review
Skill2 starsChanged 8 months agoMITView on GitHub
Pre-landing code review. Catches structural issues that tests miss — scope drift, SQL safety, race conditions, trust boundary violations. Use when asked to review a PR, check a diff, or before merging.
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
- 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
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
- 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
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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- examples/CLAUDE.mdCLAUDE.md
- claudeceptionSkill
- closeSkill
- ideaSkill
- investigateSkill
- office-hoursSkill
- plan-ceo-reviewSkill
- reflectSkill
- retroSkill
- scopeSkill
- shipSkill
- startSkill
- tddSkill
- verify-before-doneSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 157 edited versions we read keep these.
10
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 12
Read the full diff before flagging anything.
- Distinctive: line 16
Before merging or landing code changes
- Distinctive: line 17
When asked to "review this PR", "check my diff", or "code review"
- Distinctive: line 18
After completing a feature, before calling it done
- Distinctive: line 64
Every finding gets one of two treatments:
- Distinctive: line 71
Do NOT leave read-only commentary.
- Distinctive: line 76
If code behavior changed, do the docs reflect it?
- Distinctive: line 87
Read first, judge second — understand the full change before flagging anything
- Distinctive: line 88
Verify every claim with evidence from the code
- Distinctive: line 90
Prefer fixing over commenting when the fix is obvious and safe
“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
Review
The Rule
Read the full diff before flagging anything. Verify every claim — no "probably handled" language. Every finding must have an action.
When to Use
- Before merging or landing code changes
- When asked to "review this PR", "check my diff", or "code review"
- After completing a feature, before calling it done
The 5 Steps
Step 1: Understand the Change
- Get the diff -- read the full set of changes against the base branch.
- Identify the intent -- what is this change trying to accomplish? Check commit messages, PR description, any linked issues or TODO items.
- Map the blast radius -- which files changed, which systems are affected, what could break downstream.
Step 2: Scope Check
Compare stated intent against actual files changed:
- CLEAN -- changes match the stated purpose, nothing extra
- DRIFT DETECTED -- files changed that don't relate to the stated purpose
- REQUIREMENTS MISSING -- stated goals not fully addressed by the changes
Flag scope drift immediately. Unrelated changes in a PR are a common source of hidden bugs.
Step 3: Two-Pass Review
Pass 1 — Critical issues (must fix before merge):
| Category | What to look for |
| SQL safety | Raw queries, missing parameterization, injection risk |
| Race conditions | Shared state without locks, concurrent access patterns |
| Trust boundaries | Unsanitized user input, LLM output used as commands |
| Auth/authz gaps | Missing permission checks, token exposure |
| Data loss risk | Destructive operations without confirmation, missing backups |
| Error handling | Silent failures, swallowed exceptions, missing rollback |
| Enum completeness | Switch/case without default, missing status values |
Pass 2 — Informational (improve but don't block):
| Category | What to look for |
| Side effects | Functions that modify state unexpectedly |
| Magic values | Hardcoded strings, numbers without explanation |
| Dead code | Unreachable branches, unused imports |
| Test gaps | Changed behavior not covered by tests |
| Naming | Misleading names, inconsistent conventions |
Step 4: Fix or Flag
Every finding gets one of two treatments:
| Classification | Action |
| AUTO-FIX | Mechanical issues (typos, formatting, missing imports) — fix directly, one-line summary |
| ASK | Judgment calls, design questions, ambiguous trade-offs — present to user with context |
Do NOT leave read-only commentary. Every issue either gets fixed or gets a decision request.
Step 5: Documentation Check
- Are docs (README, comments, API docs) still accurate after these changes?
- If code behavior changed, do the docs reflect it?
- Flag stale documentation — don't silently leave it wrong.
What This Skill Does NOT Do
- Does not commit, push, or create PRs -- that's
/ship - Does not run the full test suite -- that's
/verify-before-done - Does not debug failing tests -- that's
/investigate
Key Principles
- Read first, judge second — understand the full change before flagging anything
- Verify every claim with evidence from the code
- Critical issues block; informational issues inform
- Prefer fixing over commenting when the fix is obvious and safe
- Scope discipline: review what changed, not the whole codebase
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.