agentleFS
abevzabevz/devops-skills/skills/pr-review/SKILL.md

pr-review

Skill0 starsChanged 41 days agoMITView on GitHub

Use when reviewing a PR or diff with no narrower artifact skill; this is the generic fallback. Mention "review this PR" or "review my diff"; use go-code-review, helm-review, kubernetes-yaml-review, dockerfile-review, or another artifact specialist when that artifact is the focus.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use oss-pr, pr-automation 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.
  • CES-LtdSkill

    oss-pr

    Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.

    Also in 3 projects that use this

  • CES-LtdSkill

    pr-automation

    PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

    Also in 3 projects that use this

  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • jtenniswoodSkill

    updates

    Summarize user-facing project updates from the last 7 days, ordered by importance and written as one-sentence "Feature: description" entries. Use when the user says "/updates", asks what changed recently, or wants a concise list of recent features, device support, fixes that users will notice, or other product value.

    Also in 3 projects that use this

  • openchamberSkill

    clack-cli-patterns

    Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.

    Also in 3 projects that use this

  • openchamberSkill

    drag-to-reorder

    Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.

    Also in 3 projects that use this

  • +6 more from openchamber

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 7

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Do not approve a change based only on a green CI badge.

    line 22
  2. Distinctive:

    Follow the Workflow, Safety rules, and Quality checklist below.

    line 26
  3. Distinctive:

    Use when the user shares a pull request, diff, or branch and asks for a review, or wants a second opinion before merging.

    line 36
  4. Very specific:

    Use go-code-review, helm-review, kubernetes-yaml-review, dockerfile-review, or another artifact specialist instead when the review is …

    line 38
  5. Distinctive:

    Read the full diff, not just the hunks — check callers and tests affected by each change.

    line 49
  6. Distinctive:

    Do not rewrite the whole PR or produce a full alternative implementation unless asked.

    line 63
  7. Distinctive:

    Do not approve or merge anything — only the user or their CI/CD does that.

    line 64
  8. Distinctive:

    If you are not confident a finding is real, say so instead of stating it as fact.

    line 66

“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

PR Review

TL;DR checklist

  • Identify the change intent and read the complete diff with callers.
  • Check correctness, security, compatibility, performance, and meaningful tests.
  • Report only actionable findings with evidence and severity.

Key read-only checks

  • Inspect the PR diff, affected call sites, and focused tests before judging.

Common pitfalls

  • Do not approve a change based only on a green CI badge.

Agent procedure

Follow the Workflow, Safety rules, and Quality checklist below.

Quick references

  • Workflow below.

Last verified: unverified

When to use

Use when the user shares a pull request, diff, or branch and asks for a review, or wants a second opinion before merging. Use go-code-review, helm-review, kubernetes-yaml-review, dockerfile-review, or another artifact specialist instead when the review is focused on that artifact.

Goal

Give an actionable, lead-engineer-level review that catches real defects and maintainability risks without rewriting the whole change.

Workflow

  1. Understand the intent of the change (PR description, linked issue, or ask the user if unclear).
  2. Read the full diff, not just the hunks — check callers and tests affected by each change.
  3. Evaluate against these dimensions:
    • Correctness (logic errors, edge cases, off-by-one, nil/None handling, race conditions)
    • Maintainability (naming, structure, duplication, hidden coupling)
    • Readability (can a new engineer follow this in six months?)
    • Performance (obvious hot-path regressions, N+1 patterns, unnecessary allocations)
    • Security (injection, secrets in code, unsafe deserialization, auth/authz gaps)
    • Tests (are the new/changed paths covered? are the tests meaningful, not just coverage padding?)
    • Backward compatibility (API/schema/config changes that break existing callers)
  4. Classify every finding by severity before writing prose.
  5. For each finding, give the file/line, the concrete failure scenario, and a suggested fix.

Safety rules

  • Do not rewrite the whole PR or produce a full alternative implementation unless asked.
  • Do not approve or merge anything — only the user or their CI/CD does that.
  • Distinguish clearly between "this is broken" and "this is a style preference."
  • If you are not confident a finding is real, say so instead of stating it as fact.

Output format

## Critical
- <file:line> — <issue> — <why it breaks, concrete scenario> — <suggested fix>

## Major
- ...

## Minor
- ...

## Suggestions
- ...

## Summary
<1-3 sentences: is this safe to merge as-is, with fixes, or does it need rework?>

Omit any section with no findings rather than writing "None."

Quality checklist

  • Every Critical/Major finding has a concrete failure scenario, not just a vague concern
  • Tests were checked, not assumed
  • Security and backward-compatibility were explicitly considered
  • No full rewrite was proposed unless requested
  • Findings are ranked most-severe first

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.