takt/builtins/en/pieces/review-only.yaml
nrslib ea7ce54912 takt: # タスク指示書: resources/ → builtins/ リネーム + export-cc 修正
## 概要
`resources/` ディレクトリを `builtins/` にリネームし、用途を明確化。同時に export-cc コマンドを拡張して全リソースをコピーするように修正する。

---

## タスク一覧

### 1. ディレクトリリネーム(優先度: 高)

| 変更前 | 変更後 |
|--------|--------|
| `resources/` | `builtins/` |
| `resources/global/{lang}/` | `builtins/{lang}/`(global/ 階層を除去) |
| `resources/project/` | `builtins/project/` |
| `resources/skill/` | `builtins/skill/` |

### 2. 不要ファイル削除(優先度: 高)

- `builtins/{lang}/prompts/` を削除
  - 対象: `interactive-system.md`, `interactive-summary.md`
  - 理由: コードから未参照、実体は `src/shared/prompts/`

### 3. コード修正 — パス参照(優先度: 高)

`resources` → `builtins`、`global/{lang}` → `{lang}` に更新:

| ファイル | 修正内容 |
|----------|----------|
| `src/infra/resources/index.ts` | `getResourcesDir()`, `getGlobalResourcesDir()`, `getLanguageResourcesDir()` 等のパス |
| `src/infra/config/paths.ts` | `getBuiltinPiecesDir()`, `getBuiltinPersonasDir()` |
| `src/infra/config/global/initialization.ts` | `copyLanguageConfigYaml()` |
| `src/infra/config/loaders/pieceCategories.ts` | `getLanguageResourcesDir()` 参照 |
| `src/features/config/ejectBuiltin.ts` | `getLanguageResourcesDir()` 参照 |
| `src/features/config/deploySkill.ts` | `getResourcesDir()` 参照 |

### 4. export-cc 修正(優先度: 高)

ファイル: `src/features/config/deploySkill.ts`

**現状**: pieces/ と personas/ のみコピー

**修正後**:
- `builtins/{lang}/` 全体を `~/.claude/skills/takt/` にコピー
- `skill/` のファイル(SKILL.md, references/, takt-command.md)は従来通り
- サマリー表示を新リソースタイプ(stances, instructions, knowledge 等)に対応
- confirm メッセージ修正:
  - 現状: `'上書きしますか?'`
  - 修正後: `'既存のスキルファイルをすべて削除し、最新版に置き換えます。続行しますか?'`

### 5. テスト修正(優先度: 中)

| ファイル | 修正内容 |
|----------|----------|
| `src/__tests__/initialization.test.ts` | `getLanguageResourcesDir` のパス期待値 |
| `src/__tests__/piece-category-config.test.ts` | mock パス |
| その他 `resources` パスを参照しているテスト | パス更新 |

### 6. ビルド・パッケージ設定(優先度: 中)

| ファイル | 修正内容 |
|----------|----------|
| `package.json` | `files` フィールドで `resources/` → `builtins/` |
| `tsconfig.json` | `resources/` への参照があれば更新 |
| `.gitignore` | 必要に応じて更新 |

### 7. ドキュメント(優先度: 低)

- `CLAUDE.md` の Directory Structure セクションを更新
- JSDoc コメントから `prompts/` 記述を削除

---

## 制約

- `builtins/{lang}/` のフラット構造は変更不可(ピースYAML内の相対パス依存)
- eject のセーフティ(skip-if-exists)は変更不要
- export-cc のセーフティ(SKILL.md 存在チェック + confirm)は維持

---

## 確認方法

- `npm run build` が成功すること
- `npm test` が全てパスすること
- `takt init` / `takt eject` / `takt export-cc` が正常動作すること
2026-02-07 14:46:20 +09:00

262 lines
7.5 KiB
YAML

# Review-Only Piece
# Reviews code or PRs without making any edits
# Local: console output only. PR specified: posts inline comments + summary to PR
#
# Flow:
# plan -> reviewers (parallel: arch-review + security-review + ai-review) -> supervise
# -> pr-comment -> COMPLETE (PR comment requested)
# -> COMPLETE (local: console output only)
# -> ABORT (rejected)
#
# All movements have edit: false (no file modifications)
#
# Template Variables:
# {iteration} - Piece-wide turn count
# {max_iterations} - Maximum iterations allowed
# {movement_iteration} - Per-movement iteration count
# {task} - Original user request
# {previous_response} - Output from the previous movement
# {user_inputs} - Accumulated user inputs
# {report_dir} - Report directory name
name: review-only
description: Review-only piece - reviews code without making edits
max_iterations: 10
stances:
review: ../stances/review.md
personas:
planner: ../personas/planner.md
architecture-reviewer: ../personas/architecture-reviewer.md
security-reviewer: ../personas/security-reviewer.md
ai-antipattern-reviewer: ../personas/ai-antipattern-reviewer.md
supervisor: ../personas/supervisor.md
pr-commenter: ../personas/pr-commenter.md
instructions:
review-arch: ../instructions/review-arch.md
review-security: ../instructions/review-security.md
review-ai: ../instructions/review-ai.md
report_formats:
architecture-review: ../report-formats/architecture-review.md
security-review: ../report-formats/security-review.md
ai-review: ../report-formats/ai-review.md
review-summary: ../report-formats/review-summary.md
initial_movement: plan
movements:
- name: plan
edit: false
persona: planner
allowed_tools:
- Read
- Glob
- Grep
- WebSearch
- WebFetch
rules:
- condition: Review scope is clear
next: reviewers
- condition: User is asking a question (not a review task)
next: COMPLETE
- condition: Requirements unclear, insufficient info
next: ABORT
appendix: |
Clarifications needed:
- {Question 1}
- {Question 2}
instruction_template: |
## Previous Response (when returned from supervise)
{previous_response}
Analyze the review request and create a review plan.
**This is a review-only piece.** No code edits will be made.
Focus on:
1. Identify which files/modules to review
2. Determine review focus areas (architecture, security, AI patterns, etc.)
3. Note any specific concerns mentioned in the request
**If a PR number is mentioned** (e.g., "PR #42"), include it in your plan
so reviewers can focus on the PR's changed files.
- name: reviewers
parallel:
- name: arch-review
edit: false
persona: architecture-reviewer
stance: review
report:
name: 01-architect-review.md
format: architecture-review
allowed_tools:
- Read
- Glob
- Grep
- WebSearch
- WebFetch
rules:
- condition: approved
- condition: needs_fix
instruction: review-arch
- name: security-review
edit: false
persona: security-reviewer
stance: review
report:
name: 02-security-review.md
format: security-review
allowed_tools:
- Read
- Glob
- Grep
- WebSearch
- WebFetch
rules:
- condition: approved
- condition: needs_fix
instruction: review-security
- name: ai-review
edit: false
persona: ai-antipattern-reviewer
stance: review
report:
name: 03-ai-review.md
format: ai-review
allowed_tools:
- Read
- Glob
- Grep
- WebSearch
- WebFetch
rules:
- condition: approved
- condition: needs_fix
instruction: review-ai
rules:
- condition: all("approved")
next: supervise
- condition: any("needs_fix")
next: supervise
- name: supervise
edit: false
persona: supervisor
stance: review
report:
- Review Summary: 04-review-summary.md
allowed_tools:
- Read
- Glob
- Grep
- WebSearch
- WebFetch
rules:
- condition: approved, PR comment requested
next: pr-comment
- condition: approved
next: COMPLETE
- condition: rejected
next: ABORT
instruction_template: |
## Review Results
{previous_response}
**This is a review-only piece.** Do NOT run tests or builds.
Your role is to synthesize the review results and produce a final summary.
**Tasks:**
1. Read all review reports in the Report Directory
2. Synthesize findings from architecture, security, and AI reviews
3. Produce a consolidated review summary with overall verdict
4. Determine routing:
- If the task mentions posting to a PR (e.g., "post comments to PR", "comment on PR"),
route to `pr-comment` movement (condition: "approved, PR comment requested")
- If local review only, route to COMPLETE (condition: "approved")
- If critical issues found, route to ABORT (condition: "rejected")
**Review Summary report format:**
```markdown
# Review Summary
## Overall Verdict: APPROVE / REJECT
## Summary
{2-3 sentences consolidating all review results}
## Review Results
| Review | Result | Key Findings |
|--------|--------|--------------|
| Architecture | APPROVE/REJECT | {Brief finding} |
| Security | APPROVE/REJECT | {Brief finding} |
| AI Antipattern | APPROVE/REJECT | {Brief finding} |
## Issues Requiring Attention
| # | Severity | Source | Location | Issue |
|---|----------|--------|----------|-------|
| 1 | High | Security | `file:line` | Description |
## Improvement Suggestions
- {Consolidated suggestions from all reviews}
```
- name: pr-comment
edit: false
persona: pr-commenter
allowed_tools:
- Read
- Glob
- Grep
- Bash
rules:
- condition: Comments posted
next: COMPLETE
- condition: Failed to post comments
next: COMPLETE
instruction_template: |
## Review Summary
{previous_response}
Post the review results to the PR as comments.
**Procedure:**
1. Extract the PR number from the task description
2. Read all review reports in the Report Directory:
- `01-architect-review.md` (Architecture review)
- `02-security-review.md` (Security review)
- `03-ai-review.md` (AI antipattern review)
- `04-review-summary.md` (Consolidated summary)
3. Filter findings by severity and post inline comments for Critical/High/Medium
4. Post a summary comment with the following format:
```
## Automated Review Summary
{Overall verdict and summary from 04-review-summary.md}
### Review Results
| Review | Result |
|--------|--------|
| Architecture | {result} |
| Security | {result} |
| AI Antipattern | {result} |
### Key Findings
{Bulleted list of important findings}
### Improvement Suggestions
{Consolidated suggestions}
---
*Generated by [takt](https://github.com/toruticas/takt) review-only piece*
```