agentleFS
Sign inStart free
griffinhillygriffinhilly/claude-code-synthesis/skills/review/SKILL.md

review

Skill67 starsChanged 4 months agoMITView on GitHub

Review completed work against success criteria and flag issues

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

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no arguments, review whatever was most recently implemented in the conversation.

    line 17
  2. Very specific:

    If /verify hasn't been run on the target, suggest running it first — /verify catches completeness issues, /review catches quality issues.

    line 22
  3. Distinctive:

    Read relevant COMP files (CLAUDE.md for conventions, MEMORY.md for gotchas)

    line 23
  4. Very specific:

    Read ~/.claude/skills/review/review-dimensions.md for what to check based on the type of work (code, data, writing).

    line 27
  5. Distinctive:

    Spec-blind: Do NOT include the original spec, plan, or coder context in the reviewer's prompt.

    line 31
  6. Very specific:

    Read ~/.claude/skills/review/output-format.md for how to organize findings.

    line 36
  7. Very specific:

    If the review surfaces architectural concerns, suggest /dialectic-review --premortem before proceeding with fixes

    line 40
  8. Very specific:

    Read ~/.claude/skills/review/rules.md for review rules and gotchas.

    line 43

“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

Evaluate completed work against its success criteria. Find problems before they compound.

Input

What to review: $ARGUMENTS

If no arguments, review whatever was most recently implemented in the conversation.

Process

Step 1: Pre-check

  • If /verify hasn't been run on the target, suggest running it first — /verify catches completeness issues, /review catches quality issues. Different concerns.
  • Read relevant COMP files (CLAUDE.md for conventions, MEMORY.md for gotchas)
  • Identify the success criteria (from /plan-task output, PLAN.md, or conversation)

Step 2: Launch Review

Read ~/.claude/skills/review/review-dimensions.md for what to check based on the type of work (code, data, writing).

Launch the review using a fresh-context subagent (use the code-reviewer agent persona for code). Apply the strengthened review discipline (per CLAUDE.md "Fresh eyes for review"):

  1. Spec-blind: Do NOT include the original spec, plan, or coder context in the reviewer's prompt. Pass the diff (or the artifact) and have the reviewer reason backward. The reviewer's lack of spec-knowledge is a feature — it surfaces unstated assumptions the spec hid.
  2. Multiple uncorrelated passes: Launch the reviewer 2-3 times in parallel with the same prompt. Union their findings. If the same model produces overlapping findings, that's signal; if they find different things, the union is the value.
  3. Treat-as-adversary: Frame the reviewer's findings as questions about the work, not defects to auto-fix. Pass each finding through "is this actually wrong, or is it the reviewer pattern-matching without context?" Keep the credible ones; reject the rest with reasoning.

Step 3: Present Findings

Read ~/.claude/skills/review/output-format.md for how to organize findings.

Step 4: Escalation Check

  • For significant reviews, consider suggesting /dialectic-review for adversarial depth
  • If the review surfaces architectural concerns, suggest /dialectic-review --premortem before proceeding with fixes

Rules

Read ~/.claude/skills/review/rules.md for review rules and gotchas.

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