agentleFS
Sign inStart free
NYTC69NYTC69/review-loop/skills/review-pr/SKILL.md

review-pr

Skill3 starsChanged 6 months agoApache-2.0View on GitHub

Comprehensive code review using specialized agents. Each agent focuses on a different quality aspect (code, errors, comments, types, tests). It runs the paired-session report mode (a PR, a ref or the local change; no writer, nothing posted). Use when the user asks for a review report on a pull request, a branch, a ref or the local change ('review PR 123', a PR URL, 'review this branch against main', 'give me a review report of my diff') or names review-pr. Not for fixing the findings (use code-quality-loop) or implementing a work item (use review-loop).

186 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use diagnose-ci-failures, docs-loop and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • zerx-labSkill

    diagnose-ci-failures

    Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.

    Also in 3 projects that use this

  • GeiserXSkill

    docs-loop

    Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.

    Also in 3 projects that use this

  • GeiserXSkill

    full-loop

    Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.

    Also in 3 projects that use this

  • n24q02mSkill

    review-delta

    Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

    Also in 3 projects that use this

  • n24q02mSkill

    build-graph

    Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.

    Also in 3 projects that use this

  • +7 more from GeiserX

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a comprehensive code review using multiple specialized agents, each focusing on a different aspect of code quality, as a paired-session …

    line 9
  2. Very specific:

    If the paired-session skill reports stage A failure: <reason>, report review-pr: paired-session entry refused (<reason>) and stop (nothing …

    line 36

“Common” is measured: kept by at least 6 in 10 of the 179 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Comprehensive Code Review

Run a comprehensive code review using multiple specialized agents, each focusing on a different aspect of code quality, as a paired-session report mode run (Step 0).

A repository with submodules cannot be reviewed in report mode yet.

Review Aspects (optional): "$ARGUMENTS"

Step 0 — Entry: paired route (the legacy workflow was removed in v2.13.0)

Resolve entry in .review-loop/config.md (exact values legacy and paired-session): legacy is refused with review-pr: the legacy workflow was removed in v2.13.0; remove "entry: legacy" from .review-loop/config.md (paired-session is the only entry); an invalid value prints review-pr: entry "<v>" is not valid (paired-session is the only entry); using paired-session, a duplicate key or an unreadable config prints review-pr: entry could not be read (<reason>); using paired-session, and both continue as absent. Then:

  • --legacy in $ARGUMENTS: refused with review-pr: the legacy workflow was removed in v2.13.0; run /review-loop:review-pr without --legacy (report mode).
  • A host that is neither macOS (uname -s is Darwin) nor native Windows (Git Bash: uname -s starts with MINGW64_NT- or MSYS_NT-): refused with review-pr: paired-session needs macOS or native Windows; Linux (WSL included) and other hosts are not supported.
  • Otherwise the paired route. Print review-pr: paired-session report mode (entry set in .review-loop/config.md) when the key is set, or review-pr: paired-session report mode (the default entry) when it is absent. Invoke the paired-session skill with --review-pr and the remaining arguments (input and aspects), and end this skill. It follows the shared contract's Review-PR entry: a PR or ref is reviewed in a temporary clone, no tests run unless you confirm a test command, the result is review-report.md, and nothing is posted unless you ask.
    • simplify is refused there before any coordinator command, with the pointer run /review-loop:code-quality-loop on the change (its POLISH-Q simplifier).
    • If the paired-session skill reports stage A failure: <reason>, report review-pr: paired-session entry refused (<reason>) and stop (nothing falls back).

Usage Examples

Default route (paired-session report mode; entry absent or paired-session, see Step 0):

/review-loop:review-pr 123
# Reviews PR #123 of this repository in a temporary clone; writes review-report.md, posts nothing

/review-loop:review-pr https://github.com/owner/repo/pull/123 code tests
# Only the code and tests specialists (the reviewer, shadow, gate and security stage always run)

Agent Descriptions

code-reviewer:

  • Checks CLAUDE.md / project guideline compliance
  • Detects bugs, logic errors, and anti-patterns
  • Reviews general code quality and style

silent-failure-hunter:

  • Finds silent failures and swallowed errors
  • Reviews catch blocks and error propagation
  • Checks error logging adequacy

comment-analyzer:

  • Verifies comment accuracy vs actual code
  • Identifies comment rot and stale docs
  • Checks documentation completeness

type-design-analyzer:

  • Analyzes type encapsulation and invariants
  • Reviews type design quality
  • Rates invariant expression strength

pr-test-analyzer:

  • Reviews behavioral test coverage
  • Identifies critical test gaps
  • Evaluates test quality and assertions

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free