autoreview
Skill2 starsChanged 26 days agoMITView on GitHub
Fresh-context independent code review of a sushiAI diff before it is committed: correctness, root cause over symptom, callers and sibling paths, security boundary, test value. Use after implementation and deslop, before landing any nontrivial change, or when the owner asks for a review.
40 other projects use a version of this.
Adopted by
Most recently taken up by
- openclaw/agent-skillstheir own version, first seen Nov 14, 2026
- jamesblackwell/falcondecktheir own version, first seen Nov 9, 2026
- openclaw/openclaw-enterprisetheir own version, first seen Nov 8, 2026
- alexandrosandre/agentic-engineeringtheir own version, first seen Nov 8, 2026
- alexandrosandre/alice-issue-agenttheir own version, first seen Nov 8, 2026
- openclaw/crabboxtheir own version, first seen Nov 3, 2026
Used with
Projects with it also use discord-e2e, openclaw-repair-sweep 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.
molt-botSkilldiscord-e2e
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.
Also in 10 projects that use this
molt-botSkillopenclaw-repair-sweep
Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.
Also in 10 projects that use this
clawdbotSkillopenclaw-performance
Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.
Also in 7 projects that use this
clawdbotSkillplugin-sdk-impact
Count Plugin SDK consumers across live ClawHub releases and bundled OpenClaw plugins before deprecation, removal, or behavior changes; supports public release-date filters.
Also in 7 projects that use this
openclawSkillopenclaw-brand
Apply OpenClaw visual identity to typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.
Also in 5 projects that use this
openclawSkillopenclaw-design
Route OpenClaw design work to canonical brand, Carapace product-interface, marketing-page, or design-audit guidance. Use when a task touches OpenClaw visual identity, shared CSS tokens, product UI, public web pages, or Carapace compliance.
Also in 5 projects that use this
- +2 more from molt-bot
- +3 more from openclaw
Other versions40 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 40
- openclaw/openclaw★ 395ksame name
- moltbot/clawdbot★ 394ksame name
- steipete/warelay★ 394ksame name
- steipete/clawdis★ 394ksame name
- moltbot/moltbot★ 394ksame name
- clawdbot/clawdbot★ 394ksame name
- molt-bot/clawdbot★ 391ksame name
- openclaw/clawhub★ 9.6ksame name
- clawdbot/clawdhub★ 9.5ksame name
- moltbot/molthub★ 9.5ksame name
30 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- author-and-verify-extensionSkill
- cut-releaseSkill
- deslopSkill
- extension-manifest-changeSkill
- figma-to-codeSkill
- ship-prSkill
- sushiai-taskSkill
- sushiai-testingSkill
- sushiai-uiSkill
- ui-evidenceSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 40 edited versions we read keep these.
1
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 21
Second engine for risky diffs: When the diff touches the renderer security settings, IPC handlers, the extension manifest validator, …
- Distinctive: line 30
Re-review only substantive fixes: No extra rounds for a nicer verdict.
“Common” is measured: kept by at least 6 in 10 of the 40 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
Autoreview
Findings are hypotheses to verify, not instructions to apply.
Run
- Pick the target. Uncommitted work:
git diff HEADplus untracked files. A branch:git diff $(git merge-base main HEAD)...HEAD. One commit:git show <sha>. Done when: the reviewer is given one exact command that reproduces the diff. - Brief the
reviewersubagent with the owner's request, the acceptance criteria, the diff command and the severity threshold (P0-P1 by default; P2-P3 only when asked). Do not tell it what you believe is wrong or why the code is right - its value is a fresh read. Done when: the brief carries no diagnosis. - Second engine for risky diffs. When the diff touches the renderer
security settings, IPC handlers, the extension manifest validator,
persistence or SSH, also run Codex read-only if it is installed
(
command -v codex): check the flags withcodex exec --help, then runcodex exec --sandbox read-onlywith the same brief. Skip silently when it is absent. - Verify every finding against the actual code before touching anything. Fix what is real; reject the rest with a one-line reason in the report. Done when: each P0/P1 is fixed or rejected with evidence.
- Re-review only substantive fixes. No extra rounds for a nicer verdict.
Severity
- P0 - breaks normal operation, loses data, crosses the security boundary, or leaks a credential or real private data (report it without repeating the value).
- P1 - wrong behaviour on a realistic path, a missed caller or sibling, a test that cannot fail.
- P2 - maintainability or clarity cost with a concrete consequence.
- P3 - style.
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.

