Research

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

by mattpocock

Source

Install

Copy install prompt for AI

Natural-language prompt you can paste into any Claude conversation. Claude Code installs it to ~/.claude/skills/research/; claude.ai and Claude Desktop adopt it for the current chat and tell you how to save it permanently.

Copy install command

curl -fsSL https://spellbook.build/i/research | bash

Drops the file into ~/.claude/skills/research/SKILL.md. The script is plain shell — inspect it by dropping the | bash.

Download skill folder

Download .zip

A research/ folder with SKILL.md (and any supporting files) — unzip into ~/.claude/skills/.

Benchmarks

This skill isn't in a benchmarked category yet. Set metadata.type in the frontmatter to activate scorecards.

Skill content

---
name: research
description: Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
---

Spin up a **background agent** to do the research, so you keep working while it reads.

Its job:

1. Investigate the question against **primary sources** — official docs, source code, specs, first-party APIs — not a secondary write-up of them. Follow every claim back to the source that owns it.
2. Write the findings to a single Markdown file, citing each claim's source.
3. Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.

engineering research