context-gatherer
Phase 0.1 — Automatic codebase scan before PRD generation. Extracts key terms from the user prompt, searches the codebase for related files, identifies existing patterns, and generates context.md in the state directory.
npx skills add majiayu000/claude-skill-registry --skill context-gatherer --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.
# Context Gatherer Runs **automatically as Phase 0.1**, before `idea-explorer` asks its first question. Purpose: ground the entire spec in the actual codebase — not assumptions. ## Slug generation Derive `{slug}` from the user's prompt before doing anything else: 1. Lowercase the full prompt string 2. Remove punctuation 3. Split into words; skip stop words: `a an the to for of in with from and or but is are was` 4. Take the first 6 significant words 5. Join with hyphens; truncate to 60 characters **Example:** ``` Prompt: "Allow personal trainers to connect with students after checkout" Slug: allow-personal-trainers-connect-students-checkout ``` ## When to run - Always runs before the first `idea-explorer` question - If `.claude/feature-state/{slug}/context.md` already exists: **load it** (do not re-scan — resume flow) - Rerun from scratch only when explicitly asked ## Step 1: Extract key terms from the user prompt Parse the user's feature prompt for: - **Entities**: nouns that likely map to data models (e.g., "student", "trainer", "subscription") - **Actions**: verbs that describe behavior (e.g., "connect", "enroll", "notify", "list") - **Domain words**: business-specific terms (e.
- Slug generation
- When to run
- Step 1: Extract key terms from the user prompt
- Step 2: Search the codebase for related files
- Step 3: Read project context files
- Step 4: Extract existing patterns
- Architecture patterns
- Naming conventions
- Similar features
- Existing entities related to the prompt
- Step 5: Generate context.md
- Step 6: Surface to user before first question
- Output location
mkdir -p .claude/feature-state/{slug}What does the context-gatherer skill do?
Phase 0.1 — Automatic codebase scan before PRD generation. Extracts key terms from the user prompt, searches the codebase for related files, identifies existing patterns, and generates context.md in the state directory.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill context-gatherer --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.