名の一部のみ判明:
|
|
49
|
+
Glob: .claude/skills/*{キーワード}*/SKILL.md で探索
|
|
50
50
|
Read: 特定したファイルの現状確認
|
|
51
51
|
else:
|
|
52
|
-
Glob:
|
|
53
|
-
|
|
52
|
+
Glob: .claude/skills/*/SKILL.md で全件確認
|
|
53
|
+
ユーザーに対象スキル選択を確認
|
|
54
54
|
```
|
|
55
55
|
|
|
56
56
|
変更設計テンプレート:
|
|
@@ -98,7 +98,7 @@ else:
|
|
|
98
98
|
2. 以下の観点で実際に修正を実施:
|
|
99
99
|
- 同一概念の重複 → 統合
|
|
100
100
|
- 過度に詳細な説明 → 簡潔化
|
|
101
|
-
-
|
|
101
|
+
- 他スキルとの重複 → 参照に置換
|
|
102
102
|
3. 修正前後の差分を記録(削除理由も明記)
|
|
103
103
|
|
|
104
104
|
報告フォーマット:
|
|
@@ -133,13 +133,13 @@ else:
|
|
|
133
133
|
|
|
134
134
|
1. 適切なツールで変更適用(ユーザー承認後)
|
|
135
135
|
2. git diffで変更内容を最終確認
|
|
136
|
-
3. `/sync-
|
|
136
|
+
3. `/sync-skills` 実行提案
|
|
137
137
|
|
|
138
138
|
## 判断基準チェックリスト
|
|
139
139
|
- [ ] 「if-then」形式で表現可能(「~の場合は~する」)
|
|
140
140
|
- [ ] 数値・個数・状態で判定可能(主観的判断を排除)
|
|
141
141
|
- [ ] 関連内容は1ファイルに集約(読み込み回数最小化)
|
|
142
|
-
- [ ]
|
|
142
|
+
- [ ] 他スキルとの関係明記(依存・参照・委譲)
|
|
143
143
|
- [ ] NG例を背景情報として含む
|
|
144
144
|
- [ ] 前提条件が全て明示されている
|
|
145
145
|
|
|
@@ -151,7 +151,7 @@ else:
|
|
|
151
151
|
| 暗黙前提 | 「エラーハンドリングを実装」 | 「TypeScript環境でasync関数のエラーハンドリング実装」 |
|
|
152
152
|
| 順序不明確 | 「以下を考慮:A、B、C」 | 「優先順:1.A(必須)、2.B(推奨)、3.C(任意)」 |
|
|
153
153
|
| 冗長説明 | 「型安全性を確保するため、型を定義し、型チェックを行い、型エラーを防ぐ」 | 「型安全性の確保(定義・チェック・エラー防止)」 |
|
|
154
|
-
| スコープ曖昧 | 「テストを書く」 | 「単体テストを書く(E2Eテストは
|
|
154
|
+
| スコープ曖昧 | 「テストを書く」 | 「単体テストを書く(E2Eテストはtypescript-testingスキル参照)」 |
|
|
155
155
|
|
|
156
156
|
## 出力例
|
|
157
157
|
|
|
@@ -159,13 +159,13 @@ else:
|
|
|
159
159
|
=== 変更実装完了 ===
|
|
160
160
|
|
|
161
161
|
【ユーザー要求】
|
|
162
|
-
「TypeScript
|
|
162
|
+
「TypeScriptのエラーハンドリング基準を厳格化したい」
|
|
163
163
|
|
|
164
164
|
【変更内容】
|
|
165
|
-
対象:
|
|
165
|
+
対象: .claude/skills/typescript-rules/SKILL.md
|
|
166
166
|
セクション: ## エラーハンドリング
|
|
167
167
|
|
|
168
|
-
変更前:
|
|
168
|
+
変更前:
|
|
169
169
|
「エラーは適切に処理する」
|
|
170
170
|
|
|
171
171
|
変更後(3回見直しプロセス完了):
|
|
@@ -187,7 +187,7 @@ else:
|
|
|
187
187
|
- 曖昧表現: 1箇所 → 0箇所
|
|
188
188
|
- NG例を背景情報として含む
|
|
189
189
|
|
|
190
|
-
メタデータ同期のため /sync-
|
|
190
|
+
メタデータ同期のため /sync-skills を実行してください。
|
|
191
191
|
```
|
|
192
192
|
|
|
193
193
|
## 実行順序
|
|
@@ -197,10 +197,10 @@ else:
|
|
|
197
197
|
4. 3回見直しプロセス
|
|
198
198
|
5. ユーザー承認
|
|
199
199
|
6. 変更適用
|
|
200
|
-
7. sync-
|
|
200
|
+
7. sync-skills提案
|
|
201
201
|
|
|
202
202
|
**スコープ**: ユーザー変更要求の理解と精度最大化実装
|
|
203
203
|
|
|
204
204
|
## エラーハンドリング
|
|
205
|
-
-
|
|
206
|
-
- **大規模変更検出**: 変更量50%以上の場合、段階的実施を提案
|
|
205
|
+
- **スキル未発見**: 利用可能なスキル一覧を表示
|
|
206
|
+
- **大規模変更検出**: 変更量50%以上の場合、段階的実施を提案
|