repository-intelligence
Skill2 starsChanged 12 days agoMITView on GitHub
Map repository architecture, ownership, dependencies, change impact, and edit conflicts. Use when the task needs evidence about what exists or what a proposed change can affect. Not for implementing changes or diagnosing a runtime failure.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- cmdr-chara/codex-toolkitword for word, first seen Oct 31, 2026
- cvsz/zomegatheir own version, first seen Sep 2, 2026
Other versions2 projects use a version of this.
Word for word · 1
- cmdr-chara/codex-toolkit★ 2100% same
Edited · 0
None found.
Wrote their own version · 1
- cvsz/zomega★ 1same 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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bin/AGENTS.mdAGENTS.md
- evaluations/AGENTS.mdAGENTS.md
- orchestration/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- skills/llms.txtllms.txt
- bug-finderSkill
- codebase-evolution-controllerSkill
- codebase-improvement-plannerSkill
- completion-proofSkill
- content-provenance-hygieneSkill
- cpp-engineeringSkill
- debugging-investigatorSkill
- delegate-with-mission-cardsSkill
- documentation-synchronizerSkill
- expo-react-native-builderSkill
- flutter-production-builderSkill
- go-engineeringSkill
- kotlin-engineeringSkill
- mobile-architecture-directorSkill
- multi-agent-work-coordinatorSkill
- optimize-codebase-performanceSkill
- product-design-directorSkill
- production-web-builderSkill
- python-engineeringSkill
- review-and-refactor-codeSkill
- rust-engineeringSkill
- screenshot-to-interfaceSkill
- security-reviewSkill
- swift-engineeringSkill
- toolchain-preflightSkill
- typescript-quality-enforcerSkill
- verification-and-releaseSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 12
Use this skill for architecture/ownership mapping, dependency boundaries, blast radius, hotspots, change impact, or likely edit conflicts.
- Distinctive: line 14
Do not trigger to delegate work, implement the change, diagnose a specific runtime failure, or approve a release.
- Distinctive: line 26
Treat scanner output as evidence leads, not ownership truth.
- Distinctive: line 31
Do not edit generated/vendor content during mapping.
- Distinctive: line 33
Prefer repository-native manifests, imports, registrations, schemas, tests, and build/deploy configuration over naming guesses.
- Very specific: line 40
Determine ownership: Use code/config/history/docs evidence.
- Very specific: line 43
Report: Use references/evidence-model.md and references/output-schema.md for the evidence/confidence contract.
- Distinctive: line 51
If the repository is too large, state a bounded slice and expand breadth-first.
- Distinctive: line 55
Stop when the requested boundary, affected surfaces, confidence, and unresolved ambiguity are explicit enough for the next specialist to …
≈ “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.
Files
Repository Intelligence
Build an evidence-backed map of the repository without turning discovery into implementation.
Trigger boundary
Use this skill for architecture/ownership mapping, dependency boundaries, blast radius, hotspots, change impact, or likely edit conflicts.
Do not trigger to delegate work, implement the change, diagnose a specific runtime failure, or approve a release.
Required inputs
Resolve repository root, task/change hypothesis, candidate/base ref when relevant, working-tree state, generated/vendor boundaries, and the decision this map must support.
For a breadth-first signal scan:
python skills/repository-intelligence/scripts/repo_signal_scan.py . --format markdownTreat scanner output as evidence leads, not ownership truth.
Safety baseline
- Preserve uncommitted user work and remain read-only.
- Do not edit generated/vendor content during mapping.
- Distinguish facts from inference and state confidence.
- Prefer repository-native manifests, imports, registrations, schemas, tests, and build/deploy configuration over naming guesses.
Workflow
- Frame the decision. State what must be mapped and what would change the next action.
- Establish state. Record branch/ref, worktree changes, languages/workspaces, generated boundaries, and major entry points. For large/noisy repositories or restartable long tasks, read
references/context-loading.mdand pack only decision-relevant evidence. - Map components and dependencies. Trace imports/calls, data/contracts, routes/events, build/runtime links, persistence, and operational boundaries.
- Determine ownership. Use code/config/history/docs evidence; mark ambiguous ownership rather than inventing it.
- Map impact. Identify direct edits, consumers, compatibility surfaces, tests, deployment units, migrations, and generated outputs.
- Locate hotspots/conflicts. Highlight high-coupling/stateful areas and likely overlapping write scopes.
- Report. Use
references/evidence-model.mdandreferences/output-schema.mdfor the evidence/confidence contract.
Handoffs and interaction boundaries
Hand parallelization to multi-agent-work-coordinator, unknown-defect hunting to bug-finder, concrete failures to debugging-investigator, migrations to codebase-evolution-controller, security-first questions to security-review, and implementation to the owning specialist.
Failure handling
If the repository is too large, state a bounded slice and expand breadth-first. If source/config disagree, report both and identify which governs runtime. If ownership cannot be proven, keep it unknown.
Stop conditions
Stop when the requested boundary, affected surfaces, confidence, and unresolved ambiguity are explicit enough for the next specialist to act safely.
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.