create-feature-catalog
Skill3 starsChanged 4 months agoApache-2.0View on GitHub
Deep-mine the source code to discover implemented features; writes ai/analysis/FEATURE_CATALOG.md.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/add-feature.mdcCursor rule
- .cursor/rules/adversarial-audit.mdcCursor rule
- .cursor/rules/ai-knowledge-layer.mdcCursor rule
- .cursor/rules/check-drift.mdcCursor rule
- .cursor/rules/cold-start.mdcCursor rule
- .cursor/rules/create-feature-catalog.mdcCursor rule
- .cursor/rules/fix-bug.mdcCursor rule
- .cursor/rules/perform-feature-add-simulation.mdcCursor rule
- .cursor/rules/post-cold-start-verification.mdcCursor rule
- .cursor/rules/review-agent-config.mdcCursor rule
- .cursor/rules/review-change.mdcCursor rule
- .cursor/rules/verify-ai-readiness.mdcCursor rule
- add-featureSkill
- cold-startSkill
- deep-testSkill
- fix-bugSkill
- review-changeSkill
- add-featureSkill
- adversarial-auditSkill
- check-docsSkill
- check-driftSkill
- cold-startSkill
- fix-bugSkill
- implement-specSkill
- perform-feature-add-simulationSkill
- post-cold-start-verificationSkill
- review-agent-configSkill
- review-changeSkill
- verify-ai-readinessSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 12
Start from user-visible surfaces: routes, UI entry points, CLI commands, public APIs.
- Very specific: line 25
Every entry [inferred]. Where a layer can't be confirmed, write "UNSURE".
- Very specific: line 26
Do not modify source. Update ai/guide/FEATURE_MAP.md candidate list to reference the catalog, nothing more.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
<!-- Copyright (c) 2026 Kunal Suri (CEA LIST). All rights reserved. -->Build the feature catalog — the highest-value artifact for agents. Budget significant
exploration; use repo-explorer for the heavy reading.
Method
- Start from user-visible surfaces: routes, UI entry points, CLI commands, public APIs. Each surface is a candidate feature.
- For each feature, trace the touch list across layers: UI, backend/services, persistence (tables/collections/files), and tests that exercise it.
- Cluster and name features the way a USER would name them, not by module names.
Output — ai/analysis/FEATURE_CATALOG.md
For every feature: name · business goal (one line) · touch list per layer · verifying tests · related features. End with two sections agents use most:
- "Where new code lives" — a decision tree from feature-type to target directories.
- The 3-file rule — for each feature, the 3 files to read first to understand it.
Rules
- Every entry
[inferred]. Where a layer can't be confirmed, write "UNSURE". - Do not modify source. Update
ai/guide/FEATURE_MAP.mdcandidate list to reference the catalog, nothing more. - Print a sampling guide at the end: the 5 entries a human should spot-check first (pick the ones you are least sure of).
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.

