Skip to content
Agentmart
Submit a tool

research

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

Skill by Fatih0234

IndexedMIT
Write a review

Chalk Labs

Need help deploying research?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/fatih0234-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 the findings as a cited Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to an isolated agent.

Use cases: documents, backend, 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 the findings as a cited Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to an isolated agent.
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

Delegate the research to the Pi `researcher` agent so the reading happens in an isolated context. The parent waits for the dispatch to finish; this is not a detached background job.

## Process

1. Decide where the repository keeps research notes. Match an existing convention. If none exists, choose a sensible final path and state it.
2. Create a unique scratch directory at `.scratch/pi-agents/research-<timestamp>/` and assign `research.md` as the agent's only writable artifact.
3. Capture `git status --short`, then invoke the Pi `subagent` tool with one `runs.run` child using agent `researcher`, `context: "fresh"`, `worktree: false`, and `async: false`. Include:
   - The exact research question and practical decision it informs.
   - Relevant repository paths and version constraints.
   - The scratch artifact's exact path.
   - The final destination you intend to use after validation.
4. The researcher must investigate **primary sources** such as official documentation, source code, specifications, and first-party APIs. Every material factual claim needs a citation to the source that owns it.
5. After delegation, compare `git status --short` with the captured state. The only new path attributable to the researcher must be the assigned scratch artifact. Stop and report any unexpected change.
6. Read the complete artifact. Check that it answers the question, separates fact from inference, cites every material claim, and records uncertainty.
7. Promote the validated report to the chosen final path. The parent performs this write so an existing project document is never replaced without review. Report both the final path and the scratch source.

If the `subagent` tool is unavailable, perform the same research in the current session and write the final artifact directly. Disclose that the research was not context-isolated.

From Fatih0234/mattpocock-skills-pi, MIT.

More from Fatih0234/mattpocock-skills-pi

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 27, 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 Fatih0234

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get research running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying research?

CallGet help
Cite this page

research skill. Agent Mart. https://agentmart.dev/skills/fatih0234-research (last updated 2026-10-24)