agentleFS
muxy-appmuxy-app/muxy/.agents/skills/review/SKILL.md

review

Skill2.4k starsChanged 2 days agoApache-2.0View on GitHub

Exhaustively review every line in a diff from a fixed point along two independent axes—repository standards and the originating spec—with evidenced findings, explicit coverage, and bounded fix verification.

192 other projects use a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 5 mentionsMay 2026: 4 mentionsJun 2026: 0 mentionsJul 2026: 2 mentionsAug 2026: 0 mentionsSep 2026: 1 mentionOct 2026: 6 mentionsNov 2026: 2 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the muxy-app/muxy repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about muxy-app/muxy

The biggest 5 of 20 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 20

Talked about on GitHub, Hacker News and Bluesky (20 times).

On GitHub · 16

11 more on GitHub

On Bluesky · 1

Used with

Projects with it also use close-spec, daily-arxiv 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

  • 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

  • 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

    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

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

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not report advisories unless user asks for them.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 156 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

Code Review

Review one immutable diff against:

  • Standards — repository instructions and documented coding standards.
  • Spec — the originating issue, PRD, or acceptance criteria.

Prepare

  1. Pin the requested input. Resolve committed endpoints to SHAs; if staged or working-tree changes are included, capture one patch snapshot. Give every reviewer that same immutable diff. Stop on invalid or empty input.
  2. Find the spec from commit references, a user-provided path, or matching files under docs/, specs/, or .scratch/. If none exists, mark the Spec axis unavailable.
  3. Find applicable repository instructions and standards such as CLAUDE.md, AGENTS.md, CONTRIBUTING.md, and CODING_STANDARDS.md.
  4. Inventory the complete diff: files, hunks, additions, deletions, renames, and binary files. Never rely on one possibly truncated diff output.
  5. Find the specs of the changes. what feature it delivers, or what issue it solves. Use PR summary or linked issues or user provided context. If not sure, Ask user before proceeding. Sometimes its possible to understand the spec from the code changes as well.

Review

  • Inspect every added, changed, and deleted line in every file, including tests, docs, configuration, migrations, lock/generated files, renames, and binaries. Read surrounding code and call sites where needed.
  • Maintain a file-and-hunk checklist against the inventory. Inspect file by file or in smaller batches so output cannot hide lines through truncation. Do not finish with an unchecked line or hunk.
  • Report only issues introduced by the diff. A blocker requires evidence of an acceptance, correctness, security, data-loss, compatibility, or explicit required-standard violation. Style preferences, generic code smells, speculative hardening, optional refactors, and unrelated debt are non-blocking advisories.
  • For findings, provide severity, file:line, the violated spec/rule or invariant, a concrete failure scenario, evidence, and the smallest valid fix. Do not report vague possibilities.
  • Return PASS or CHANGES NEEDED, then blockers, advisories, and coverage totals. PASS means zero blockers, not zero possible improvements.

Compare both coverage reports with the inventory. If anything is missing, review only the missing batches before reporting; an incomplete review cannot pass.

Report

  • Present ## Standards and ## Spec separately. End with blocker and advisory counts per axis. Do not let advisories change a pass into failure.
  • Also when presenting, each findings should have severity, High, Medium, Low and clarify which ones must be fixed before proceeding.
  • Recommend FIX BEFORE PROCEEDING, CONSIDER FIXING, or PROCEED from the evidenced severity, confidence, and risk, and name the findings that drive the recommendation. The review is read-only: the user decides whether to fix. Ask for that decision and do not edit or dispatch a fixer without explicit approval.
  • Do not report advisories unless user asks for them.
  • Provide a TL;DR section in the end in short in a table

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.