review
Skill0 starsChanged 4 months agoApache-2.0View on GitHub
Review code changes from a range of commits. The user provides the scope and purpose of the change. Use when asked to review codes changes.
192 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/veronatheir own version, first seen Nov 8, 2026
- microsoft/FluidFrameworktheir own version, first seen Nov 8, 2026
- charliee1w/consolidation-memorytheir own version, first seen Nov 8, 2026
- jisuzzzz/haechitheir own version, first seen Nov 8, 2026
- apokamo/kajitheir own version, first seen Nov 8, 2026
- dirien/yet-another-agent-harnesstheir own version, first seen Nov 8, 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★ 141ksame name
- ansible/ansible★ 71ksame name
- docling-project/docling★ 70ksame name
- traefik/traefik★ 65ksame name
- ClickHouse/ClickHouse★ 51ksame name
- temporalio/temporal★ 24ksame name
- tisfeng/Easydict★ 15ksame name
- juicedata/juicefs★ 15ksame name
- elie222/inbox-zero★ 13ksame name
- gitkraken/vscode-gitlens★ 10ksame 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.
In this repository2 other files it gives its agents.
- cf-temp-deploySkill
- pdf-readerSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Ensure the following is provided by the user.
- Distinctive: line 31
If you find an issue with code not touched by the change, mark it and report it later in phase 3.
- Distinctive: line 44
Don't lookup best practices somewhere else.
“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.
Files
Code Review Guide
Prerequisites
Ensure the following is provided by the user. If any is lacking, ask the user to provide the missing information. Refuse to review if the information is not provided.
- Description Of The Change: A ticket/issue number, or, lacking that, a description of the purpose of the change. In case of a ticket/issue number, use existing tooling to retrieve it. Tooling depends on the format of the issue/ticket.
- Range Of Commits: The user provides a range of commits that encompass the change.
- User Understanding: The User must know the objective of the change on a non-technical level and must describe it in their own words.
Review Process
The review must be performed in distinct phases.
Phase 1: Knowledge Gathering.
The description of the change gives you the purpose, but to properly review the change you need to gather more information. This goes further than just the files touched by the change and the diff. Changes in a system also influence logic in other parts of it. Look how the data flows through the programm and ends up in code paths touched by the change. Build a callgraph that you can refer back to. See if you can spot invariants that must be upheld. Look at tests. If you find an issue with code not touched by the change, mark it and report it later in phase 3. While reviewing, don't run the code or test suites. Ask the user if this is necessary, but explain why. If you want to validate an assumption or possible issue, you are free to write a proof-of-concept test for it and execute it.
Phase 2: Review
Once you think you gathered enough information, review the code according to the following criteria. Treat each criteria independently. The criteria are listed from highest priority to lowest priority.
- Purpose: Does the change completely solve the problem from the issue description.
- Security: The change must not introduce security issues or weaken the security of the overall system.
- Stability: The change does not negatively affect the stability of the software when running. I.e. during runtime the software remains available, reliable, and does not consume more resources.
- Maintainability: Clear design and architecture based on software architecture principles. Other developers can maintain the code without asking the author of the change.
- Simplicity: Low complexity code change. It is easy to see what the code does and why. I.e. clear naming, the cyclomatic complexity is minimal without clever hacks or premature abstractions.
- Best practices: Is the change using best practices according to the language and libraries used. Rely solely of your trained knowledge or best practices established in the project's documentation. Don't lookup best practices somewhere else.
- Test coverage: Where possible, the changed code is tested with full coverage.
For each criteria if you have a finding, rank it in one of three categories:
- Low: Minor finding or nitpick. A strict reviewer might call this out or when training a junior developer to give advice. On its own, the finding is worth a note, but can also be left uncommented.
- Medium: Introduces unnecessary complexity, missed test coverage, non-obvious behaviour, problems in edge-cases, or violates best-practices. Can be left as is but needs a discussion. In general, it should be changed.
- High: Real problem. Fails purpose of the change. Breaks existing behaviour or causes a regression. Introduces a security problem. Can cause stability issues. Introduces too much complexity and can be done in a simpler way.
Phase 3: Report
The final report must list each review category separately. For each category present your findings from low to high. A finding should be in the following format:
[rank]: SHORT DESCRIPTION
FULL DESCRIPTIONWhere rank is the rank (low, medium, high). SHORT DESCRIPTION names the finding in a short sentence.
FULL DESCRIPTION describes the finding in multiple sentences, clearly describing where the problem is, why it is a problem, and, if possible, how it can be solved in your opinion. The full description should be understandable and give proper
context.
Finally, give a short judgement how well the issue/ticket or user description from the review prerequisites matches what was implemented by the change.
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.

