Skip to main content
skill CX Codex

investigation — Claude Code skill: scaffold a research folder

Builds a dated folder under scratch/ with a README and checklist for one code investigation. Useful when you need to follow data flow or map an unfamiliar system.

BSD-3-Clause-Clear 1 installs ★ 624 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add talmolab/sleap --skill investigation -a claude-code
Open on GitHub

What investigation does

The skill creates scratch/{YYYY-MM-DD}-{descriptive-name} inside your repo and puts a README.md there: what you are looking into, the background, and a checklist you tick off as answers appear. Scripts and data files land in the same folder. A big job can be split into numbered sub-documents.

Investigations come in a few loose shapes that often overlap. Tracing follows calls or data forward and backward from one component. Architecture work starts at entry points and walks every layer. Bugs go through reproduction, root-cause tracing and a proposed fix. Feasibility work writes throwaway scripts to see whether an idea holds. Design research compares options and records the trade-offs, with numbered design questions (DQ1, DQ2) when decisions come in rounds.

Standalone scripts are meant to run through uv with inline dependencies; code that imports the project is called with python directly. External packages get cloned into scratch/repos/ when you need to read their source. The catch: scratch/ sits in .gitignore, so nothing there reaches a commit. Findings have to be pasted into the PR description, since a PR that points at scratch files is not self-contained.

What it helps with

  • trace where a value comes from and where it goes
  • map an unfamiliar codebase layer by layer
  • reproduce a bug and pin down its root cause
  • test whether an idea is feasible with a throwaway script
  • compare API design options before writing code

Example prompts for the agent

  • Start an investigation: trace from load_labels to the file write.
  • Figure out why test_predict fails and keep the notes in an investigation folder.
  • Gather context on the export API and lay out the design alternatives.

How to install investigation

1Skills CLI (Vercel)

npx skills add talmolab/sleap --skill investigation -a claude-code

2Manually: put the files in place

~/.claude/skills/investigation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/investigation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about investigation

How do I install investigation in Claude Code?

Run npx skills add talmolab/sleap --skill investigation -a claude-code. The skill ends up at ~/.claude/skills/investigation/SKILL.md.

What does the investigation skill do?

It creates a dated folder in scratch/ for a single question, with a README holding the task and a checklist, then scripts and data for the actual digging. The work itself can be tracing, architecture mapping, a bug hunt, a feasibility test or design research.

Do the scratch notes end up in git?

No, that folder is in .gitignore. Copy the findings into the PR description yourself, because references to scratch files will not survive in the repository.

Similar skills

All skills for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open