code-surgeon-context-researcher
Use when analyzing a codebase to select relevant files, build dependency maps, and extract architectural patterns for informed implementation planning
npx skills add majiayu000/claude-skill-registry --skill code-surgeon-baagad-ai-code-surgeon-2 --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.
# code-surgeon Context Researcher ## Overview **context-researcher** is the most complex sub-skill. It receives requirements and framework information, then performs deep codebase analysis to select relevant files, understand dependencies, and extract team conventions. **Core principle:** Transform a requirement into deeply-understood codebase context that enables precise, informed implementation planning. --- ## When to Use This skill runs in **Phase 2** of code-surgeon orchestration, after Issue Analyzer and Framework Detector complete. **Input from:** - Issue Analyzer: `{issue_type, requirements[], file_hints}` - Framework Detector: `{primary_language, frameworks[], is_monorepo}` - Main Orchestrator: `{repo_root, depth_mode}` **Output to:** - Implementation Planner (Phase 3) --- ## The Challenge Context Researcher must answer: **"What in this codebase is relevant to this requirement?"** For a 500K line codebase: - ❌ Can't load all files (token explosion) - ❌ Can't parse full AST (too slow, 100+ seconds) - ❌ Can't guess blindly (might miss critical code) - ✅ Must intelligently select relevant files - ✅ Must understand file relationships - ✅ Must respect token budget - ✅ Must comp
- Overview
- When to Use
- The Challenge
- Analysis Pipeline
- Step 1: Preparation (30 seconds)
- Step 2: File Discovery (1 minute)
- Step 3: Dependency Mapping (1 minute)
- Step 4: Pattern Extraction (1 minute)
- Step 5: Team Conventions Extraction (30 seconds)
- Step 6: Content Extraction (2 minutes)
- Step 7: Caching for Performance (30 seconds)
- Output Format
- Depth Modes
- QUICK Mode (30K tokens)
What does the code-surgeon-context-researcher skill do?
Use when analyzing a codebase to select relevant files, build dependency maps, and extract architectural patterns for informed implementation planning
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill code-surgeon-baagad-ai-code-surgeon-2 --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.