research
Investigate a question against high-trust primary sources and capture the findings as a cited Markdown file in the repo.
Skill by Fatih0234
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.
About
Use cases: documents, backend, research, agent-building
Reviews
Write a reviewNo 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
- 0.488score
prototype
Fatih0234
Build a throwaway prototype to answer a design question.
SkillBFreshness: BClaude Code +9 - 0.488score
domain-modeling
Fatih0234
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.488score
tdd
Fatih0234
Test-driven development.
SkillBFreshness: BClaude Code +9 - 0.488score
codebase-design
Fatih0234
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.488score
code-review
Fatih0234
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillBFreshness: BClaude Code +9 - 0.485score
triage
Fatih0234
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
SkillBFreshness: BClaude Code +9 - 0.485score
improve-codebase-architecture
Fatih0234
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillBFreshness: BClaude Code +9 - 0.485score
to-spec
Fatih0234
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
SkillBFreshness: BClaude Code +9 - 0.485score
to-tickets
Fatih0234
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker…
SkillBFreshness: BClaude Code +9 - 0.485score
wayfinder
Fatih0234
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time…
SkillBFreshness: BClaude Code +9 - 0.482score
ask-matt
Fatih0234
Ask which skill or flow fits your situation.
SkillBFreshness: BClaude Code +9 - 0.477score
implement
Fatih0234
Implement a piece of work based on a spec or set of tickets.
SkillBFreshness: BClaude Code +9
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
- Source
- GitHubgithub-graphql
More from Fatih0234
- 0.520score
prototype
Fatih0234
Build a throwaway prototype to answer a design question.
SkillBFreshness: B★ 2Claude Code +9 - 0.520score
tdd
Fatih0234
Test-driven development.
SkillBFreshness: B★ 2Claude Code +9 - 0.520score
codebase-design
Fatih0234
Shared vocabulary for designing deep modules.
SkillBFreshness: B★ 2Claude Code +9 - 0.520score
domain-modeling
Fatih0234
Build and sharpen a project's domain model.
SkillBFreshness: B★ 2Claude Code +9 - 0.520score
code-review
Fatih0234
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillBFreshness: B★ 2Claude Code +9 - 0.520score
grilling
Fatih0234
Grill the user relentlessly about a plan, decision, or idea.
SkillBFreshness: B★ 2Claude Code +9
Cite this page
research skill. Agent Mart. https://agentmart.dev/skills/fatih0234-research (last updated 2026-10-24)