workflow-research-codebase
This skill should be used when conducting comprehensive codebase research to answer questions, understand architecture, or prepare context for implementation planning. It spawns parallel sub-agents and synthesizes findings into a structured research document.
npx skills add majiayu000/claude-skill-registry --skill workflow-research-codebase --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.
# Research Codebase Workflow ## Overview Conduct comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings into a structured research document. **Type:** FLEXIBLE - Adapt research depth and agent spawning to the complexity of the question. **Output:** `research.md` with YAML frontmatter containing findings, code references, and architecture insights. ## When to Use Use this workflow when: - Exploring unfamiliar parts of a codebase - Preparing context for implementation planning - Understanding how existing features work - Answering architectural questions - Gathering context before creating PRDs or implementation plans **Announce at start:** "I'm using the research-codebase workflow to investigate this thoroughly." ## Initial Setup When this workflow is invoked, respond with: ``` I'm ready to research the codebase. Please provide your research question or area of interest, and I'll analyze it thoroughly by exploring relevant components and connections. ``` Then wait for the user's research query. ## Steps to Follow ### Step 1: Read Directly Mentioned Files First If the user mentions specific files (tickets, d
- Overview
- When to Use
- Initial Setup
- Steps to Follow
- Step 1: Read Directly Mentioned Files First
- Step 2: Analyze and Decompose the Research Question
- Step 3: Spawn Parallel Sub-Agent Tasks
- Step 4: Wait and Synthesize
- Step 5: Gather Metadata
- Step 6: Generate Research Document
- Step 7: Sync and Present Findings
- Step 8: Handle Follow-Up Questions
- Important Notes
- Critical Ordering
What does the workflow-research-codebase skill do?
This skill should be used when conducting comprehensive codebase research to answer questions, understand architecture, or prepare context for implementation planning. It spawns parallel sub-agents and synthesizes findings into a structured research document.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill workflow-research-codebase --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.