research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
Skill by netname
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/netname-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 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
- upstream: mattpocock/skills · invocation: model · adapted-for: pi · upstream-path: skills/engineering/research · upstream-commit: c55ee46073ed923f86ce59a5eb3b6d895095d1b7
- Instructions
- 40 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Dispatch one detached `mp-researcher` child to do the research, so you keep working while it reads. This skill runs through `pi-subagents`, so before launching, confirm the `subagent` tool is available (registered by the `pi-subagents` extension; `pi list --approve` shows it). If it is missing, stop and print: ``` pi install npm:pi-subagents ``` Then confirm the child's web tools are registered: `web_search`, `fetch_content`, `get_search_content`, and `source_check` (from `pi-web-access`). If any is missing, stop and print: ``` pi install npm:pi-web-access ``` A missing tool is a setup failure, not permission to do the research yourself or to weaken the citation guarantee. Then: 1. Give the child the question in the asker's own terms, and give it a **unique, explicit output path** for its note (for example `.scratch/research/<name>.md`) through the `subagent` call's `output:` field, so two concurrent children can never pick the same file. 2. Launch it detached (`async: true`) with a fresh, isolated context, and save its run identity. 3. Collect its result before the question is considered answered: read the returned note (the run reports where its `output:` artifact landed — a relative path may be routed under `pi-subagents`' managed artifact storage) and persist it to the repo path you chose. 4. A child that fails, is refused, is abandoned, or is still running leaves the question **unresolved and visible**. Report it as not completed, with the reason, and never fill the gap with uncited prose. 5. Answer with the child's findings, naming where the cited note was saved. The child investigates **primary sources** (official docs, source code, specs, first-party APIs), follows every claim back to the source that owns it, and writes a single cited Markdown file. That output contract lives in `mp-researcher`; the dispatch mechanics (fresh vs. fork, run identity, steering, cancellation) belong to the bundled `pi-subagents` skill.
From netname/pi-adapted-mp-skills, MIT.
More from netname/pi-adapted-mp-skills
- 0.529score
git-guardrails
netname
Set up guardrails that block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they run.
SkillBFreshness: BClaude Code +9 - 0.504score
diagnosing-bugs
netname
Diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
netname
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
code-review
netname
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 - 0.499score
codebase-design
netname
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
prototype
netname
Build a throwaway prototype to answer a design question.
SkillBFreshness: BClaude Code +9 - 0.499score
tdd
netname
Test-driven development.
SkillBFreshness: BClaude Code +9 - 0.496score
improve-codebase-architecture
netname
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillBFreshness: BClaude Code +9 - 0.496score
setup-matt-pocock-skills
netname
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout.
SkillBFreshness: BClaude Code +9 - 0.496score
to-spec
netname
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 - 0.496score
to-tickets
netname
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 - 0.496score
triage
netname
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
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 19, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/netname/pi-adapted-mp-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from netname
- 0.529score
git-guardrails
netname
Set up guardrails that block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they run.
SkillBFreshness: BClaude Code +9 - 0.504score
diagnosing-bugs
netname
Diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.499score
prototype
netname
Build a throwaway prototype to answer a design question.
SkillBFreshness: BClaude Code +9 - 0.499score
codebase-design
netname
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
netname
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
code-review
netname
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
Cite this page
research skill. Agent Mart. https://agentmart.dev/skills/netname-research (last updated 2026-10-24)