code-review-graph
Skill1 starsChanged 2 months agoMPL-2.0View on GitHub
Use when the user asks for code-review-graph, graph-backed code review, structural codebase analysis, blast-radius analysis, dependency impact, affected-flow tracing, callers/callees/importers, architecture maps, repo onboarding, risk-scored diffs, token-efficient codebase exploration, or persistent graph context using the installed code-review-graph MCP or CLI. Use for unfamiliar repositories, large diffs, risky refactors, hidden dependency impact, affected tests, architectural hotspots, and compact code context retrieval. Do not use for tiny single-file edits, simple exact-text search, semantic file discovery only, normal GitHub issue or PR triage, generic architecture advice without repo evidence, or security-specific threat modeling. If the primary task is locating files by intent, use vexor-cli first. If the primary task is improving architecture or refactoring strategy, use improve-codebase-architecture and add this skill only for graph evidence. If the primary task is AppSec threat modeling, use security-threat-model.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- vudovn/ag-kittheir own version, first seen Oct 8, 2026
- vudovn/antigravity-kittheir own version, first seen Oct 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- vudovn/ag-kit★ 8.2ksame name
- vudovn/antigravity-kit★ 8.2ksame 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 repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/composition-patterns/AGENTS.mdAGENTS.md
- .agents/skills/react-best-practices/AGENTS.mdAGENTS.md
- .agents/skills/react-native-skills/AGENTS.mdAGENTS.md
- .agents/skills/vercel-optimize/AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- ai-coding-disciplineSkill
- artifact-system-designerSkill
- artifact-validation-workflowSkill
- catalogue-routerSkill
- chat-export-capability-minerSkill
- cli-creatorSkill
- codex-coding-os-masterSkill
- codex-design-artifactsSkill
- vercel-composition-patternsSkill
- create-prdSkill
- crisis-command-centerSkill
- customer-journey-mapSkill
- deep-criticSkill
- defensive-security-checklistSkill
- docSkill
- evidence-checkerSkill
- external-skill-overlay-packSkill
- grill-meSkill
- grill-with-docsSkill
- humanizerSkill
- improve-codebase-architectureSkill
- new-project-documentation-systemSkill
- pdfSkill
- playwrightSkill
- postgres-security-best-practicesSkill
- pre-mortemSkill
- process-docsSkill
- product-strategySkill
- project-session-continuitySkill
- quality-improvement-problem-solvingSkill
- quant-reviewSkill
- vercel-react-best-practicesSkill
- vercel-react-native-skillsSkill
- security-best-practicesSkill
- security-ownership-mapSkill
- security-threat-modelSkill
- ssot-auditorSkill
- ssot-drafterSkill
- storyscope-structural-auditSkill
- support-docsSkill
- technical-docs-packSkill
- vercel-optimizeSkill
- vexor-cliSkill
- wbs-artifact-plannerSkill
- working-backwardsSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.