creep-spreadlisted

Analyze project artifacts and generate a populated CONTEXT.md (or CONTEXT-MAP.md and multiple CONTEXT.md files for multi-context repos) with domain terms extracted from existing code, documentation, and configuration. Use when seeding a new hive, analyzing an existing project, or enriching an existing CONTEXT.md. Trigger on: "generate a domain glossary", "create a CONTEXT.md from project artifacts", "analyze project artifacts for domain terms", "enrich CONTEXT.md with terms from project", "update CONTEXT.MD", "update CONTEXT-MAP.md", "update project context definitions".
brenpike/hivemind · ★ 0 · AI & Automation · score 59

Install: claude install-skill brenpike/hivemind

## Quick Reference Before: - [ ] Project root resolved via `git rev-parse --show-toplevel` - [ ] Project root resolved and artifact files accessible - [ ] At least one project artifact readable (README.md, CLAUDE.md, package manifest, or source files) After: - [ ] CONTEXT.md or CONTEXT-MAP.md created following canonical format - [ ] Terms extracted from actual project artifacts, not invented - [ ] General programming terms excluded per CONTEXT-FORMAT.md Rules # Creep Spread Analyze a project's existing artifacts and generate a populated domain glossary following the canonical format defined in `${CLAUDE_PLUGIN_ROOT}/skills/plan-interrogation/references/CONTEXT-FORMAT.md`. ## When to Use - New project adopting the hivemind plugin (called by seed-hive) - Existing project that lacks a CONTEXT.md - Existing project where CONTEXT.md needs enrichment with newly discovered terms - After significant project changes (new modules, renamed concepts) ## Required Inputs None. Operates on the current project root resolved via `git rev-parse --show-toplevel`. ## Procedure 1. Resolve project root via `git rev-parse --show-toplevel`. Stop blocked if not a git repository. 2. **Mode detection:** Check for existing context files at the project root. - If `<project root>/CONTEXT-MAP.md` exists: set `mode: update-multi`. Read existing CONTEXT-MAP.md and all referenced per-context CONTEXT.md files. Extract existing term names (lines matching `**Term**:` pattern) into a known-terms set