AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

GitHub Contributor

A phase-based playbook for shipping pull requests that maintainers of third-party repos actually merge.

Dev & CodingIntermediate★ 1,323⑂ 212AI score 9/10Last updated: Aug 8, 2026

What it does

Breaks the PR lifecycle into five phases, each targeting a distinct failure mode:

  • Phase 1 – Discovery: treat CONTRIBUTING.md as a hard contract, benchmark your diff against recently merged PRs with gh pr list, and write a scope contract before coding
  • Phase 2 – Implementation: branch from upstream main, smallest-possible diff, Conventional Commits, --fixup + autosquash workflow
  • Phase 3 – Quality gates: run the project's exact lint/test commands, isolate the data directory before real E2E runs on Tauri/Electron apps, self-audit every "I tested…" claim, verify mergeability before declaring ready
  • Phase 4 – PR description: body skeleton (Summary / Why / Test Plan / Backward Compatibility / Screenshots), test-coverage matrix, AI-assisted disclosure template, screenshot handling without polluting the repo
  • Phase 5 – Post-submission: reply inline to bot reviews via gh api in_reply_to, rebase with --force-with-lease, filter counter-review findings by probability/cost/scenario

Closes with 10 anti-patterns that get PRs shut down and concrete quality metrics (1–5 files, <200 lines of production code, <24h response time).

Who it's for

  • Developers making their first contributions to unfamiliar OSS repos
  • Anyone using AI assistance who needs to disclose it credibly
  • Teams standardizing bot-review responses and rebase hygiene

Examples

  1. "Open a PR upstream for this fix" → parse CONTRIBUTING.md → compare size to merged baseline → minimal commits → PR body with real test evidence
  2. "Respond to the CodeRabbit review" → filter findings, then reply on each line citing the fixing commit and test
  3. "Rebase my branch against main" → fetch, resolve file-by-file, autosquash fixups, push with --force-with-lease so review threads survive

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/github-contributor/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the github-contributor folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/github-contributor/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git /tmp/ccs && mkdir -p ~/.claude/skills && cp -r /tmp/ccs/github-contributor ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm git --version and gh --version work. Install GitHub CLI if needed (brew install gh or your OS package manager) and authenticate with gh auth login.
  2. Clone the repo to a temp folder: git clone https://github.com/daymade/claude-code-skills.git /tmp/ccs
  3. Create your skills directory: mkdir -p ~/.claude/skills
  4. Copy the whole skill folder, including references/: cp -r /tmp/ccs/github-contributor ~/.claude/skills/
  5. Verify with ls ~/.claude/skills/github-contributor — you should see SKILL.md plus a references/ directory.
  6. Restart Claude Code and try a prompt like "submit a PR to owner/repo" to trigger the skill.
View source on GitHub ↗License: MIT