Skills mattpocock skills Engineering workflow

research

Use it when:
You need facts about an API, library or topic checked against their source, without stopping your work.
It does:
Starts a background agent that reads primary sources: official docs, source code, specs and first-party APIs.
You get:
One Markdown file in your repo, with a source cited for each claim.
Needs:
An agent that can run subagents in the background.

Skill 7 of 24 in the Engineering workflow bundle, after domain-modeling and before handoff.

TL;DR

It hands the reading to a background agent, so you and the main agent keep working. That agent investigates the question against primary sources, such as official docs, source code, specs and first-party APIs, rather than second-hand write-ups, and follows each claim back to the source that owns it. The findings go into a single Markdown file with a citation for each claim, saved in the folder where your repo keeps similar notes; if there's none, it picks a place and tells you where.

Summarizes the skill at 5beb35b. Its SKILL.md has changed by 7 words since.

npx skills add https://github.com/mattpocock/skills --skill research
Total Downloads
782,612 on skills.sh, Nov 9, 2026
Repo stars
318,714 mattpocock/skills
First seen
Jul 2, 2026 on skills.sh
Weekly Downloads
31K
-19% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 2138,186
Sep 2834,526
Oct 535,076
Oct 1244,719
Oct 1937,348
Oct 2633,920
Nov 234,879
Nov 930,995
Category

Articles, docs, internal comms, research write-ups and prose that doesn't read as generated.

Type

A multi-step process the agent follows: interview, debug, run a TDD loop, review.

Effect

Its own steps create or change files, git state or local tools.

Needs

Relies on the agent being able to spawn subagents.

Publisher

Everyone else. Unverified vendor claims default to community.

Topics

SKILL.md

From mattpocock/skills at a496f55. Checked daily, last changed Oct 30, 2026.

Frontmatter
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. Start it with a fresh context window.

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.