agentleFS
stormlightlabsstormlightlabs/mire/.claude/skills/review/SKILL.md

review

Skill1 starsChanged 20 days agoApache-2.0View on GitHub

Review a pull request or branch for defects and report the findings. Runs a standard pass or an adversarial pass. Use for /review, /adv-rev, code review, PR review, or when asked to check a diff before merge.

192 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

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read the changed files around the diff, not only the diff.

    line 50
  2. Very specific:

    Do not repeat a finding an earlier pass raised and a revise pass fixed, unless the fix did not hold.

    line 124
  3. Very specific:

    If the same finding survives two revise passes without its cause changing, stop and escalate to the user.

    line 126

“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

Review

Review a diff and report findings. Do not edit code during a review pass; the revise skill owns changes.

The storm skill runs the review stages fab sequence gives the pull request from .github/fabrial-sequence.toml, each pass in a fresh agent. A pass checks its own findings, reports to whoever invoked it, and posts only when they ask.

Pick the target and the pass

The argument is a pull request number, a branch name, or empty for the current branch, then the pass. Without one, the pass is standard.

PassBrief
StandardCorrectness, edge cases, security, concurrency, performance, API compatibility, test coverage, readability.
AdversarialWorst case only: security holes, races, unhandled input, violated invariants, tests that cannot fail.

The adversarial pass runs after the standard pass and is handed its findings. It reports again only those that the code still gets wrong, and otherwise looks for what the standard pass would miss. The adversarial-reviewer agent lists what it hunts and what it owes each finding.

Complexity

Both passes weigh complexity, because a defect is cheaper to prevent than to find. Ask of each change:

  • Is this harder than the problem it solves? Name the simpler version and what it would cost.
  • Does it add an interface, a layer, or a configuration point that one concrete helper would cover?
  • How many things must a reader hold at once to know this is correct?
  • Does it repeat something the codebase already does, under a new name?
  • Could a check replace the care this asks of the next person to touch it?

Report complexity the way you report a defect: what it costs, and what to do instead. "Simpler would be better" without a concrete alternative is not a finding.

Gather context first

Read the changed files around the diff, not only the diff. Read the task the change is for: the branch name, the pull request body or the first commit names it. For an arcl task, arcl context <id> gives its acceptance criteria and spec; for an issue, gh issue view <n> or issue_read; otherwise the pull request body is the task.

references/reading-the-diff.md gives the commands. In short: fetch the branch, pin its head commit once and review that, use one transport (gh, or the GitHub MCP tools in a cloud session), and read the change through git rather than the working tree, which may hold another branch.

Judge against something

A finding needs a source. Rank them:

  1. The task's acceptance criteria and its spec.
  2. AGENTS.md, and the conventions the surrounding code already keeps.
  3. Tests that exist, tests that should exist, and tests that cannot fail.
  4. Behavior a user can observe.

Taste alone is a nit at most. A disagreement between models is not a finding.

Prose

Documentation in the diff is a change like any other, and so are the pull request title and body, the branch's commit messages and the comments posted. Judge them against the writing-docs skill and its tells catalogue.

What you findSeverity
Documentation contradicts the code it describeshigh
User-visible behavior changed, documents did notmedium
A catalogued tell, or one pattern used throughoutmedium
Past a soft limit or a length targetlow
Heading case, term driftnit

A pattern repeated through a document is one finding naming the pattern, not one per instance.

Finding format

One line per finding:

<severity> · <path>:<line> — <problem> → <why it matters> → <fix direction>
SeverityMeans
blockerMerging causes data loss, a crash, a security hole, or a regression.
highWrong behavior in a case the change is supposed to handle.
mediumWrong behavior in an unhandled case, or a missing test for one.
lowWorks, but will cause a defect later.
nitStyle or naming inside the repository's conventions.

State what breaks and with what input. A finding that cannot name a failing case is speculation; drop it or mark it nit.

Keep the report readable

  • Most severe first, with no preamble and no closing summary.
  • Under 200 words. Past ten findings, give the ten that matter and say how many you left out. Cut a finding rather than compressing ten into denser prose.
  • Cite <path>:<line> instead of quoting the diff back.
  • Group repeats: one finding naming every site.
  • Open with one line naming the pass, the target and what you ran as: Adversarial pass on #12 at 4f2a91c · <model> · <effort>. Use the model identifier the harness reports.

Say No findings when there are none rather than inventing one.

Stop conditions

  • Do not repeat a finding an earlier pass raised and a revise pass fixed, unless the fix did not hold.
  • If the same finding survives two revise passes without its cause changing, stop and escalate to the user.

Do not

  • Edit files, commit, push, approve, or merge.
  • Review a diff you wrote in this same session without saying so.

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.