agentleFS
Sign inStart free
LightbridgeLabLightbridgeLab/CodeCannon/.claude/skills/review/SKILL.md

review

Skill1 starsChanged 8 months agoMITView on GitHub

Code Cannon: Run a standalone code review on a pull request

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images 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.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If ai is "off", say:

    line 15
  2. Very specific:

    If $ARGUMENTS is a number, use it as the PR number.

    line 25
  3. Very specific:

    If $ARGUMENTS is empty, detect the current branch's open PR:

    line 27
  4. Very specific:

    If no PR is found, abort and say: "No open PR found for the current branch.

    line 32
  5. Very specific:

    Read the PR diff via gh pr diff <number>

    line 45
  6. Distinctive:

    Read any files needed for full context

    line 46
  7. Distinctive:

    After the review agent completes, relay its verdict to the user:

    line 53

“Common” is measured: kept by at least 6 in 10 of the 157 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

What /review does

/review runs a standalone code review on a PR. It wraps .claude/review-agent-prompt.md.

Pre-flight

If ai is "off", say:

"Code review is disabled for this project (REVIEW_GATE is set to 'off' in .codecannon.yaml). To enable reviews, set REVIEW_GATE to 'ai' or 'advisory' and re-run CodeCannon/sync.py."

Do not proceed.

Step 1 — Identify the PR

If $ARGUMENTS is a number, use it as the PR number.

If $ARGUMENTS is empty, detect the current branch's open PR:

gh pr view --json number --jq '.number'

If no PR is found, abort and say: "No open PR found for the current branch. Pass a PR number explicitly: /review <number>"

Step 2 — Run the review

Load .claude/review-agent-prompt.md and perform the review for the PR number.

If sub-agent spawning is supported: invoke a dedicated review agent with the prompt and PR number.

If sub-agent spawning is not supported: perform the review yourself inline — follow the instructions in the review-agent prompt directly.

The review must:

  1. Read the PR diff via gh pr diff <number>
  2. Read any files needed for full context
  3. Post findings as a PR comment via gh pr comment <number>

Step 3 — Report verdict

After the review agent completes, relay its verdict to the user:

  • APPROVE → "Review passed. Run /submit-for-review to merge (or it may already be merged if called from /submit-for-review)."
  • REQUEST CHANGES → Surface the CRITICAL findings. Say: "Fix the issues above and run /review again before merging."

Important

  • This command does not commit, push, or merge anything. It only reviews.
  • It may be called manually at any time, not just from /submit-for-review.
  • The review comment is posted to GitHub for the audit trail.
<!-- generated by CodeCannon/sync.py | skill: review | adapter: claude | hash: 8371e76b | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

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