research

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

IndexedMIT

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/jamesdebatty-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.

About

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.

Use cases: documents, backend, research, agent-building

Reviews

Write a review

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 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.
License: MIT
Metadata: updated: 2026-09-06 · use-case: 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.
Instructions: 11 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
openai.yaml · agents/

SKILL.md (first lines)

# Research

Investigate the question against primary sources: official documentation, source code, specifications, and first-party APIs. Follow substantive claims to the source that owns them and distinguish observed facts from inference or unresolved gaps.

Read and cite the exact version or revision relevant to the question. When comparing behavior across versions, inspect both revisions; a current description does not establish what an earlier release did.

Handle a focused lookup directly. Delegate a bounded question when independent useful work can proceed alongside it and the harness permits delegation. Before spawning, read the current-harness Entry contract in `~/.agents/pstack-models.md`. Use `research worker` for investigation or `bulk reader` for bounded extraction. Pass `model@effort` as Codex `model` and `reasoning_effort`, or Claude Code `model` and `effort`; `inherit-parent@inherit-parent` omits both.

Capture findings and source links in the repository's existing research-note location, or a sensible task-owned Markdown file when no convention exists. Stop when the requested question is answered to the stated evidence standard or the remaining gap requires unavailable input. State that gap precisely.

From jamesdebatty/skills, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Sep 8, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/jamesdebatty/skills
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from jamesdebatty

Cite this page

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