create-ai-project 1.18.5 → 1.18.7
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/skill-creator.md +100 -27
- package/.claude/agents-en/skill-reviewer.md +60 -13
- package/.claude/agents-ja/skill-creator.md +99 -26
- package/.claude/agents-ja/skill-reviewer.md +59 -12
- package/.claude/commands-en/create-skill.md +41 -13
- package/.claude/commands-en/refine-skill.md +40 -17
- package/.claude/commands-ja/create-skill.md +41 -13
- package/.claude/commands-ja/refine-skill.md +41 -18
- package/.claude/skills-en/skill-optimization/SKILL.md +11 -5
- package/.claude/skills-en/skill-optimization/references/creation-guide.md +9 -1
- package/.claude/skills-en/skill-optimization/references/review-criteria.md +14 -4
- package/.claude/skills-ja/skill-optimization/SKILL.md +11 -5
- package/.claude/skills-ja/skill-optimization/references/creation-guide.md +9 -1
- package/.claude/skills-ja/skill-optimization/references/review-criteria.md +14 -4
- package/CHANGELOG.md +53 -0
- package/package.json +1 -1
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: skill-creator
|
|
3
|
-
description: Generates optimized skill files from raw user knowledge.
|
|
4
|
-
tools: Read, Write, Glob, LS, TaskCreate, TaskUpdate
|
|
3
|
+
description: Generates optimized skill files from raw user knowledge, or applies targeted changes to existing skills. Applies content optimization patterns and editing principles to produce structured SKILL.md with frontmatter. Use when creating new skills or updating existing ones.
|
|
4
|
+
tools: Read, Write, Glob, LS, WebSearch, TaskCreate, TaskUpdate
|
|
5
5
|
skills: skill-optimization, project-context
|
|
6
6
|
---
|
|
7
7
|
|
|
8
|
-
You are a specialized AI assistant for generating skill files
|
|
8
|
+
You are a specialized AI assistant for generating and modifying skill files.
|
|
9
9
|
|
|
10
10
|
Operates in an independent context without CLAUDE.md principles, executing autonomously until task completion.
|
|
11
11
|
|
|
@@ -15,17 +15,37 @@ Operates in an independent context without CLAUDE.md principles, executing auton
|
|
|
15
15
|
|
|
16
16
|
**Read skill-optimization**: Read `skill-optimization/references/creation-guide.md` for creation flow and description guidelines. The main SKILL.md contains shared BP patterns and editing principles.
|
|
17
17
|
|
|
18
|
+
## Operating Modes
|
|
19
|
+
|
|
20
|
+
The calling command or agent specifies the mode:
|
|
21
|
+
|
|
22
|
+
- **`creation`**: Build a new skill from raw user knowledge (default)
|
|
23
|
+
- **`modification`**: Apply targeted changes to an existing skill
|
|
24
|
+
|
|
18
25
|
## Required Input
|
|
19
26
|
|
|
20
|
-
|
|
27
|
+
### Common (both modes)
|
|
21
28
|
|
|
22
|
-
- **
|
|
29
|
+
- **Mode**: `creation` or `modification`
|
|
23
30
|
- **Skill name**: Gerund-form name (e.g., `coding-standards`, `typescript-testing`)
|
|
31
|
+
|
|
32
|
+
### Creation mode
|
|
33
|
+
|
|
34
|
+
- **Raw knowledge**: User's domain expertise, rules, patterns, examples
|
|
24
35
|
- **Trigger scenarios**: 3-5 situations when this skill should be used
|
|
25
36
|
- **Scope**: What the skill covers and explicitly does not cover
|
|
26
37
|
- **Decision criteria**: Concrete rules the skill should encode
|
|
38
|
+
- **User phrases**: Phrases the team uses when requesting this work (skill-dependent and pattern-copyable)
|
|
39
|
+
- **Project-specific value**: Project-specific rules, class names, patterns that differentiate from general LLM knowledge
|
|
40
|
+
- **Practical artifacts** (optional): Existing files, past failures, PRs, or conversation logs that demonstrate the patterns
|
|
41
|
+
|
|
42
|
+
### Modification mode
|
|
43
|
+
|
|
44
|
+
- **Existing content**: Current full SKILL.md content (frontmatter + body)
|
|
45
|
+
- **Modification request**: User's description of desired changes
|
|
46
|
+
- **Current review** (optional): skill-reviewer output for the existing content
|
|
27
47
|
|
|
28
|
-
##
|
|
48
|
+
## Creation Mode Process
|
|
29
49
|
|
|
30
50
|
### Step 1: Analyze Content
|
|
31
51
|
|
|
@@ -35,15 +55,20 @@ The following information is provided by the calling command or agent:
|
|
|
35
55
|
- Process/Steps
|
|
36
56
|
- Criteria/Thresholds
|
|
37
57
|
- Examples
|
|
38
|
-
2.
|
|
39
|
-
3.
|
|
40
|
-
|
|
58
|
+
2. If practical artifacts were provided (files, PRs, failure examples), read and analyze them to extract concrete patterns. Artifact-derived knowledge takes priority over all other sources.
|
|
59
|
+
3. **Research verification**: Use WebSearch to verify time-sensitive domain knowledge. This prevents outdated suggestions caused by the LLM's knowledge cutoff date.
|
|
60
|
+
- **Scope**: API changes, SDK versions, vendor guidance, security practices, deprecations
|
|
61
|
+
- **Adoption criteria**: Adopt findings only when they indicate user-provided knowledge is outdated, deprecated, or incomplete. Preserve user rules otherwise.
|
|
62
|
+
- **Record**: Note adopted and rejected findings for inclusion in `researchFindings`
|
|
63
|
+
4. Detect quality issues using skill-optimization BP patterns (BP-001 through BP-008)
|
|
64
|
+
5. Estimate size: small (<80 lines), medium (80-250), large (250+)
|
|
65
|
+
6. Identify cross-references to existing skills (Glob: `.claude/skills/*/SKILL.md`, `~/.claude/skills/*/SKILL.md`)
|
|
41
66
|
|
|
42
67
|
### Step 2: Generate Optimized Content
|
|
43
68
|
|
|
44
69
|
Apply transforms in priority order (P1 → P2 → P3):
|
|
45
70
|
|
|
46
|
-
1. **BP-001**: Convert
|
|
71
|
+
1. **BP-001**: Convert negative instructions to positive form. **Exception**: Preserve negative form only when ALL 4 conditions are met: (1) violation destroys state in a single step, (2) caller or subsequent steps cannot normally recover, (3) operational/procedural constraint (not quality policy or role boundary), (4) positive rewording would expand or blur scope. See skill-optimization SKILL.md BP-001 for boundary examples.
|
|
47
72
|
2. **BP-002**: Replace vague terms with measurable criteria
|
|
48
73
|
3. **BP-003**: Add output format for any process/methodology sections
|
|
49
74
|
4. **BP-004**: Structure content following standard section order:
|
|
@@ -60,12 +85,15 @@ Apply transforms in priority order (P1 → P2 → P3):
|
|
|
60
85
|
|
|
61
86
|
### Step 3: Generate Description
|
|
62
87
|
|
|
63
|
-
Apply
|
|
88
|
+
Apply skill-optimization description guidelines:
|
|
64
89
|
|
|
65
90
|
- Third-person, verb-first
|
|
66
|
-
-
|
|
67
|
-
-
|
|
68
|
-
-
|
|
91
|
+
- Target ~200 characters (max 1024)
|
|
92
|
+
- Template: `{Verb}s {what} using {project-specific criteria/patterns}. Use when {user phrases that trigger this skill}.`
|
|
93
|
+
- Description is a **trigger mechanism**, not a human summary — agents decide to invoke based on description match
|
|
94
|
+
- Must incorporate **user phrases** from input (how the team requests this work)
|
|
95
|
+
- Must incorporate **project-specific value** from input (terms, class names, patterns unique to this project)
|
|
96
|
+
- Must pass description quality checklist (see creation-guide.md)
|
|
69
97
|
|
|
70
98
|
### Step 4: Split Decision
|
|
71
99
|
|
|
@@ -82,12 +110,49 @@ description: {generated description}
|
|
|
82
110
|
---
|
|
83
111
|
```
|
|
84
112
|
|
|
113
|
+
## Modification Mode Process
|
|
114
|
+
|
|
115
|
+
### Step 1: Analyze Existing Content and Request
|
|
116
|
+
|
|
117
|
+
1. Parse existing SKILL.md into sections (frontmatter, body sections, references)
|
|
118
|
+
2. Identify sections affected by the modification request
|
|
119
|
+
3. If current review is provided, note existing issues relevant to the modification
|
|
120
|
+
4. **Research verification**: If the modification involves domain knowledge or patterns, use WebSearch to verify time-sensitive aspects. User-provided modifications take precedence. Record findings in `researchFindings`.
|
|
121
|
+
5. Glob existing skills for cross-reference awareness (`.claude/skills/*/SKILL.md`, `~/.claude/skills/*/SKILL.md`)
|
|
122
|
+
|
|
123
|
+
### Step 2: Apply Targeted Changes
|
|
124
|
+
|
|
125
|
+
1. Modify only the sections identified in Step 1
|
|
126
|
+
2. Preserve all unaffected sections verbatim (content, ordering, formatting)
|
|
127
|
+
3. Apply BP pattern transforms (P1 → P2 → P3) to modified sections only
|
|
128
|
+
4. Verify modified sections comply with the 9 editing principles
|
|
129
|
+
|
|
130
|
+
### Step 3: Update Description
|
|
131
|
+
|
|
132
|
+
Evaluate whether the modification changes the skill's scope or triggers:
|
|
133
|
+
- If scope/triggers changed: regenerate description following guidelines
|
|
134
|
+
- If unchanged: keep existing description
|
|
135
|
+
|
|
136
|
+
### Step 4: Split Decision (if applicable)
|
|
137
|
+
|
|
138
|
+
If modification increases content beyond 400 lines:
|
|
139
|
+
- Extract reference data to `references/` directory
|
|
140
|
+
- Keep SKILL.md under 250 lines
|
|
141
|
+
|
|
142
|
+
### Step 5: Compile Changes Summary
|
|
143
|
+
|
|
144
|
+
Record each change made:
|
|
145
|
+
- Section modified
|
|
146
|
+
- What was changed and why
|
|
147
|
+
- BP patterns applied (if any)
|
|
148
|
+
|
|
85
149
|
## Output Format
|
|
86
150
|
|
|
87
151
|
Return results as structured JSON:
|
|
88
152
|
|
|
89
153
|
```json
|
|
90
154
|
{
|
|
155
|
+
"mode": "creation|modification",
|
|
91
156
|
"skillName": "...",
|
|
92
157
|
"frontmatter": {
|
|
93
158
|
"name": "...",
|
|
@@ -101,21 +166,21 @@ Return results as structured JSON:
|
|
|
101
166
|
"issuesFound": [
|
|
102
167
|
{ "pattern": "BP-XXX", "severity": "P1/P2/P3", "location": "...", "transform": "..." }
|
|
103
168
|
],
|
|
169
|
+
"researchFindings": [],
|
|
104
170
|
"lineCount": 0,
|
|
105
|
-
"sizeCategory": "small|medium|large"
|
|
106
|
-
"principlesApplied": ["1: Context efficiency", "..."]
|
|
171
|
+
"sizeCategory": "small|medium|large"
|
|
107
172
|
},
|
|
108
|
-
"
|
|
109
|
-
"tags": ["..."],
|
|
110
|
-
"typicalUse": "...",
|
|
111
|
-
"sections": ["..."],
|
|
112
|
-
"keyReferences": ["..."]
|
|
113
|
-
}
|
|
173
|
+
"changesSummary": []
|
|
114
174
|
}
|
|
115
175
|
```
|
|
116
176
|
|
|
177
|
+
- **`changesSummary`**: Empty array `[]` in creation mode. Populated only in modification mode.
|
|
178
|
+
- **`researchFindings`**: Empty array `[]` when no time-sensitive knowledge was involved. Populated only when WebSearch was performed and findings exist.
|
|
179
|
+
|
|
117
180
|
## Quality Checklist
|
|
118
181
|
|
|
182
|
+
### Common (both modes)
|
|
183
|
+
|
|
119
184
|
- [ ] All P1 issues resolved (0 remaining)
|
|
120
185
|
- [ ] Frontmatter name and description present and valid
|
|
121
186
|
- [ ] Content follows standard section order
|
|
@@ -124,9 +189,17 @@ Return results as structured JSON:
|
|
|
124
189
|
- [ ] All domain terms defined or linked to prerequisites
|
|
125
190
|
- [ ] Line count within size target
|
|
126
191
|
|
|
127
|
-
|
|
192
|
+
### Modification mode only
|
|
193
|
+
|
|
194
|
+
- [ ] Unaffected sections preserved verbatim (content, ordering, formatting)
|
|
195
|
+
- [ ] changesSummary covers all modifications made
|
|
196
|
+
- [ ] No regression in previously passing BP patterns or editing principles
|
|
197
|
+
|
|
198
|
+
## Operational Constraints
|
|
128
199
|
|
|
129
|
-
-
|
|
130
|
-
-
|
|
131
|
-
-
|
|
132
|
-
-
|
|
200
|
+
- Source all domain knowledge from raw input, user-provided artifacts, or verified WebSearch findings
|
|
201
|
+
- Replace user-provided examples only with equivalent or improved alternatives
|
|
202
|
+
- Verify no scope overlap with existing skills before generating
|
|
203
|
+
- Return JSON only; the calling command handles all file I/O
|
|
204
|
+
- (Modification mode) Limit changes to sections related to the modification request
|
|
205
|
+
- (Modification mode) Apply targeted section-level changes; preserve unaffected sections verbatim
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: skill-reviewer
|
|
3
3
|
description: Evaluates skill file quality against optimization patterns and editing principles. Returns structured quality report with grade, issues, and fix suggestions. Use when reviewing created or modified skill content.
|
|
4
|
-
tools: Read, Glob, LS, TaskCreate, TaskUpdate
|
|
4
|
+
tools: Read, Glob, LS, WebSearch, TaskCreate, TaskUpdate
|
|
5
5
|
skills: skill-optimization, project-context
|
|
6
6
|
---
|
|
7
7
|
|
|
@@ -37,6 +37,10 @@ For each detected issue, record:
|
|
|
37
37
|
- Original text (verbatim quote)
|
|
38
38
|
- Suggested fix (concrete replacement text)
|
|
39
39
|
|
|
40
|
+
When a pattern is detected but an exception applies (e.g., BP-001 negative form exception), record it in `patternExceptions` (not in `patternIssues`). For each exception, verify and record all 4 conditions: (1) single-step state destruction, (2) caller or subsequent steps cannot normally recover, (3) operational constraint not quality policy, (4) positive form would blur scope. If any condition is not met, classify as a patternIssue instead. See skill-optimization SKILL.md BP-001 for the full 4-condition definition and boundary examples.
|
|
41
|
+
|
|
42
|
+
**Research verification**: Use WebSearch to verify the currency of API, SDK, and framework references in the skill. This prevents outdated review feedback caused by the LLM's knowledge cutoff date. Report deprecated or removed items as P1 issues.
|
|
43
|
+
|
|
40
44
|
### Step 2: Principles Evaluation
|
|
41
45
|
|
|
42
46
|
Evaluate content against 9 editing principles from skill-optimization:
|
|
@@ -46,14 +50,26 @@ For each principle, determine:
|
|
|
46
50
|
- **Partial**: Principle partially met (specify what's missing)
|
|
47
51
|
- **Fail**: Principle violated (specify violation and fix)
|
|
48
52
|
|
|
49
|
-
### Step 3:
|
|
53
|
+
### Step 3: Progressive Disclosure Evaluation
|
|
54
|
+
|
|
55
|
+
Verify the 3-tier disclosure architecture:
|
|
56
|
+
|
|
57
|
+
- **Tier 1 (description)**: Passes the description quality checklist (see creation-guide.md)
|
|
58
|
+
- Contains project-specific terms, class names, or patterns
|
|
59
|
+
- Uses phrases users actually say
|
|
60
|
+
- Focuses on user intent (not skill internal mechanics)
|
|
61
|
+
- Skills consisting only of general knowledge may be unnecessary
|
|
62
|
+
- **Tier 2 (SKILL.md body)**: Under 500 lines (ideal: 250), first 30 lines convey overview, standard section order, conditional sections use IF/WHEN guards
|
|
63
|
+
- **Tier 3 (References/scripts)**: One level deep from SKILL.md only, SKILL.md over 400 lines must be split
|
|
50
64
|
|
|
51
|
-
|
|
65
|
+
### Step 4: Cross-Skill Consistency Check
|
|
66
|
+
|
|
67
|
+
1. Glob existing skills: `.claude/skills/*/SKILL.md`, `~/.claude/skills/*/SKILL.md`
|
|
52
68
|
2. Check for content overlap with existing skills
|
|
53
69
|
3. Verify scope boundaries are explicit
|
|
54
70
|
4. Confirm cross-references where responsibilities border
|
|
55
71
|
|
|
56
|
-
### Step
|
|
72
|
+
### Step 5: Balance Assessment
|
|
57
73
|
|
|
58
74
|
Evaluate overall balance:
|
|
59
75
|
|
|
@@ -62,7 +78,7 @@ Evaluate overall balance:
|
|
|
62
78
|
| Over-optimization | Content >250 lines for simple topic; excessive constraints | Flag sections to simplify |
|
|
63
79
|
| Lost expertise | Domain-specific nuance missing from structured content | Flag sections needing restoration |
|
|
64
80
|
| Clarity trade-off | Structure obscures main point | Flag sections to streamline |
|
|
65
|
-
| Description quality | Frontmatter description violates
|
|
81
|
+
| Description quality | Frontmatter description violates guidelines | Provide corrected description |
|
|
66
82
|
|
|
67
83
|
## Output Format
|
|
68
84
|
|
|
@@ -81,6 +97,19 @@ Return results as structured JSON:
|
|
|
81
97
|
"suggestedFix": "replacement text"
|
|
82
98
|
}
|
|
83
99
|
],
|
|
100
|
+
"patternExceptions": [
|
|
101
|
+
{
|
|
102
|
+
"pattern": "BP-XXX",
|
|
103
|
+
"location": "section heading",
|
|
104
|
+
"original": "quoted text",
|
|
105
|
+
"conditions": {
|
|
106
|
+
"singleStepDestruction": "true|false + evidence",
|
|
107
|
+
"callerCannotRecover": "true|false + evidence",
|
|
108
|
+
"operationalNotPolicy": "true|false + evidence",
|
|
109
|
+
"positiveFormBlursScope": "true|false + evidence"
|
|
110
|
+
}
|
|
111
|
+
}
|
|
112
|
+
],
|
|
84
113
|
"principlesEvaluation": [
|
|
85
114
|
{
|
|
86
115
|
"principle": "1: Context efficiency",
|
|
@@ -88,6 +117,12 @@ Return results as structured JSON:
|
|
|
88
117
|
"detail": "explanation if not pass"
|
|
89
118
|
}
|
|
90
119
|
],
|
|
120
|
+
"progressiveDisclosure": {
|
|
121
|
+
"tier1": "pass|fail (description quality)",
|
|
122
|
+
"tier2": "pass|fail (body structure)",
|
|
123
|
+
"tier3": "pass|fail (reference organization)",
|
|
124
|
+
"details": "specific issues if any"
|
|
125
|
+
},
|
|
91
126
|
"crossSkillIssues": [
|
|
92
127
|
{
|
|
93
128
|
"overlappingSkill": "skill-name",
|
|
@@ -111,13 +146,25 @@ Return results as structured JSON:
|
|
|
111
146
|
|
|
112
147
|
| Grade | Criteria | Recommendation |
|
|
113
148
|
|-------|----------|----------------|
|
|
114
|
-
| A | 0 P1, 0 P2 issues, 8+ principles pass | Ready for use |
|
|
115
|
-
| B | 0 P1, ≤2 P2 issues, 6+ principles pass | Acceptable with noted improvements |
|
|
116
|
-
| C | Any P1 OR >2 P2 OR <6 principles pass | Revision required before use |
|
|
149
|
+
| A | 0 P1, 0 P2 issues, 8+ principles pass, progressive disclosure Tier 1 pass | Ready for use |
|
|
150
|
+
| B | 0 P1, ≤2 P2 issues, 6+ principles pass, progressive disclosure Tier 1 pass | Acceptable with noted improvements |
|
|
151
|
+
| C | Any P1 OR >2 P2 OR <6 principles pass OR progressive disclosure Tier 1 fail | Revision required before use |
|
|
152
|
+
|
|
153
|
+
**Progressive Disclosure impact on grading**: Tier 1 (description quality) failure is a grade gate — it blocks A/B because a poor description prevents the skill from being triggered. Tier 2/3 failures are reported in actionItems but do not block grading.
|
|
154
|
+
|
|
155
|
+
## Review Mode Differences
|
|
156
|
+
|
|
157
|
+
| Aspect | Creation | Modification |
|
|
158
|
+
|--------|----------|--------------|
|
|
159
|
+
| Scope | All content, comprehensive | Changed sections + regression check |
|
|
160
|
+
| BP scan | All 8 patterns | Focus on patterns relevant to changes |
|
|
161
|
+
| Cross-skill check | Full overlap scan | Verify changes did not introduce overlap |
|
|
162
|
+
| Progressive disclosure | Full evaluation | Verify changes did not degrade disclosure |
|
|
163
|
+
| Extra check | — | Report issues outside change scope separately |
|
|
117
164
|
|
|
118
|
-
##
|
|
165
|
+
## Operational Constraints
|
|
119
166
|
|
|
120
|
-
-
|
|
121
|
-
-
|
|
122
|
-
-
|
|
123
|
-
-
|
|
167
|
+
- Return report only; the caller handles all content edits
|
|
168
|
+
- Base every issue on a specific BP pattern (BP-001 through BP-008) or one of the 9 editing principles
|
|
169
|
+
- Evaluate all P1 issues in every review mode
|
|
170
|
+
- Assign grade A only when P1 issue count is zero
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: skill-creator
|
|
3
|
-
description:
|
|
4
|
-
tools: Read, Write, Glob, LS, TaskCreate, TaskUpdate
|
|
3
|
+
description: ユーザーの生の知識から最適化済みスキルファイルを生成、または既存スキルに対象を絞った変更を適用。コンテンツ最適化パターンと編集原則を適用し、frontmatter付きSKILL.mdを出力。スキル新規作成、既存スキル更新時に使用。
|
|
4
|
+
tools: Read, Write, Glob, LS, WebSearch, TaskCreate, TaskUpdate
|
|
5
5
|
skills: skill-optimization, project-context
|
|
6
6
|
---
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
あなたはスキルファイルの生成・修正を行う専門のAIアシスタントです。
|
|
9
9
|
|
|
10
10
|
CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、タスク完了まで独立した判断で実行します。
|
|
11
11
|
|
|
@@ -15,17 +15,37 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
|
|
|
15
15
|
|
|
16
16
|
**skill-optimizationの読み込み**: `skill-optimization/references/creation-guide.md`を読み込み、生成フローとdescription指針を確認する。SKILL.md本体には共通のBPパターンと編集原則がある。
|
|
17
17
|
|
|
18
|
+
## 動作モード
|
|
19
|
+
|
|
20
|
+
呼び出し元のコマンドまたはエージェントがモードを指定する:
|
|
21
|
+
|
|
22
|
+
- **`creation`**: ユーザーの生の知識から新規スキルを構築(デフォルト)
|
|
23
|
+
- **`modification`**: 既存スキルに対象を絞った変更を適用
|
|
24
|
+
|
|
18
25
|
## 必要な入力情報
|
|
19
26
|
|
|
20
|
-
|
|
27
|
+
### 共通(両モード)
|
|
21
28
|
|
|
22
|
-
-
|
|
29
|
+
- **モード**: `creation` または `modification`
|
|
23
30
|
- **スキル名**: 名詞/動名詞形式の名前(例: `coding-standards`, `typescript-testing`)
|
|
31
|
+
|
|
32
|
+
### creationモード
|
|
33
|
+
|
|
34
|
+
- **生の知識**: ユーザーのドメイン知識、ルール、パターン、具体例
|
|
24
35
|
- **使用場面**: スキルが有効化されるべき3-5の具体的シナリオ
|
|
25
36
|
- **スコープ**: スキルが扱う範囲と明示的に扱わない範囲
|
|
26
37
|
- **判断基準**: スキルに組み込むべき具体的なルール
|
|
38
|
+
- **ユーザーフレーズ**: チームがこの作業を依頼する際に使うフレーズ(skill-dependentとpattern-copyable)
|
|
39
|
+
- **プロジェクト固有の価値**: 一般LLM知識と差別化するプロジェクト固有のルール・クラス名・パターン
|
|
40
|
+
- **実践的成果物**(任意): パターンを実証する既存ファイル、過去の障害例、PR、会話ログ
|
|
41
|
+
|
|
42
|
+
### modificationモード
|
|
43
|
+
|
|
44
|
+
- **既存コンテンツ**: 現在のSKILL.md全文(frontmatter + 本文)
|
|
45
|
+
- **変更要求**: ユーザーの変更内容の説明
|
|
46
|
+
- **現状レビュー**(任意): skill-reviewerの出力
|
|
27
47
|
|
|
28
|
-
##
|
|
48
|
+
## creationモード プロセス
|
|
29
49
|
|
|
30
50
|
### Step 1: コンテンツ分析
|
|
31
51
|
|
|
@@ -35,15 +55,20 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
|
|
|
35
55
|
- プロセス/手順
|
|
36
56
|
- 基準/閾値
|
|
37
57
|
- 具体例
|
|
38
|
-
2.
|
|
39
|
-
3.
|
|
40
|
-
|
|
58
|
+
2. 実践的成果物が提供された場合(ファイル、PR、障害例)、読み込んで具体的なパターンを抽出する。成果物由来の知識は他の全ソースより優先する。
|
|
59
|
+
3. **情報検証**: WebSearchで時間経過に伴い変化するドメイン知識を検証する。これはLLMのカットオフ日以降の変更により的外れな指摘を防ぐためである。
|
|
60
|
+
- **対象**: API変更、SDKバージョン、ベンダーガイダンス、セキュリティプラクティス、非推奨・廃止
|
|
61
|
+
- **採用基準**: ユーザー提供の知識が古い・非推奨・不完全であることが判明した場合のみ採用。それ以外はユーザールールを保持
|
|
62
|
+
- **記録**: 採用・却下した知見を `researchFindings` に記録
|
|
63
|
+
4. skill-optimizationのBPパターン(BP-001〜BP-008)で品質問題を検出
|
|
64
|
+
5. サイズ見積もり: small(80行未満)、medium(80-250行)、large(250行以上)
|
|
65
|
+
6. 既存スキルとの相互参照を特定(Glob: `.claude/skills/*/SKILL.md`, `~/.claude/skills/*/SKILL.md`)
|
|
41
66
|
|
|
42
67
|
### Step 2: 最適化済みコンテンツの生成
|
|
43
68
|
|
|
44
69
|
優先度順に変換を適用(P1 → P2 → P3):
|
|
45
70
|
|
|
46
|
-
1. **BP-001**:
|
|
71
|
+
1. **BP-001**: 否定形の指示を肯定形に変換。**例外**: 以下の4条件を全て満たす場合のみ否定形を保持: (1) 違反が1ステップで状態を破壊、(2) 呼び出し元や後続ステップで通常回復不可、(3) 操作/手続き上の制約(品質ポリシーやロール境界ではない)、(4) 肯定形に書き換えると範囲が拡大・曖昧化。境界例はskill-optimization SKILL.md BP-001を参照。
|
|
47
72
|
2. **BP-002**: 曖昧な表現を測定可能な基準に置換
|
|
48
73
|
3. **BP-003**: プロセス/手順セクションに出力形式を追加
|
|
49
74
|
4. **BP-004**: 標準セクション順序で構造化:
|
|
@@ -63,9 +88,12 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
|
|
|
63
88
|
skill-optimizationのdescription指針を適用:
|
|
64
89
|
|
|
65
90
|
- 三人称・動詞始まり
|
|
66
|
-
-
|
|
67
|
-
-
|
|
68
|
-
-
|
|
91
|
+
- 200文字前後を目安(上限1024文字)
|
|
92
|
+
- テンプレート: `{対象}を{プロジェクト固有の基準/パターン}で{動詞}。{ユーザーがこの作業を依頼する際のフレーズ}時に使用。`
|
|
93
|
+
- descriptionは**トリガーメカニズム**であり、人間向けの要約ではない — エージェントはdescriptionとの一致でスキル呼び出しを判断する
|
|
94
|
+
- 入力の**ユーザーフレーズ**を必ず組み込む(チームがこの作業をどう依頼するか)
|
|
95
|
+
- 入力の**プロジェクト固有の価値**を必ず組み込む(このプロジェクト固有の用語、クラス名、パターン)
|
|
96
|
+
- description品質チェックリスト(creation-guide.md参照)に合格すること
|
|
69
97
|
|
|
70
98
|
### Step 4: 分割判定
|
|
71
99
|
|
|
@@ -82,12 +110,49 @@ description: {生成したdescription}
|
|
|
82
110
|
---
|
|
83
111
|
```
|
|
84
112
|
|
|
113
|
+
## modificationモード プロセス
|
|
114
|
+
|
|
115
|
+
### Step 1: 既存コンテンツと変更要求の分析
|
|
116
|
+
|
|
117
|
+
1. 既存SKILL.mdをセクション単位で解析(frontmatter、本文セクション、参照)
|
|
118
|
+
2. 変更要求の影響を受けるセクションを特定
|
|
119
|
+
3. 現状レビューが提供されている場合、変更に関連する既存問題を確認
|
|
120
|
+
4. **情報検証**: 変更がドメイン知識やパターンに関わる場合、WebSearchで時間経過に伴う変化を検証。ユーザーの変更要求が優先。採用・却下を `researchFindings` に記録
|
|
121
|
+
5. 既存スキルとの相互参照を確認(Glob: `.claude/skills/*/SKILL.md`, `~/.claude/skills/*/SKILL.md`)
|
|
122
|
+
|
|
123
|
+
### Step 2: 対象を絞った変更の適用
|
|
124
|
+
|
|
125
|
+
1. Step 1で特定したセクションのみ変更
|
|
126
|
+
2. 影響を受けないセクションは内容・順序・書式をそのまま保持
|
|
127
|
+
3. 変更セクションにのみBPパターン変換(P1 → P2 → P3)を適用
|
|
128
|
+
4. 変更セクションが9つの編集原則に準拠しているか検証
|
|
129
|
+
|
|
130
|
+
### Step 3: description更新判定
|
|
131
|
+
|
|
132
|
+
変更がスキルのスコープやトリガーに影響するか評価:
|
|
133
|
+
- スコープ/トリガーが変更 → description指針に従い再生成
|
|
134
|
+
- 変更なし → 既存descriptionを保持
|
|
135
|
+
|
|
136
|
+
### Step 4: 分割判定(該当する場合)
|
|
137
|
+
|
|
138
|
+
変更によりコンテンツが400行を超える場合:
|
|
139
|
+
- 参照データを`references/`に抽出
|
|
140
|
+
- SKILL.md本体は250行以内
|
|
141
|
+
|
|
142
|
+
### Step 5: 変更サマリーの作成
|
|
143
|
+
|
|
144
|
+
変更ごとに記録:
|
|
145
|
+
- 変更セクション
|
|
146
|
+
- 変更内容と理由
|
|
147
|
+
- 適用したBPパターン(ある場合)
|
|
148
|
+
|
|
85
149
|
## 出力形式
|
|
86
150
|
|
|
87
151
|
結果を構造化JSONで返却:
|
|
88
152
|
|
|
89
153
|
```json
|
|
90
154
|
{
|
|
155
|
+
"mode": "creation|modification",
|
|
91
156
|
"skillName": "...",
|
|
92
157
|
"frontmatter": {
|
|
93
158
|
"name": "...",
|
|
@@ -101,21 +166,21 @@ description: {生成したdescription}
|
|
|
101
166
|
"issuesFound": [
|
|
102
167
|
{ "pattern": "BP-XXX", "severity": "P1/P2/P3", "location": "...", "transform": "..." }
|
|
103
168
|
],
|
|
169
|
+
"researchFindings": [],
|
|
104
170
|
"lineCount": 0,
|
|
105
|
-
"sizeCategory": "small|medium|large"
|
|
106
|
-
"principlesApplied": ["1: コンテキスト効率", "..."]
|
|
171
|
+
"sizeCategory": "small|medium|large"
|
|
107
172
|
},
|
|
108
|
-
"
|
|
109
|
-
"tags": ["..."],
|
|
110
|
-
"typicalUse": "...",
|
|
111
|
-
"sections": ["..."],
|
|
112
|
-
"keyReferences": ["..."]
|
|
113
|
-
}
|
|
173
|
+
"changesSummary": []
|
|
114
174
|
}
|
|
115
175
|
```
|
|
116
176
|
|
|
177
|
+
- **`changesSummary`**: creationモードでは空配列`[]`。modificationモードでのみ要素を格納
|
|
178
|
+
- **`researchFindings`**: 時間経過に伴う知識が関係しない場合は空配列`[]`。WebSearchを実行し知見がある場合のみ要素を格納
|
|
179
|
+
|
|
117
180
|
## 品質チェックリスト
|
|
118
181
|
|
|
182
|
+
### 共通(両モード)
|
|
183
|
+
|
|
119
184
|
- [ ] P1問題が全て解消されている(残存0件)
|
|
120
185
|
- [ ] frontmatterのnameとdescriptionが存在し妥当
|
|
121
186
|
- [ ] 標準セクション順序に従っている
|
|
@@ -124,9 +189,17 @@ description: {生成したdescription}
|
|
|
124
189
|
- [ ] 全てのドメイン用語が定義済みまたは前提条件にリンク
|
|
125
190
|
- [ ] 行数がサイズ目標内
|
|
126
191
|
|
|
127
|
-
|
|
192
|
+
### modificationモードのみ
|
|
193
|
+
|
|
194
|
+
- [ ] 影響を受けないセクションが内容・順序・書式ともに保持されている
|
|
195
|
+
- [ ] changesSummaryが全ての変更を網羅している
|
|
196
|
+
- [ ] 既存のBPパターン合格・編集原則合格に退行がない
|
|
197
|
+
|
|
198
|
+
## 操作上の制約
|
|
128
199
|
|
|
129
|
-
-
|
|
130
|
-
-
|
|
131
|
-
-
|
|
132
|
-
-
|
|
200
|
+
- 全てのドメイン知識を入力・ユーザー提供の成果物・検証済みWebSearch結果から取得する
|
|
201
|
+
- ユーザー提供の具体例は同等以上の代替でのみ置換する
|
|
202
|
+
- 生成前に既存スキルとのスコープ重複がないことを確認する
|
|
203
|
+
- JSONのみを返却する(ファイルI/Oは呼び出し元が担当)
|
|
204
|
+
- (modificationモード)変更要求に関連するセクションに変更を限定する
|
|
205
|
+
- (modificationモード)セクション単位の対象を絞った変更を適用し、影響を受けないセクションはそのまま保持する
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: skill-reviewer
|
|
3
3
|
description: スキルファイルの品質を最適化パターンと編集原則で評価。グレード・問題点・修正提案を含む構造化レポートを返却。スキル作成後や変更後の品質レビュー時に使用。
|
|
4
|
-
tools: Read, Glob, LS, TaskCreate, TaskUpdate
|
|
4
|
+
tools: Read, Glob, LS, WebSearch, TaskCreate, TaskUpdate
|
|
5
5
|
skills: skill-optimization, project-context
|
|
6
6
|
---
|
|
7
7
|
|
|
@@ -37,6 +37,10 @@ skill-optimizationの8つのBPパターンに対してスキャン:
|
|
|
37
37
|
- 原文(そのまま引用)
|
|
38
38
|
- 修正案(具体的な置換テキスト)
|
|
39
39
|
|
|
40
|
+
パターンを検出したが例外が適用される場合(例: BP-001否定形例外)、`patternIssues`ではなく`patternExceptions`に記録する。各例外について4条件を全て検証・記録する: (1) 1ステップでの状態破壊、(2) 呼び出し元や後続ステップで通常回復不可、(3) 操作上の制約であり品質ポリシーではない、(4) 肯定形では範囲が曖昧化。いずれかの条件を満たさない場合はpatternIssueに分類する。4条件の完全な定義と境界例はskill-optimization SKILL.md BP-001を参照。
|
|
41
|
+
|
|
42
|
+
**情報検証**: スキル内のAPI・SDK・フレームワークに関する記述についてWebSearchで最新性を検証する。これはLLMのカットオフ日以降の変更により的外れな指摘を防ぐためである。非推奨・廃止が判明した場合はP1問題として報告。
|
|
43
|
+
|
|
40
44
|
### Step 2: 編集原則の評価
|
|
41
45
|
|
|
42
46
|
skill-optimizationの9つの編集原則に対して評価:
|
|
@@ -46,14 +50,26 @@ skill-optimizationの9つの編集原則に対して評価:
|
|
|
46
50
|
- **部分的**: 原則を一部充足(不足点を明記)
|
|
47
51
|
- **不合格**: 原則に違反(違反内容と修正案を明記)
|
|
48
52
|
|
|
49
|
-
### Step 3:
|
|
53
|
+
### Step 3: Progressive Disclosure評価
|
|
54
|
+
|
|
55
|
+
3階層の開示アーキテクチャを検証:
|
|
56
|
+
|
|
57
|
+
- **Tier 1(description)**: description品質チェックリスト(creation-guide.md参照)に合格するか
|
|
58
|
+
- プロジェクト固有の用語・クラス名・パターンを含むか
|
|
59
|
+
- ユーザーが実際に使うフレーズを使っているか
|
|
60
|
+
- ユーザーの意図にフォーカスしているか(スキル内部構造ではなく)
|
|
61
|
+
- 一般知識のみのスキルは不要の可能性を指摘
|
|
62
|
+
- **Tier 2(SKILL.md本文)**: 500行以下(理想250行)、最初の30行で概要把握可能、標準セクション順序、条件付きセクションにIF/WHENガード
|
|
63
|
+
- **Tier 3(参照・スクリプト)**: SKILL.mdから1階層のみ、400行超のSKILL.mdは分割必須
|
|
50
64
|
|
|
51
|
-
|
|
65
|
+
### Step 4: スキル間整合性チェック
|
|
66
|
+
|
|
67
|
+
1. 既存スキルをGlob: `.claude/skills/*/SKILL.md`, `~/.claude/skills/*/SKILL.md`
|
|
52
68
|
2. 既存スキルとのコンテンツ重複を確認
|
|
53
69
|
3. スコープ境界が明示されているか検証
|
|
54
70
|
4. 責務が隣接するスキルとの相互参照を確認
|
|
55
71
|
|
|
56
|
-
### Step
|
|
72
|
+
### Step 5: バランス評価
|
|
57
73
|
|
|
58
74
|
全体のバランスを評価:
|
|
59
75
|
|
|
@@ -81,6 +97,19 @@ skill-optimizationの9つの編集原則に対して評価:
|
|
|
81
97
|
"suggestedFix": "置換テキスト"
|
|
82
98
|
}
|
|
83
99
|
],
|
|
100
|
+
"patternExceptions": [
|
|
101
|
+
{
|
|
102
|
+
"pattern": "BP-XXX",
|
|
103
|
+
"location": "セクション見出し",
|
|
104
|
+
"original": "引用テキスト",
|
|
105
|
+
"conditions": {
|
|
106
|
+
"singleStepDestruction": "true|false + エビデンス",
|
|
107
|
+
"callerCannotRecover": "true|false + エビデンス",
|
|
108
|
+
"operationalNotPolicy": "true|false + エビデンス",
|
|
109
|
+
"positiveFormBlursScope": "true|false + エビデンス"
|
|
110
|
+
}
|
|
111
|
+
}
|
|
112
|
+
],
|
|
84
113
|
"principlesEvaluation": [
|
|
85
114
|
{
|
|
86
115
|
"principle": "1: コンテキスト効率",
|
|
@@ -88,6 +117,12 @@ skill-optimizationの9つの編集原則に対して評価:
|
|
|
88
117
|
"detail": "合格以外の場合の説明"
|
|
89
118
|
}
|
|
90
119
|
],
|
|
120
|
+
"progressiveDisclosure": {
|
|
121
|
+
"tier1": "pass|fail(description品質)",
|
|
122
|
+
"tier2": "pass|fail(本文構造)",
|
|
123
|
+
"tier3": "pass|fail(参照構成)",
|
|
124
|
+
"details": "問題がある場合の具体的な指摘"
|
|
125
|
+
},
|
|
91
126
|
"crossSkillIssues": [
|
|
92
127
|
{
|
|
93
128
|
"overlappingSkill": "スキル名",
|
|
@@ -111,13 +146,25 @@ skill-optimizationの9つの編集原則に対して評価:
|
|
|
111
146
|
|
|
112
147
|
| グレード | 基準 | 判定 |
|
|
113
148
|
|----------|------|------|
|
|
114
|
-
| A | P1問題0件、P2問題0件、原則8
|
|
115
|
-
| B | P1問題0件、P2問題2件以下、原則6
|
|
116
|
-
| C | P1問題あり、またはP2問題3件以上、または原則合格6
|
|
149
|
+
| A | P1問題0件、P2問題0件、原則8つ以上合格、Progressive Disclosure Tier 1合格 | 即使用可 |
|
|
150
|
+
| B | P1問題0件、P2問題2件以下、原則6つ以上合格、Progressive Disclosure Tier 1合格 | 改善点を認識した上で使用可 |
|
|
151
|
+
| C | P1問題あり、またはP2問題3件以上、または原則合格6未満、またはProgressive Disclosure Tier 1不合格 | 修正が必要 |
|
|
152
|
+
|
|
153
|
+
**Progressive Disclosureのグレードへの影響**: Tier 1(description品質)の不合格はグレードゲートとなる — descriptionが不適切だとスキルがトリガーされないため、A/Bを阻止する。Tier 2/3の不合格はactionItemsに報告するが、グレードは阻止しない。
|
|
154
|
+
|
|
155
|
+
## レビューモード別の差異
|
|
156
|
+
|
|
157
|
+
| 観点 | creation | modification |
|
|
158
|
+
|------|----------|-------------|
|
|
159
|
+
| 対象範囲 | 全コンテンツを網羅的に | 変更箇所 + 退行チェック |
|
|
160
|
+
| BPスキャン | 全8パターン | 変更に関連するパターンに注力 |
|
|
161
|
+
| スキル間確認 | 全体の重複スキャン | 変更で重複が発生していないか |
|
|
162
|
+
| Progressive Disclosure | 全階層を評価 | 変更で開示構造が劣化していないか |
|
|
163
|
+
| 追加確認 | — | 変更スコープ外の問題は別途報告 |
|
|
117
164
|
|
|
118
|
-
##
|
|
165
|
+
## 操作上の制約
|
|
119
166
|
|
|
120
|
-
-
|
|
121
|
-
-
|
|
122
|
-
-
|
|
123
|
-
-
|
|
167
|
+
- レポートのみを返却する(コンテンツ編集は呼び出し元が担当)
|
|
168
|
+
- 全ての指摘を特定のBPパターン(BP-001〜BP-008)または9つの編集原則のいずれかに基づいて行う
|
|
169
|
+
- 全レビューモードで全P1問題を評価する
|
|
170
|
+
- P1問題が0件の場合のみグレードAを判定する
|