Web Research · IN-DEPTH PROFILE

research Skill

Research delegates a focused question to a background agent, directing it to primary sources and asking it to save cited findings in one Markdown file in the repository's existing notes location.

View listed source ↗Installation guide ↓
Best for

Engineers gathering source-backed technical facts

What you get

Investigate technical facts + Delegate reading work

Main limitation

The result is limited by the chosen question and the sources found; a cited note is not proof that every relevant source was covered.

First risk

Inference presented as a sourced fact. Secondary claims or stale documents can distort an implementation decision. Prefer the source that owns each claim, distinguish uncertainty, and re-check evidence before relying on it.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-09-23

Pinned revision · c55ee460

Open pinned commit ↗
SkillSignal profileSource-grounded

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

IN PLAIN ENGLISH

What it does—and when it fits

Research delegates a focused question to a background agent, directing it to primary sources and asking it to save cited findings in one Markdown file in the repository's existing notes location.

This is aimed at Engineers gathering source-backed technical facts. Compare the examples below with your task, then review the limitations, permissions, and risks before installing.

What you get
  • Investigate technical factsTrace claims to official documentation, source code, specifications, or first-party APIs.
  • Delegate reading workLet a background agent gather evidence while the main session continues.
  • Keep results in the repositoryCreate one cited Markdown artifact following the project's existing note conventions.
What makes it different
  • This profile is manually organized around the current upstream SKILL.md workflow.
  • The capability boundary remains explicitly tied to mattpocock/skills.
  • Core uses, limitations, and risks are separated for pre-install review.
Community signalskills.sh All-time: #74 · 567.4K installs

No verified review text is in the current dataset. Use the linked source for the latest discussion.

Read the source note ↗

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project install (recommended)
npx skills add https://github.com/mattpocock/skills --skill research --agent claude-code
Personal install
npx skills add https://github.com/mattpocock/skills --skill research --agent claude-code -g

Project install stays with this repository for team sharing. Personal install adds -g and works across repositories.

View install paths
Project path.claude/skills/research/
Personal path~/.claude/skills/research/
Official agent docs

Claude Code discovers custom Skill folders automatically at project or personal scope.

View path evidence ↗

TYPICAL WORKFLOW

A practical workflow

01

Investigate technical facts

Trace claims to official documentation, source code, specifications, or first-party APIs.

02

Delegate reading work

Let a background agent gather evidence while the main session continues.

03

Keep results in the repository

Create one cited Markdown artifact following the project's existing note conventions.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. This profile is manually organized around the current upstream SKILL.md workflow.
  2. The capability boundary remains explicitly tied to mattpocock/skills.
  3. Core uses, limitations, and risks are separated for pre-install review.

Limitations

  1. The result is limited by the chosen question and the sources found; a cited note is not proof that every relevant source was covered.
  2. A background research agent may be unavailable in some environments, and saved findings can become stale as sources change.

COMPARE THE TRADEOFF

Consider these close alternatives

These are deterministic nearby candidates, not paid placements or a universal ranking. Open the full profile before choosing.

01

Same job family · native to Codex + Claude Code

copilot-spaces

Ground Copilot work in curated project knowledge spaces.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Pinned · 1f564408
Open copilot-spaces profile ↗
02

Same job family · native to Codex + Claude Code

summarize

Turn long-form web, audio and document inputs into structured briefs.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Editorial source
Open summarize profile ↗
03

Same job family · native to Codex + Claude Code

brave-search

Fast web discovery and content extraction through Brave Search.
Tradeoff to check
Detailed package files are not fully catalogued.
First risk
Review before install · Medium
Source state
Editorial source
Open brave-search profile ↗
Compare more in the directory →

BEST FIT

Who it is for

→

Engineers gathering source-backed technical facts

→

Teams that need a traceable research note before implementation

BEFORE YOU USE IT

Risks to review before use

Medium

Inference presented as a sourced fact

Secondary claims or stale documents can distort an implementation decision. Prefer the source that owns each claim, distinguish uncertainty, and re-check evidence before relying on it.

Medium

Upstream instruction drift

Behavior can change with upstream updates. Record the commit used for important workflows and review updates before adoption.

SECURITY

What the permission profile means

  • Declared access remains governed by the current upstream SKILL.md and runtime requests.
  • Treat repository files, web content, and tool output as untrusted input.
  • SkillSignal has not independently executed or security-audited this package; external skills.sh labels are not SkillSignal certification.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

COMMON QUESTIONS

research Skill FAQ

What is the research Skill?

Research delegates a focused question to a background agent, directing it to primary sources and asking it to save cited findings in one Markdown file in the repository's existing notes location.

How do I install the research Skill?

Open and review the listed source, choose the project or personal path for your Agent, then verify the first run in a controlled project. Open the listed skills.sh page and upstream repository; verify the current SKILL.md.

Is the research Skill safe to use?

SkillSignal checked the source on 2026-09-23, but that is not a runtime test or security certification. Review the “Inference presented as a sourced fact” risk first and begin with the least access required.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream Skill instructionsSource-linked

TAGS

researchprimary-sourcesdocumentation

Manually expanded from the current upstream SKILL.md and linked source at mattpocock/skills, checked 2026-08-20. This is an original summary, not an execution result or security certification.