Skip to content
Agent Orchestration
Skill

/research

Investigate an open question and return grounded, sourced findings

From plugin
oh-my-claudecode
39k39 skills21 agents21 commands11 hooks
+1
Install
$ npx -y skills add Yeachan-Heo/oh-my-claudecode --skill research --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/research

Context preview

The summary Claude sees to decide when to auto-load this skill.

Investigate an open question and return grounded, sourced findings

SKILL.md

research.SKILL.md
name: research
description: Investigate an open question and return grounded, sourced findings

Research

Use this skill when the next step depends on something not yet known. Research answers questions; it does not implement.

This is the canonical research lane. `deep-dive`, `sciomc`, and `autoresearch` route here.

Goal

Replace assumptions with evidence, and say plainly what remains uncertain.

Workflow

1. State the question precisely enough to know when it is answered. 2. Search the repo and its docs first — local evidence outranks recollection. 3. For external SDKs, frameworks, or APIs, consult official documentation. 4. Sweep more than one way when the answer could hide: by file, by symbol, by caller, by history. 5. Synthesize into findings, each tied to where it came from.

Scale

  • **Narrow lookup** — answer it directly.
  • **Multiple independent questions** — investigate in parallel.
  • **Unknown-size discovery** — keep going until additional passes surface nothing new.

Rules

  • Cite the source: file and line, or the document consulted.
  • Distinguish what was verified from what was inferred.
  • Report contradicting evidence rather than picking the tidier story.
  • Do not implement as a side effect of researching.

Output

  • The question
  • Findings, each with its source
  • What remains unknown or unverifiable
  • Recommended next step, if one follows
Ships withoh-my-claudecode

For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI. Liked OmC but found it a bit overkill? Try gajae-code.

Get the whole plugin

Other skills on oh-my-claudecode.