review
Skill1 starsChanged 5 days agoApache-2.0View on GitHub
Review the change made for a task against its specification's acceptance criteria — not a generic code review, but a check that the diff actually satisfies what the spec asked for.
192 other projects use a version of this.
Adopted by
Most recently taken up by
- dzhng/skillstheir own version, first seen Nov 15, 2026
- muxy-app/muxytheir own version, first seen Nov 15, 2026
- macro-inc/macrotheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- markmhendrickson/neotomatheir own version, first seen Nov 15, 2026
- felipeam86/pipe-skillstheir own version, first seen Nov 15, 2026
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.
dzhngSkillclose-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
dzhngSkilldesign-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
LambenthanSkilldaily-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
LambenthanSkillexp-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
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- garrytan/gstack★ 142ksame name
- ansible/ansible★ 71ksame name
- docling-project/docling★ 71ksame name
- traefik/traefik★ 66ksame name
- ClickHouse/ClickHouse★ 51ksame name
- temporalio/temporal★ 24ksame name
- ccch1mneyyy/dsh-Go★ 24ksame name
- tisfeng/Easydict★ 15ksame name
- juicedata/juicefs★ 15ksame name
- elie222/inbox-zero★ 13ksame name
182 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 156 edited versions we read keep these.
5
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
- Very specific: line 8
Use this skill when the user explicitly invokes it, or when flow invokes it as the last step of its pipeline.
- Distinctive: line 14
If the user pointed you to a specific spec file, use that.
- Distinctive: line 20
Read the specification in full, especially its Acceptance criteria and Verification plan sections.
- Distinctive: line 30
Simplification/reuse: only flag genuine over-engineering or missed reuse — don't nitpick style.
- Distinctive: line 32
Don't re-review unrelated pre-existing code the task didn't touch, and don't repeat verification the spec's plan already covers unless you …
- Distinctive: line 36
If you can't tell whether a criterion is met without a decision only the user can make, stop and ask.
“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.
Files
Review
Use this skill when the user explicitly invokes it, or when flow invokes it as the last step of its pipeline.
Review is read-only: report findings, don't fix them. If the user wants fixes applied, that's a follow-up /implement invocation, or an explicit request to make a specific change.
Find the specification to review against
- If the user pointed you to a specific spec file, use that.
- Otherwise, look at
.dcc/specs/*.done.md— specsimplementhas already marked done.- None found: ask the user which spec (or which diff) to review, or whether to run
/implementfirst. - Exactly one, or one that was clearly just completed in this session: use it, and tell the user which one.
- Several plausible candidates: ask the user which one.
- None found: ask the user which spec (or which diff) to review, or whether to run
Read the specification in full, especially its Acceptance criteria and Verification plan sections.
Review the actual change
Identify the diff this specification produced — the commits or working-tree changes made for this task, using the repository's version control (e.g. comparing against the spec's recon_commit, or whatever the repository shows as the relevant change; ask if it's genuinely ambiguous which changes belong to this task).
For each acceptance criterion, check whether the change actually satisfies it — don't just check that the code looks reasonable in isolation. Also check, at the altitude the task warrants:
- Correctness: logic errors, edge cases the acceptance criteria call out, integration points the spec identified.
- Consistency: does the implementation follow the approach and files the spec described, or did it quietly diverge in a way that matters?
- Simplification/reuse: only flag genuine over-engineering or missed reuse — don't nitpick style.
Don't re-review unrelated pre-existing code the task didn't touch, and don't repeat verification the spec's plan already covers unless you have reason to doubt it passed.
Ask when genuinely unclear
If you can't tell whether a criterion is met without a decision only the user can make, stop and ask.
- Running standalone (invoked directly by the user, not as a
flowsubagent): check whether a skill namedgrill-meis available; if so, use it to run the clarifying question(s). If it isn't available, ask directly and wait for the answer. - Running as a
flowsubagent (your invocation says so): you have no interactive question tool here. Stop immediately and make your entire remaining output a single lineNEEDS INPUT:followed by the question(s), numbered, each with your recommended answer — don't callgrill-meorAskUserQuestion, and don't mix in a partial progress report.flowwill relay it to the user and resume you with the answer; continue exactly where you left off when that happens.
Either way, once answered, continue the review.
Result
Report findings against each acceptance criterion (met / not met / unclear), most important first. Don't modify code yourself.
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
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.

