agentleFS
Sign inStart free
adeerkhanadeerkhan/vitruvius/skills/review/SKILL.md

review

Skill10 starsChanged 5 days agoMITView on GitHub

Run a tough but constructive internal critique of an engineering artifact — a design, draft report, calculation set, specification, or research brief. Use when the user asks for a review, critique, feedback, or wants weaknesses found before something is finalized or submitted. Severity-graded findings with a concrete revision plan.

192 other projects use a version of this, 1 of them edited.

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

4 rules. 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    Run an adversarial review of an engineering artifact.

    line 20
  2. Distinctive:

    Before searching, name the question, the artifact/scope (or say it is a literature review), the jurisdiction/edition, and the effort budget …

    line 26
  3. Very specific:

    Follow the artifact contract: save findings to outputs/<slug>-review.md.

    line 33
  4. Distinctive:

    Do not praise vaguely. Do not predict "approval" — assess revision risk and evidence quality.

    line 72

“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
<!-- VITRUVIUS-COMPILED-SKILL:BEGIN v1 sha256=b1e41d2a4017dc0788831c4d53f45f9cf5cc024dade131d9cf0c13f8928c6ae6 -->

Engineering Artifact Review

Run an adversarial review of an engineering artifact. This reuses the engineering-research evidence discipline but the artifact is the subject, not a question to research.

Input Gate

Before searching, name the question, the artifact/scope (or say it is a literature review), the jurisdiction/edition, and the effort budget (user-set or thorough). Ask ONE clarifying question if the ask is too vague, then proceed. See references/input-gate.md.

Workflow

Follow the artifact contract: save findings to outputs/<slug>-review.md.

  1. Identify the artifact and its claims — what is it (design, calc set, spec, brief, report), what does it claim, and what standard/code governs it?
  2. Verify the load-bearing items — for a design: loads, factors, material properties, code sections, sign conventions. For a report: every number, figure, and citation. Check each against the primary source.
  3. Read the source itself, not a summary of it — a criticism of a claim you did not open is not a finding; it is blocked. Name the source and location you actually read beside every criticism, so the reader can re-check it rather than take your word for it. Report a problem you inferred only when it is labelled inferred, and never smooth a missing read into a pass.
  4. Produce a severity-graded review:
    • FATAL — unsafe, non-compliant, or unsupported; must fix before use
    • MAJOR — likely wrong or a real gap; fix before finalizing
    • MINOR — clarity, consistency, polish Each finding cites the specific section/line/claim it targets. Every finding must be fully substantiated — a location you read plus evidence that supports it. An empty tier is a valid result: write none rather than padding to a count. Ground severity in the artifact's own claims and stated limitations: a step it never claimed to take is a scope note, not a FATAL. For a FATAL, state the strongest defense and the evidence that rules it out — a FATAL without a refuted defense is a suspicion, not a FATAL.
  5. Check what was NOT verified — mark blocked where the source could not be read; never let a missing check read as a pass.
  6. Write a revision plan — prioritized, concrete steps per finding.

Output

Save exactly one review to outputs/<slug>-review.md:

  • Summary assessment
  • Strengths (tied to specific evidence)
  • Findings (FATAL / MAJOR / MINOR, each anchored to a section/claim)
  • Verification status (verified / inferred / blocked per load-bearing item, each naming the source and location that was actually read)
  • Revision plan

Do not praise vaguely. Do not predict "approval" — assess revision risk and evidence quality.

Scope and Boundaries

  • This skill produces research — it does NOT produce final designs or construction documents.
  • Research-only, not for final engineering sign-off. Licensed engineers must review and approve any design based on this research.

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