Skip to content
Agentmart
Submit a tool

research

Investigate a question against high-trust primary sources and capture findings as a markdown file in the repo.

Skill by lynchypin

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lynchypin-research

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Investigate a question against high-trust primary sources and capture findings as a markdown file in the repo. Spins up a background agent so the main conversation keeps working while it reads.

Use cases: documents, research, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/research

What's inside

Skill name
research
Description
Investigate a question against high-trust primary sources and capture findings as a markdown file in the repo. Spins up a background agent so the main conversation keeps working while it reads.
License
MIT
Instructions
36 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Research

Investigate a question against primary sources — official docs, source
code, specs, first-party APIs — not secondary write-ups. Follow every
claim back to the source that owns it.

## Process

1. **Spin up a background agent** so the main conversation keeps
   working while it reads.

2. The background agent's job:
   - Investigate the question against **primary sources only**.
   - Write findings to a single markdown file, citing each claim's
     source.
   - Save where the repo already keeps such notes; if no convention
     exists, use `docs/research/`.

3. When the research agent completes, summarize key findings back to
   the caller (wayfinder or the user).

## What counts as a primary source

- Official documentation (not blog posts about the docs)
- Source code of the library/tool in question
- Published specifications (RFCs, W3C specs, language specs)
- First-party API references
- The project's own code and git history

## What this skill must never do

- Never cite secondary sources as the authority — trace back to primary.
- Never guess when the answer is findable.
- Never block the main conversation — always use a background agent.

From lynchypin/project-onboard, MIT.

More from lynchypin/project-onboard

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 5, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from lynchypin

Cite this page

research skill. Agent Mart. https://agentmart.dev/skills/lynchypin-research (last updated 2026-10-24)