CLAUDE.md
CLAUDE.mdCLAUDE.mdroot
Quality
79/100
Scores the file, not the repository.Length
353 words
7 headings · 0 code blocksRepository
16
— · pushed 173 days agoLast changed
3 days ago
First indexed 3 days ago.1# CLAUDE.md23This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.45## Common Commands67- **Build**: `pnpm run build` - Compiles TypeScript and packages with ncc8- **Package**: `pnpm run package` - Alias for build command9- **Lint**: `pnpm run lint` - ESLint with TypeScript support, must have 0 warnings10- **Type Check**: `pnpm run type-check` - TypeScript compilation check without output11- **Test**: `pnpm run test` - Runs Jest test suite with full coverage12- **Manual Review**: `pnpm run review` - Runs ts-node on ai-review.ts for local testing1314## Architecture Overview1516This is a **GitHub Action** that provides AI-powered code review for Pull Requests using multiple LLM providers (OpenAI, Anthropic, Google Gemini).1718### Core Components1920- **`src/index.ts`**: GitHub Action entry point that validates inputs, generates git diffs, and delegates to ai-review.ts21- **`src/ai-review.ts`**: Main review engine with hunk-based diff processing, LLM integration via Vercel AI SDK, and GitHub API comment posting22- **`src/system-prompt.ts`**: Configurable system prompt builder with default code review guidelines and XML response format enforcement23- **`types.ts`**: Type definitions for Finding objects (path, line, message, severity, suggestion, code)2425### Key Architecture Patterns2627- **Provider Agnostic**: Uses Vercel AI SDK (`ai` package) for unified LLM access across OpenAI, Anthropic, and Google28- **Hunk-Based Processing**: Splits diffs into individual hunks rather than arbitrary size limits for focused reviews29- **Structured XML Output**: Enforces consistent XML response format with severity levels (required, optional, nit, fyi)30- **Line Resolution**: Maps XML findings to actual GitHub line numbers through diff parsing31- **Retry Logic**: Built-in exponential backoff for LLM API failures32- **Custom Prompts**: Supports custom review prompts while preserving XML response format3334### Environment Variables3536The action expects these environment variables (set automatically by GitHub Actions):37- `GITHUB_TOKEN`: GitHub API access38- `MODEL_PROVIDER`: "openai", "anthropic", or "gemini"39- `MODEL_NAME`: Specific model (e.g., "gpt-4o", "claude-3-sonnet-20240229")40- `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`: Provider-specific keys41- `CUSTOM_PROMPT`: Optional custom review prompt42- `GITHUB_REPOSITORY`: Owner/repo format4344### TypeScript Configuration4546- Target ES2020 with CommonJS modules for Node.js 20+ compatibility47- Strict typing enabled with declaration files48- Uses `@vercel/ncc` for single-file bundling in `dist/index.js`
Also in quantfive/codepress-review
Diff this repo’s formatsOne repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| quantfive/codepress-review.cursor/rules/prompt-writing-rules.mdc · 16 | Cursor rules | no sections | 4/100 | 3 days ago |
Similar configs
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| Adit-Jain-srm/NightmareNetCLAUDE.md · 45 | CLAUDE.md | buildtestlint-formatstyle+6 | 100/100 | 3 days ago | |
| dotCMS/corecore-web/CLAUDE.md · 949 | CLAUDE.md | teststylearchtesting-strategy+3 | 100/100 | 3 days ago | |
| nimbalyst/nimbalystpackages/android/CLAUDE.md · 1.4k | CLAUDE.md | setupbuildstylearch+2 | 100/100 | 3 days ago | |
| microsoft/playwrightCLAUDE.md · 94k | CLAUDE.md | buildtestlint-formatstyle+7 | 100/100 | 3 days ago | |
| dotCMS/coreCLAUDE.md · 949 | CLAUDE.md | setupbuildteststyle+7 | 99/100 | today | |
| lollipopkit/flutter_server_boxCLAUDE.md · 8.3k | CLAUDE.md | buildteststylearch+2 | 98/100 | 3 days ago | |
| caliber-ai-org/ai-setupCLAUDE.md · 1.2k | CLAUDE.md | buildtestlint-formatstyle+1 | 97/100 | 3 days ago | |
| khrnchn/sedekah-jeCLAUDE.md · 89 | CLAUDE.md | testlint-formatstylearch+6 | 97/100 | 3 days ago |
