Research

SkillAI & models

The research skill is a skill for AI agents that investigates an open question and returns grounded, sourced findings. It gives the agent a structured way to do research work and hand back results with sources attached, so the person using the agent can see where the findings come from.

Use Research in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Research and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Research skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have an AI agent that supports loading skills.

ResearchStart free

What your AI can do with it

  • Investigate an open question on the agent's behalf
  • Return findings that are grounded rather than unsourced
  • Attach sources to the findings it returns
  • Run as a skill the agent can invoke when research is needed

Getting started

  1. Have an AI agent that supports loading skills.
  2. Add the research skill to the agent's available skills.
  3. Ask the agent an open question and let it use the skill to investigate and return sourced findings.

What this skill tells your AI

The instructions your AI receives, as published by yeachan-heo/oh-my-claudecode in skills/research/SKILL.md and read by ahel’s review.

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

Signals

GitHub stars
39k
Forks
4k
Last commit
Oct 2026
Hacker News mentions
20

Questions

What is a research skill?
It is a skill an AI agent can use to investigate an open question and return findings with sources, so the results are grounded rather than unsourced.
What are some examples of research skills?
This item describes one research skill: investigating an open question and returning grounded, sourced findings. It does not list other examples.
What are the six research skills?
This item does not define a set of six research skills. It describes a single skill for investigating open questions and returning sourced findings.
What are the four main types of research skills?
This item does not categorize research skills into four types. It covers one skill: investigating an open question and returning grounded findings with sources.
How do the findings include sources?
The skill returns findings with sources attached, so the results it hands back are grounded and traceable.
Advanced
Item type
skill
Key
research-yeachan-heo
Source
github.com/yeachan-heo/oh-my-claudecode