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

Local PR Review

by windmill-labs in windmill-labs/windmill

Runs the same code review locally that GitHub's auto-review actions run on a PR, delegating to a fresh-context subagent so the review isn't biased by the main session's own reasoning.

Custom licenceAuto-check passedDevelopment

Install Local PR Review

skills CLI
$ npx skills add windmill-labs/windmill --skill local-review -a claude-code

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

GitHub CLI
$ gh skill install windmill-labs/windmill local-review --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/windmill-labs/windmill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/local-review .claude/skills/local-review && 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
local-review
GitHub stars
18k
Token cost
~995 tokens
SKILL.md length
349 words
Files
1
Skills in repo
42
Repo updated
First seen
Licence
Custom licence

At a glance

Runs the same code review locally that GitHub's auto-review actions run on a PR, delegating to a fresh-context subagent so the review isn't biased by the main session's own reasoning.

  • Works in 4 steps: Determine the PR scope (cheap, do this… → Delegate the review to a fresh-context… → Receive the findings from the subagent… → …
  • Reviewing the current PR or branch diff before merging
  • SKILL.md covers Steps, Subagent prompt template, Output format and Posting comments (--comment)
  • Calls gh and git

What it does

The skill explains why a subagent is required: if the user has been iterating on a diff, the main session has absorbed their reasoning and rationalizations and will anchor on it, missing what a cold-context reviewer like CI would catch. It first determines the PR or branch cheaply in the main session, from an argument or by comparing the current branch to main, then delegates the review to a fresh subagent with a self-contained prompt naming the PR, pointing it to read the review policy and the AGENTS.md files in touched directories, specifying the output format, and carrying any comment flag or extra reviewer instructions the user gave.

In Claude Code it uses a dedicated read-only subagent type for this, falling back to a general-purpose one if that is unavailable; for other CLIs it uses whatever fresh-session mechanism they expose, or tells the user to run the skill in a fresh session rather than defeat the purpose by running inline. Findings come back and are relayed to the user verbatim, without re-summarizing or filtering, and posting them as PR comments is done by the main session since the subagent itself is read-only.

When your agent uses it

  • Reviewing the current PR or branch diff before merging
  • Running a cold-context review after iterating on a diff yourself
  • Posting review findings as PR comments

Example prompts

  • “Run the local review on this branch against main before I open the PR.”
  • “Review this PR and post the findings as comments.”
  • “Give me a fresh-context review of my diff, I've been staring at it too long.”

Requirements

  • The gh CLI
  • A REVIEW.md policy file in the repository

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Determine the PR scope (cheap, do this in the main session)
  2. Delegate the review to a fresh-context subagent with a self-contained prompt. The prompt MUST include
  3. Receive the findings from the subagent and relay them to the user verbatim. Do not re-summarize, re-judge, or filter — the whole point of…
  4. Post comments if --comment was requested: use the gh commands below with the subagent's output as the body. The main session does the…

What it can do on your machine

Read from SKILL.md and the folder at commit fb22e5c. 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

    Shell commands in SKILL.md call:

    • gh
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    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

Local PR Review loads about 995 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~995

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 349 words (~995 tokens).

“Run the same review locally that the GitHub auto-review actions run on PRs (Claude / Codex / Pi). The review policy lives in REVIEW.md.”

— opening of SKILL.md by windmill-labs, Custom licence
name
local-review

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/local-review of windmill-labs/windmill.

Open the folder on GitHubat commit fb22e5c

Compare with similar skills

Local PR Review 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.

Local PR Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local PR Review this skillwindmill-labs/windmill18k—~995Automated safety check: PassCustom licence
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
Cherry Studio PR ReviewCherryHQ/cherry-studio52k—~3.9kAutomated safety check: PassAGPL-3.0
PR Reviewjaemk/self_update961—~1.5kAutomated safety check: NotesMIT
Zen Comprehensive ReviewEliasOulkadi/shokunin114—~4kAutomated safety check: PassMIT
PR Reviewjaemk/cached2.1k—~2.5kAutomated safety check: NotesMIT

Similar skills

  • GitHub Review Iteration

    prisma/orm

    Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

  • Cherry Studio PR Review

    CherryHQ/cherry-studio

    Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.

    52k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed

  • PR Review

    jaemk/self_update

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.

    961 GitHub stars~1.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

  • Zen Comprehensive Review

    EliasOulkadi/shokunin

    Orchestrate a multi-model code review: spawn 3 review subagents, merge findings.

    114 GitHub stars~4k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • PR Review

    jaemk/cached

    Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/cached.

    2.1k GitHub stars~2.5k tokensUpdated 8 days ago
    DevelopmentAuto-check: notes

More from windmill-labs/windmill

All 42 skills in this repo

  • Windmill Trigger Type Checklist

    windmill-labs/windmill

    Checklist of every backend, frontend, CLI and capture change needed to add a new TriggerCrud-based trigger type, such as Azure, GCP or Kafka, to Windmill.

    18k GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • Windmill AI Evals

    windmill-labs/windmill

    Writes and runs black-box benchmark cases for Windmill's flow, app, script, CLI and global AI generation modes, including before-and-after comparisons.

    18k GitHub stars~969 tokensUpdated today
    Auto-check: notes

  • Domain Modeling and Glossary

    windmill-labs/windmill

    Actively challenges vague or conflicting terminology as you design, and keeps a living domain glossary file up to date in real time.

    18k GitHub stars~622 tokensUpdated today
    Auto-check passed

  • Draft PR with CI Rounds

    windmill-labs/windmill

    Opens a draft GitHub pull request with a conventional title and explicit body, then drives CI review rounds before marking it ready.

    18k GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Windmill Dev Page Preview

    windmill-labs/windmill

    Opens the Windmill dev page to preview a flow, script or app, choosing between proxy and direct mode and deciding whether the agent or the runtime starts the wmill dev server.

    18k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Windmill Rust Backend Patterns

    windmill-labs/windmill

    Sets Rust conventions for the Windmill backend: error types, SQLx queries, JSON handling, async rules, module layout and rust-analyzer navigation.

    18k GitHub stars~869 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Local PR Review

What does Local PR Review do?

Runs the same code review locally that GitHub's auto-review actions run on a PR, delegating to a fresh-context subagent so the review isn't biased by the main session's own reasoning. The skill explains why a subagent is required: if the user has been iterating on a diff, the main session has absorbed their reasoning and rationalizations and will anchor on it, missing what a cold-context reviewer like CI would catch.md files in touched directories, specifying the output format, and carrying any comment flag or extra reviewer instructions the user gave.

When should I use Local PR Review?

Local PR Review fits situations like: reviewing the current PR or branch diff before merging; running a cold-context review after iterating on a diff yourself; posting review findings as PR comments.

How do I install Local PR Review in Claude Code?

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

How do I install Local PR Review in Codex?

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

Can I use Local PR Review 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 windmill-labs/windmill --skill local-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-review, .gemini/skills/local-review, .github/skills/local-review and .opencode/skills/local-review in your project.

What does Local PR Review need to run?

Going by SKILL.md and its folder, Local PR Review needs the command-line tools its instructions call (gh and git). Our summary lists: The gh CLI; A REVIEW.md policy file in the repository.

Does Local PR Review access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Local PR Review 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 Local PR Review use?

Local PR Review has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Local PR Review use?

About 995 tokens (SKILL.md is roughly 4k 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 Local PR Review?

Skills that share tags, products or a category with Local PR Review: GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 52k stars), PR Review (jaemk/self_update, 961 stars) and Zen Comprehensive Review (EliasOulkadi/shokunin, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local PR Review?

windmill-labs (a GitHub organization) maintains it in windmill-labs/windmill, which has 18,146 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on October 9, 2026.

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