Agent skill · Documentation

investigate-create-doc

Investigate a codebase topic and produce structured markdown documentation. Collects investigation scope, explores the code, and writes a README plus sub-docs for each area. Use when the user asks to investigate, spike, research, analyze, or document how something works in the codebase.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill investigate-create-doc --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/analysis/investigate-create-doc/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Investigate & Document Investigate a codebase topic and produce a structured set of markdown documents with findings. ## Phase 1 — Scope the Investigation Use AskQuestion to collect: ### 1. Topic Ask: "What should I investigate?" — free text. Examples: - "How account context works" - "All the ways we fetch user data" - "The authentication flow" ### 2. Context Ask: "Any context I should know before starting?" — free text, optional. Examples: - "We're planning to refactor this area" - "Focus on hooks that query GraphQL" - "Related to ticket RETIRE-1874" ### 3. Known areas / entry points Ask: "Any specific files, functions, or areas I should start from?" — free text, optional. ### 4. Directory name Suggest a kebab-case name derived from the topic. Ask the user to confirm or override. Output goes to: `docs/{directory-name}/` --- ## Phase 2 — Define Questions (DO NOT INVESTIGATE YET) The goal of this phase is to understand **what needs to be answered**, not to answer anything. 1. Do a **light** codebase scan — just enough to identify the shape of the problem (file names, export names, rough structure). Do NOT read full files or trace consumers yet. 2. From the topic, context, and ligh

What's inside
Steps it walks through
  1. Phase 1 — Scope the Investigation
  2. 1. Topic
  3. 2. Context
  4. 3. Known areas / entry points
  5. 4. Directory name
  6. Phase 2 — Define Questions (DO NOT INVESTIGATE YET)
  7. Review: one call, all areas
  8. Phase 3 — Plan the Investigation
  9. Phase 4 — Investigate Each Area (Parallel Subagents)
  10. Subagent prompt template
  11. After all subagents return
  12. Phase 5 — Write the Documents
  13. Directory structure
  14. README.md format
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the investigate-create-doc skill do?

Investigate a codebase topic and produce structured markdown documentation. Collects investigation scope, explores the code, and writes a README plus sub-docs for each area. Use when the user asks to investigate, spike, research, analyze, or document how something works in the codebase.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill investigate-create-doc --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.

Keep going