enterprise-discover
Deep codebase learning agent. Run FIRST on any new project, any new worktree, or whenever hardcoded paths break. Produces stack-profile.json, stack-traps.json, and stack-best-practices.json that all enterprise-* skills consume. Supports incremental mode — only re-scans what changed since last profile. Without this, the pipeline guesses — and guesses wrong.
npx skills add majiayu000/claude-skill-registry --skill enterprise-discover --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Enterprise Discover — Deep Stack Learning Agent You are profiling a codebase you have never seen before. Your job: produce structured JSON profiles that tell every downstream enterprise skill exactly where things live, how to run tests, what conventions to follow, and what landmines to avoid. This skill exists because hardcoded paths kill portability. When enterprise-build assumes `npx jest` and the project uses `pytest`, the pipeline breaks. Discovery eliminates these assumptions. --- ## WHEN TO TRIGGER - **Always**: as Stage 0 of `/enterprise` on any project without existing profile JSONs - **Always**: when switching to a new codebase or monorepo package - **Always**: when a downstream skill fails due to wrong paths, wrong test commands, or wrong conventions - **On demand**: `/enterprise-discover` standalone - **Incremental**: when profile exists but `profiled_commit != HEAD` — only re-run affected phases --- ## OUTPUT FILES All files written to `.claude/enterprise-state/`: | File | Purpose | |------|---------| | `stack-profile.json` | Structure, commands, conventions — the primary config | | `stack-traps.json` | Type/schema/convention traps that will break code | | `stack-best
- WHEN TO TRIGGER
- OUTPUT FILES
- INCREMENTAL MODE
- PIPELINE: 5 PHASES
- Phase 1: SCAN (3 parallel agents)
- Phase 2: DEEP ANALYZE (4 parallel agents, needs Phase 1 results)
- Phase 3: RESEARCH (web search, needs Phase 1 results)
- Phase 4: SYNTHESIZE
- Phase 5: PRESENT
- PROJECT PROFILE TEMPLATE (generated from JSON)
- USAGE BY DOWNSTREAM SKILLS
- Stack Resolution Preamble (copy into each skill)
- Conditional Blocks
Search for auth patterns across the codebase Search for tenant isolation patterns grep -rn "tenant_id\|organization_id\|org_id\|account_id\|workspace_id\|team_id" $SOURCE_DIR --include="*.$EXT" Check for RLS policies grep -rn "CREATE POLICY\|ROW LEVEL SECURITY" $MIGRATION_DIR --include="*.sql" Verify test framework is installed and configured Check test config files exist ls jest.config* vitest.config* pytest.ini .rspec 2>/dev/null Run a quick test to confirm the command works
What does the enterprise-discover skill do?
Deep codebase learning agent. Run FIRST on any new project, any new worktree, or whenever hardcoded paths break. Produces stack-profile.json, stack-traps.json, and stack-best-practices.json that all enterprise-* skills consume. Supports incremental mode — only re-scans what changed since last profile. Without this, the pipeline guesses — and guesses wrong.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill enterprise-discover --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.