agentleFS
maidepsmaideps/ai-harness-framework/skills/review/SKILL.md

review

Skill2 starsChanged 7 days agoMITView on GitHub

Independent verification pass before the feature gate — scope, diff, and evidence.

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

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before reporting a feature as done

    line 12
  2. Distinctive:

    When picking up someone else's in-flight work

    line 13
  3. Very specific:

    Check the feature's dependency chain: dependencies must be passing or the gate will refuse the transition.

    line 20
  4. Very specific:

    Verify the evidence path: evidence field in .harness/state/<feature-id>.json (bound to a commit), the trail verify-feature wrote in …

    line 21
  5. Distinctive:

    Write down anything not verified — say it in the handoff instead of implying it.

    line 22
  6. Distinctive:

    Never present a partial result as the whole.

    line 27

“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

An adversarial pass on your own work before it goes through the gate. It exists so the feature gate verifies something worth verifying.

When to Use

  • Before running npm run verify-feature -- <id>
  • Before reporting a feature as done
  • When picking up someone else's in-flight work

Workflow

  1. Re-read the feature definition in feature_list.json — behavior, verification criteria, dependencies. The diff must implement THAT feature, nothing else, and its tests must check THAT behavior: a test that passes against different behavior makes the gate pass for the wrong reason.
  2. Review the diff file by file: scope creep, unrelated edits, debug artifacts, commented-out code, TODOs without owners.
  3. Confirm the gates actually ran and their output was read — PASS vs SKIP must be reported separately; a SKIP is not evidence.
  4. Check the feature's dependency chain: dependencies must be passing or the gate will refuse the transition.
  5. Verify the evidence path: evidence field in .harness/state/<feature-id>.json (bound to a commit), the trail verify-feature wrote in .harness/trails/, state files updated.
  6. Write down anything not verified — say it in the handoff instead of implying it.

Rules

  • Review is adversarial: assume the change is wrong until the evidence says otherwise.
  • Never present a partial result as the whole.
  • The gate is the mechanism; this pass is the discipline. Both are required.

Quick Reference

  • Feature definition re-read; diff matches it
  • No scope creep or debug artifacts
  • Gates ran; PASS/SKIP reported honestly
  • Dependencies passing
  • Evidence recorded and trail present

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.