Skip to content
Back to skills

Research

ASecurity

Investigate an open question and return grounded, sourced findings

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 13, 2026
ai-agentsgogitapidocumentation

Works with

  • api
  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 13, 2026

npx -y skills add 1225Sakura/oh-my-deepseekharness --skill research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Research?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/1225sakura-research/badge)](https://www.skillsdirectory.com/skills/1225sakura-research)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: research
description: Investigate an open question and return grounded, sourced findings
when-to-use: The next step depends on something not yet known — codebase facts, external SDK/framework/API behavior, history. Research answers questions; it does not implement. Not for stateful iterative improvement loops (use autoresearch).
---

# 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. OMC's retired `deep-dive` / `sciomc` lanes converge here; in omd, `autoresearch` is a separate stateful improvement loop, not a research entry point.

## 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 — `grep` / `glob` / `read`; local evidence outranks recollection.
3. For external SDKs, frameworks, or APIs, consult official documentation via `web_search` / `read_page`.
4. Sweep more than one way when the answer could hide: by file, by symbol, by caller, by history (`git log` / `git_diff`).
5. Synthesize into findings, each tied to where it came from.

## Scale

- **Narrow lookup** — answer it directly.
- **Multiple independent questions** — investigate in parallel: spawn background `subagent`s (`omd-agent-explore` for code questions, `omd-agent-document-specialist` for external documentation).
- **Unknown-size discovery** — keep going until additional passes surface nothing new.

## Rules

- Cite the source: file and line, or the document/URL 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

## State Contract (状态契约)

Research **holds no mode state**. Findings are delivered as the final message (when running as a subagent) or the session summary; durable facts worth keeping go to `mcp__omd-state__notepad_write_priority` / `notepad_write_working`. Research itself creates no files under `.omd/state/`.

Files in this skill

  • SKILL.md2.2 KB
  • SKILL.zh.md2.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.