Skip to main content
ClaudeWave
EN, English
Skill288 repo starsupdated 7d ago

contributor

# ClaudeWave: Contributor Skill The contributor skill automates the open source contribution workflow from repository discovery through pull request submission. Use it when users want to contribute to open source projects, find issues to address, submit pull requests, or ask for help with GitHub-based contributions. This skill systematically prevents common contribution failures by conducting reconnaissance before writing code, including scanning for available issues, checking for competing PRs, deep-reading issue comments to understand maintainer preferences, and verifying whether fixes should target upstream dependencies instead.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/majiayu000/spellbook /tmp/contributor && cp -r /tmp/contributor/skills/contributor ~/.claude/skills/contributor
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Contributor

Automated open source contribution workflow that takes you from a GitHub repo URL to merged PRs, with built-in safeguards against common contribution failures.

## Why this skill exists

Open source contributions fail for predictable reasons: fixing in the wrong layer (your PR gets closed because the maintainer preferred an upstream fix), colliding with other contributors, not following project conventions, or over-engineering a simple fix. This workflow prevents each of those failures through systematic pre-checks.

## Phase 1: Reconnaissance

Before writing any code, gather intelligence about the project and its contribution landscape.

### 1.1 Identify the target

Ask the user for:
- The GitHub repo URL (e.g., `pydantic/pydantic-ai`)
- Their GitHub username and email for commits
- Any specific issue they want to work on (or ask to scan for available ones)

### 1.2 Scan for available issues

Use `gh` CLI to find issues worth contributing to:

```bash
# Get open issues with metadata
gh issue list -R <owner>/<repo> --state open --limit 50 \
  --json number,title,labels,assignees,comments

# Check for competing PRs on each candidate
gh pr list -R <owner>/<repo> --state open \
  --search "<issue_number> in:title,body"
```

**Filter criteria** (apply in order):
1. No assignee
2. No open PR already fixing it (check both linked PRs and title/body search)
3. Fewer than 5 competing PRs
4. Prefer labels: `bug`, `good first issue`, `help wanted`
5. Prefer issues with maintainer comments suggesting a fix direction

### 1.3 Deep-read issue comments

For each candidate issue, read the full comment thread:

```bash
gh issue view <number> -R <owner>/<repo> --json body,comments
```

Extract:
- **Maintainer fix direction**: Do they prefer fixing here or in an upstream dependency?
- **Suggested approach**: Any code pointers, file references, or architectural guidance?
- **Blockers**: Is this waiting on another PR or release?
- **Who's working on it**: Even without assignment, someone might have commented "I'll take this"

### 1.4 Check for upstream redirection

This is the single most common failure mode. Before committing to any fix:

```bash
# Check if maintainers reference another repo
gh issue view <number> -R <owner>/<repo> --json comments \
  | grep -i "upstream\|genai-prices\|separate repo\|other repo"

# Check related repos for recent PRs mentioning this issue
gh pr list -R <owner>/<related-repo> --state open --limit 10 \
  --json title,body | grep -i "<issue_number>\|<issue_keywords>"
```

If there's any signal the fix belongs elsewhere, stop and ask the user before proceeding.

## Phase 2: Pre-communication

Never submit a PR cold. Always communicate your intent first.

### 2.1 Post a solution outline on the issue

Before writing code, leave a comment on the issue with your proposed approach. This serves two purposes: it claims the work (politely), and it gives maintainers a chance to redirect you before you waste effort.

**Template:**
```
Hi, I've been looking into this and traced the root cause to <X>.

Before I open a PR, I wanted to confirm the preferred approach:
A) <approach A — e.g., fix in this repo by modifying X>
B) <approach B — e.g., upstream fix in related-repo>

I can implement either direction. Happy to adjust based on your preference.
```

Wait for maintainer response before proceeding to code. If no response after 24-48 hours on an active project, proceed with the most conservative approach (smallest scope fix in the current repo).

### 2.2 Draft PR strategy

Plan to open as a Draft PR first. Convert to ready-for-review only after:
- CI passes
- Maintainer acknowledges the approach (via issue comment or PR review)

## Phase 3: Repository Setup

### 3.1 Fork and clone

```bash
gh repo fork <owner>/<repo> --clone --remote
cd <repo>
```

### 3.2 Determine the development branch

Don't assume `main`. Check what recent merged PRs target:

```bash
gh pr list -R <owner>/<repo> --state merged --limit 10 \
  --json baseRefName,mergedAt
```

Use the most common `baseRefName` from recent merges.

### 3.3 Read contribution guidelines

Check these files in order (read whichever exist):

```
CONTRIBUTING.md
.github/CONTRIBUTING.md
.github/PULL_REQUEST_TEMPLATE.md
.github/PULL_REQUEST_TEMPLATE/
```

Extract:
- Required commit message format
- Test requirements
- Pre-commit hooks or linting requirements
- DCO/CLA requirements
- Branch naming conventions

### 3.4 Understand CI

```bash
ls .github/workflows/
```

Read the CI config to know what checks will run on your PR. Identify the commands for:
- Linting / formatting
- Type checking
- Unit tests
- Integration tests
- Pre-commit hooks

### 3.5 Set up the environment

Follow the project's documented setup process. Run the full test suite once to establish a passing baseline before making any changes.

## Phase 4: Code Fix

### 4.1 Branch per issue

```bash
git checkout -b fix/issue-<number>-<short-desc> <base-branch>
```

### 4.2 Implementation principles

- **Adopt the maintainer's suggested approach** if one exists in the issue comments
- **Minimal fix**: change only what's necessary to fix the issue. Don't refactor surrounding code, add features, or "improve" things along the way
- **Match project style**: follow the existing code patterns, naming conventions, and architecture
- **No hardcoding**: avoid hardcoded values unless the project already uses them in the same context
- **Add tests**: every fix needs a corresponding test that would have caught the bug. Follow the project's existing test patterns

### 4.3 Test your changes

Run the project's test suite. All existing tests must pass. Your new test must also pass. If the project has type checking or linting, run those too.

Language-specific verification:
- **Python**: `pytest`, `mypy`, `ruff` (or whatever the project uses)
- **TypeScript**: `npx tsc --noEmit`, project test command
- **Rust**: `cargo check && cargo test`
- **Go**: `go build ./... && go test ./...`

##
agentsmd-optimizeSkill

Audit AND optimize a CLAUDE.md / AGENTS.md instruction file — score it against the five high-leverage patterns, flag anti-patterns, then apply approved fixes in place. Use when the user says 优化 CLAUDE.md / 优化 AGENTS.md / optimize my agent doc / 帮我改 claudemd, or after an audit when they want the fixes applied (not just reported).

agentsmd-scaffoldSkill

Generate or update repository-specific AGENTS.md instruction files from real repo evidence. Use when asked to create, design, scaffold, split, or improve root or scoped AGENTS.md files for Codex/Claude/agent workflows, especially when a repo needs directory-specific rules, validation commands, generated-file boundaries, or a short agent onboarding router.

api-designSkill

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

app-ui-designSkill

Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.

app-user-story-qaSkill

End-to-end app feature inventory and user-story testing workflow with a canonical tracker. Use when the user asks to audit every feature, derive expected behavior from code, test user journeys, or explicitly fix and retest documented UX or logistical defects.

architecture-foundationSkill

Design architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust/Go crate, package, module, runtime, workflow, or service boundaries, compare mature project architecture, prevent stacked one-off PRs, audit migration debt in existing repos, or produce a spec before coding.

architecture-researchSkill

Evidence-driven architecture research for understanding real systems and making technical decisions. Use when doing architecture landscape studies, source-backed system archaeology, build-vs-buy or adopt/adapt/build decisions, open-source and commercial comparisons, revisiting an earlier architecture choice, or handling requests such as 架构调研, 架构选型, 竞品架构, 技术尽调, 同类方案, 开源替代, how is X built, and what should we learn from X. Do not use for small mechanical changes, market-only discovery, or detailed design after the technology direction is already fixed.

ask-opencliSkill

Ask Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask grok", "ask gemini", "用 grok 查", "grok 怎么看", "让 gemini 分析", or wants a second opinion from Grok/Gemini without paying API tokens. Routes to opencli which drives the already-logged-in Chrome session.