agentleFS
CarriedWorldUniverseCarriedWorldUniverse/nexus/.agents/skills/review/SKILL.md

review

Skill0 starsChanged 36 days agoApache-2.0View on GitHub

How to review a change before merge — confidence-based, verify findings, enforce the security gate; and how to receive review without performative agreement.

192 other projects use a version of this.

Adopted by

Most recently taken up by

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

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 6

    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. Very specific:

    Read the actual file:line for every claim.

    line 12
  2. Distinctive:

    Verify before implementing.

    line 18
  3. Distinctive:

    Read the whole feedback without reacting.

    line 19
  4. Distinctive:

    Check each against the codebase reality — is it sound for THIS code?

    line 21
  5. Distinctive:

    If feedback is wrong, push back with technical reasoning.

    line 22
  6. Distinctive:

    Never reply "You're absolutely right" / "Great point".

    line 24
  7. Distinctive:

    If any item is unclear, stop and ask before implementing anything — items may be related.

    line 25

“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

review

Reviewing a change

  1. Review the diff for real, high-priority issues: bugs, logic errors, security holes, broken conventions. Report only what truly matters — don't pad with nits.
  2. Adversarially verify each finding before you report it. Assume you're wrong; try to refute the issue. If you can't refute it, it's real.
  3. Read the actual file:line for every claim. Don't report from a grep match alone — open it and walk the logic.
  4. Load the security skill and confirm its scan gate is green for this change.
  5. One ticket per review. Flag scope creep.
  6. Rank findings: critical (fix now), important (fix before merge), minor (note for later).

Receiving review (no performative agreement)

Verify before implementing. Ask before assuming.

  1. Read the whole feedback without reacting.
  2. Restate each item in your own words, or ask if it's unclear.
  3. Check each against the codebase reality — is it sound for THIS code?
  4. If feedback is wrong, push back with technical reasoning. If right, just fix it.
  5. Fix one item at a time; test each.
  • Never reply "You're absolutely right" / "Great point". Respond with the technical substance or the action.
  • If any item is unclear, stop and ask before implementing anything — items may be related.

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.