pre-review
Skill628 starsChanged 4 days agoMITView on GitHub
Deep code review before opening a pull request. Use when running /pre-review on local changes.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- arklexai/arksimtheir own version, first seen Oct 8, 2026
- ai2cm/acetheir own version, first seen Oct 8, 2026
- ffwright/claude-skillstheir own version, first seen Aug 17, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ai2cm/ace★ 259same name
- arklexai/arksim★ 234same name
- ffwright/claude-skills★ 0same name
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 repository71 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- analyticsSkill
- batch-feature-devSkill
- ci-runnersSkill
- ci-workflow-refsSkill
- cleanupSkill
- client-idsSkill
- cloud-sync-moduleSkill
- codeownershipSkill
- coin-families-contractSkill
- coin-modulesSkill
- commentsSkill
- configurationSkill
- console-logSkill
- create-changesetSkill
- create-prSkill
- data-layer-advancedSkill
- debug-rn-native-crashSkill
- dependency-patchesSkill
- detect-data-leaksSkill
- device-intent-executorSkill
- devtools-import-boundarySkill
- dialogs-sliceSkill
- docs-migrateSkill
- docs-update-or-createSkill
- domain-dataSkill
- e2e-desktop-add-or-updateSkill
- e2e-desktop-onboardSkill
- e2e-earnSkill
- e2e-mobile-add-or-updateSkill
- e2e-mobile-onboardSkill
- e2e-swapSkill
- errorsSkill
- feature-devSkill
- fix-ciSkill
- flow-packageSkill
- get-pr-commentsSkill
- git-conventionsSkill
- i18n-keysSkill
- impacting-prsSkill
- knip-migrationSkill
- ldls-nativeSkill
- ldls-webSkill
- ledger-wallet-cliSkill
- legacy-migrationSkill
- mvvm-architectureSkill
- new-packageSkill
- package-public-apiSkill
- pnpm-resolutionSkill
- prefer-set-hasSkill
- react-generalSkill
- rebuild-to-fix-lib-import-errorsSkill
- remove-feature-flagSkill
- run-buildsSkill
- run-e2e-ciSkill
- runner-imagesSkill
- run-testsSkill
- slack-pr-messageSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
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 33
Ask the user which items to fix: "all criticals", "all", "#1,#2, #3", or "skip" → /create-pr
“Common” is measured: kept by at least 6 in 10 of the 3 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
Pre-Review
Deep code review before you open a PR.
Process
- Choose the review range. Default:
git diff develop...HEAD. If the user names another range (for exampleHEAD~1..HEAD), use that instead. All prompts in step 2 must review this exact diff, not a different ref pair. Launch 5
code-revieweragents in parallel, each with a different focus:- A: Layers and boundaries first (
.agents/skills/structure-flow/SKILL.md,.agents/skills/flow-package/SKILL.md,.agents/skills/domain-data/SKILL.md,.agents/skills/package-public-api/SKILL.md), then MVVM for app composition underapps/*/src/mvvm/and for presentation infeatures/flow/**(Container, ViewModel, View, steps;.agents/skills/mvvm-architecture/SKILL.md,.agents/skills/flow-package/SKILL.md). Apply review-only gaps from.agents/agents/references/review-rules.md; do not repeat whatpnpm lint:archalready fails on CI. - B — Correctness (edge cases, null handling, error states)
- C — Code quality & conventions (Lumen UI, TypeScript, naming, new deps). Reject new
.pnpmfile.cjshooks andpnpm.packageExtensions(skillpnpm-resolution). - D — General review — DRY, KISS, missing tests, anything that would slow down a reviewer or cause future regressions
- E — Security: invoke the
detect-data-leaksskill for PII; check for auth bypass, injection, SSRF, crypto misuse; scan the diff for hardcoded secrets, tokens, API keys, or private keys.
Each agent prompt: "Review the diff from step 1 (the same range). Focus on [FOCUS]. Return findings with file:line, severity (🔴 Critical / 🟡 Suggestion / 🟢 Nice to have), and suggested fix."
- A: Layers and boundaries first (
Merge + deduplicate findings. Present grouped by severity:
🔴 Critical — path/to/file.ts:42 — issue → fix 🟡 Suggestion — ... 🟢 Nice to have — ... Summary: X critical, Y suggestions, Z nice-to-haves- Ask the user which items to fix: "all criticals", "all", "#1,#2, #3", or "skip" →
/create-pr
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.

