菜单
Extract and generate coding best practices from PR review comments. Use when the user asks to "extract best practices", "analyze PR comments", "generate coding standards", "create best practices from PRs", or "update coding guidelines from reviews".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use this skill when controlling agent behavior in TypeScript Agent SDK platforms — restricting allowed tools, setting budget and turn limits, crafting system prompts that guide agents to specific behaviors, implementing the file pre-creation pattern, augmenting prompts with runtime context, building message loggers, or tracking agent run metadata (cost, duration, iterations).
Use this skill when implementing TypeScript hook callbacks for the Claude Agent SDK — creating PreToolUse hooks to allow/deny tool calls, PostToolUse hooks to inject additionalContext, building factory functions for parameterized hooks, using HookCallback and HookJSONOutput types, applying isPreToolUseInput and isPostToolUseInput type guards, or designing a hooks strategy for an Agent SDK platform. Hooks in the TypeScript SDK are async functions, NOT JSON config files.
Use this skill when developing TypeScript applications with the Claude Agent SDK (@anthropic-ai/claude-agent-sdk), implementing query() calls, configuring SDK options, handling streaming message iteration, working with SDKMessage and SDKResultMessage types, managing AbortSignal, passing custom env variables, or setting up the single-point-of-contact types file for SDK imports.
基于 SOC 职业分类
| name | best-practices-extractor |
| description | Extract and generate coding best practices from PR review comments. Use when the user asks to "extract best practices", "analyze PR comments", "generate coding standards", "create best practices from PRs", or "update coding guidelines from reviews". |
| version | 1.0.0 |
Extract coding best practices from PR review comments and codebase analysis to generate .claude/best-practices/ documentation.
All outputs are saved to .claude/pr-review-comments/.
For regular updates - fast and tracks state:
cd plugin/skills/best-practices-extractor
bash scripts/incremental_update.sh OWNER REPO_NAME
First run does full extraction; subsequent runs fetch only new PRs.
Output: .claude/pr-review-comments/{repo}_inline_comments.ndjson
For first-time setup or comprehensive analysis:
bash scripts/extract_pr_comments.sh REPO_NAME
Output: .claude/pr-review-comments/{repo}_inline_comments.ndjson
Organize extracted comments by directory structure:
bash scripts/sort_comments_by_filetree.sh .claude/pr-review-comments/{repo}_inline_comments.ndjson
Output: .claude/pr-review-comments/sorted/
After extracting comments:
.claude/best-practices/ files.claude/best-practices/
├── README.md # Index
├── naming-conventions.md
├── error-handling.md
├── type-safety.md
├── testing.md
└── ...
Each guideline should include:
## [Number]. [Title]
**Guideline:** [Clear statement]
**Why:** [Impact explanation]
**Example:**
```typescript
// Good
{example}
// Bad
{counter_example}
Source: PR #{number}
## Prerequisites
- **GitHub CLI (`gh`)**: Authenticated - check with `gh auth status`
- **jq**: JSON processor - check with `jq --version`
## Integration
This skill **generates** best practices. The `code-reviewer` agent and `/4_review` command **validate** against them.
Workflow:
1. Extract PR comments (this skill)
2. Analyze and generate `.claude/best-practices/`
3. Reviews automatically validate against best practices
## Additional Resources
- **`references/default-categories.md`** - Example category definitions
- **`references/scripts-guide.md`** - Detailed script documentation