New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Review Contributor PR

by foldkit in foldkit/foldkit

Review, discuss, or finish a Foldkit pull request opened by an external contributor.

MITAuto-check passedDevelopment

Install Review Contributor PR

skills CLI
$ npx skills add foldkit/foldkit --skill review-contributor-pr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install foldkit/foldkit review-contributor-pr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/foldkit/foldkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/review-contributor-pr .claude/skills/review-contributor-pr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
review-contributor-pr
GitHub stars
918
Token cost
~1.1k tokens
SKILL.md length
580 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

Review, discuss, or finish a Foldkit pull request opened by an external contributor.

  • Merge-readiness checks
  • SKILL.md covers Understand the contribution, Review the full change, Decide between feedback and… and Finish the branch
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Pending review discussions

What it does

Review Contributor PR is an agent skill from foldkit/foldkit. Review, discuss, or finish a Foldkit pull request opened by an external contributor. Use for merge-readiness checks, pending review discussions, contributor feedback, PR prioritization, and taking an accepted contribution across the finish line.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests and Prioritization frameworks. The licence is MIT.

When your agent uses it

  • Merge-readiness checks
  • Pending review discussions
  • Contributor feedback
  • PR prioritization

Example prompts

  • “/review-contributor-pr”

What it can do on your machine

Read from SKILL.md and the folder at commit d21db42. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Contributor PR loads about 1.1k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 580 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from foldkit/foldkit at commit d21db42, republished under its MIT licence (© foldkit). 580 words, ~1,067 tokens.

Download SKILL.mdSave it as .claude/skills/review-contributor-pr/SKILL.md (or your agent's skills folder).
name
review-contributor-pr
description
Review, discuss, or finish a Foldkit pull request opened by an external contributor. Use for merge-readiness checks, pending review discussions, contributor feedback, PR prioritization, and taking an accepted contribution across the finish line.

Review Contributor PR

Review the contribution at Foldkit's framework quality bar. Separate design decisions that need contributor input from bounded finishing work a maintainer can complete.

Understand the contribution

Inspect the pull request, linked issue, full diff against its base, commits, reviews, pending comments, checks, and relevant surrounding code. Explain in plain language:

  • What changes for a Foldkit consumer.
  • Whether the behavior belongs in Foldkit.
  • The main benefit, tradeoffs, and compatibility risk.
  • Whether the pull request is a draft, needs contributor feedback, or is ready for maintainer finishing work.

When choosing among pull requests, prefer the oldest non-draft contribution by default. Override that order for dependencies, regressions, or substantially higher framework value.

Review the full change

Start with architecture and correctness. Then audit the entire diff for API design, state modeling, naming, factoring, Effect and Foldkit conventions, tests, comments, prose, changesets, documentation, examples, and public metadata.

  • Search for the whole defect class after finding one instance.
  • Read test names, fixture names, comments, TSDoc, changeset text, and user-facing copy as prose.
  • Apply the repository conventions relevant to the changed subsystem. Do not turn concerns from an unrelated component into review requirements.
  • Put tests in the suite owned by the behavior or abstraction under test.
  • For UI changes, inspect both the website and UI showcase when they expose the component. Exercise the browser behavior changed by the diff, including opt-out or disabled behavior and representative dynamic states when relevant.

Do not expand a focused contribution into a repository-wide migration or a new testing framework. Open a follow-up issue for worthwhile adjacent work.

Decide between feedback and finishing

Leave contributor feedback when the design is unresolved, the intended behavior is unclear, or the remaining work would materially change the contribution. State the important missing pieces first, then perform a targeted second review after they are addressed.

Take the pull request across the finish line when its direction is accepted and the remaining work is bounded cleanup, tests, documentation, rebasing, or pull request metadata. Do not make the contributor wait through another review cycle for changes a maintainer can finish safely.

If the user says pending review comments are for discussion, discuss them before editing. Use a comment-only GitHub review unless the user explicitly asks to approve or request changes. When the user will post comments, provide links to the exact current diff lines and drafts in their voice.

Show full SKILL.md (185 more words)Show less

Finish the branch

Use an isolated checkout when the current workspace belongs to different work. Preserve the contributor's commits and prefer separate maintainer cleanup commits. Rewrite contributor commits or force-push only when rebasing or another explicit need requires it.

Follow the commit skill for local commits. A request to push with --no-verify skips the Git hook, not explicit verification. Keep broad follow-up work out of the branch.

Before declaring the pull request merge-ready:

  • Re-read the full diff against the current base.
  • Confirm the changeset covers every changed published package and describes the actual consumer impact.
  • Run checks proportionate to the change, including visual verification for UI work.
  • Rebase when needed and resolve the result against current conventions, not merely for textual compatibility.
  • Audit the title as a Conventional Commit subject and the description as the squash commit body.
  • Read the remote title, description, and head commit back after updating or pushing.
  • Wait for required CI checks to pass.

Do not merge for the user unless they explicitly ask. Report remaining blockers precisely, or say that the pull request is ready to queue when none remain.

© foldkit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/review-contributor-pr of foldkit/foldkit.

Open the folder on GitHubat commit d21db42

Compare with similar skills

Review Contributor PR next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Review Contributor PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Contributor PR this skillfoldkit/foldkit918—~1.1kAutomated safety check: PassMIT
Run Nx Generatornrwl/nx29k2 repos~592Automated safety check: NotesMIT
LoopX PR Program Managerloopx-project/loopx6.2k—~1.9kAutomated safety check: PassApache-2.0
Dough Landterryyin/lizard2.5k—~3.8kAutomated safety check: PassCustom licence
Bug TriageDonchitos/Claude-Code-Game-Studios26k—~2.3kAutomated safety check: PassMIT
PR Status Triagevercel/next.js143k—~866Automated safety check: PassMIT

Similar skills

  • Run Nx Generator

    nrwl/nx

    Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes

  • LoopX PR Program Manager

    loopx-project/loopx

    Tracks a group of pull or merge requests across repositories as durable LoopX state: inventory, reconcile changes, keep priorities and a roadmap, and monitor over time.

    6.2k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Dough Land

    terryyin/lizard

    Dough Land lands everything in one reviewed checkout on the authorized remote trunk: commits all of its changes, reconciles and publishes them without force, and refreshes a supplied default…

    2.5k GitHub stars~3.8k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Bug Triage

    Donchitos/Claude-Code-Game-Studios

    Reviews the open bug backlog, separates severity from priority, assigns fixes to sprints and reports systemic trends, writing a dated triage file.

    26k GitHub stars~2.3k tokensUpdated 9 days ago
    DevelopmentAuto-check passed

  • PR Status Triage

    vercel/next.js

    Official

    Triage CI failures and PR review comments using scripts/pr-status.js.

    143k GitHub stars~866 tokensUpdated today
    Testing & QAAuto-check passed

  • Shift Issue Writer

    shift-editor/shift

    Sets the rules for finding, writing and updating Shift GitHub issues: search for duplicates first, use outcome-focused titles and testable acceptance criteria.

    347 GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed

More from foldkit/foldkit

All 18 skills in this repo

  • Commit Changes

    foldkit/foldkit

    Create a git commit in the Foldkit monorepo with changeset enforcement and formatting.

    918 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Foldkit

    foldkit/foldkit

    A skill your agent uses whenever working with Foldkit. An agent skill from foldkit/foldkit.

    918 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Write Release Blog Post

    foldkit/foldkit

    Outline, draft, or revise a Foldkit version release blog post using the repository's announcement style and editorial preferences.

    918 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Audit Program

    foldkit/foldkit

    Audit an existing Foldkit program against the architecture, conventions, and quality bar.

    918 GitHub stars~7.2k tokensUpdated today
    Auto-check passed

  • Generate Program

    foldkit/foldkit

    Generate a complete, idiomatic Foldkit program from a natural language description.

    918 GitHub stars~20k tokensUpdated today
    Auto-check passed

  • Changesets

    foldkit/foldkit

    Concise PR finalization changesets. An agent skill from foldkit/foldkit.

    918 GitHub stars~923 tokensUpdated today
    Auto-check passed

Categories

Questions about Review Contributor PR

What does Review Contributor PR do?

Review, discuss, or finish a Foldkit pull request opened by an external contributor. Review Contributor PR is an agent skill from foldkit/foldkit. Review, discuss, or finish a Foldkit pull request opened by an external contributor.

When should I use Review Contributor PR?

Review Contributor PR fits situations like: merge-readiness checks; pending review discussions; contributor feedback; PR prioritization.

How do I install Review Contributor PR in Claude Code?

Run `npx skills add foldkit/foldkit --skill review-contributor-pr -a claude-code`. Or copy the skill folder (.agents/skills/review-contributor-pr in foldkit/foldkit) into .claude/skills/review-contributor-pr in your project. Claude Code loads it when a task matches its description.

How do I install Review Contributor PR in Codex?

Run `npx skills add foldkit/foldkit --skill review-contributor-pr -a codex`. Or copy the skill folder (.agents/skills/review-contributor-pr in foldkit/foldkit) into .agents/skills/review-contributor-pr in your project. Codex loads it when a task matches its description.

Can I use Review Contributor PR in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add foldkit/foldkit --skill review-contributor-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-contributor-pr, .gemini/skills/review-contributor-pr, .github/skills/review-contributor-pr and .opencode/skills/review-contributor-pr in your project.

What does Review Contributor PR need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Contributor PR is instructions for the agent only.

Does Review Contributor PR access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review Contributor PR safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Review Contributor PR use?

Review Contributor PR is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Contributor PR use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review Contributor PR?

Skills that share tags, products or a category with Review Contributor PR: Run Nx Generator (nrwl/nx, 29k stars), LoopX PR Program Manager (loopx-project/loopx, 6.2k stars), Dough Land (terryyin/lizard, 2.5k stars) and Bug Triage (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Contributor PR?

foldkit (a GitHub organization) maintains it in foldkit/foldkit, which has 918 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 8, 2026.

Source: foldkit/foldkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.