research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
Skill by KenSuh
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/kensuh-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: not checked yet.
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
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
Spin up a **background agent** to do the research, so you keep working while it reads. Its job: 1. Investigate the question against **primary sources** (official docs, source code, specs, first-party APIs), not a secondary write-up of them. Follow every claim back to the source that owns it. 2. Write the findings to a single Markdown file, citing each claim's source. 3. Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.
From KenSuh/open-agent-harness, MIT.
More from KenSuh/open-agent-harness
- 0.606score
gpt-5-4-prompting
KenSuh
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
humanize-korean
KenSuh
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
computer-use
KenSuh
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-scan
KenSuh
한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize
KenSuh
AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-redo
KenSuh
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
codex-cli-runtime
KenSuh
Internal helper contract for calling the codex-companion runtime from Claude Code
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
codex-result-handling
KenSuh
Internal guidance for presenting Codex helper output back to the user
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
codebase-design
KenSuh
Shared vocabulary for designing deep modules.
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
prototype
KenSuh
Build a throwaway prototype to answer a design question.
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
domain-modeling
KenSuh
Build and sharpen a project's domain model.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/KenSuh/open-agent-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.740score
research
mattpocock
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 302.4KClaude Code +9 - 0.406score
research
moeru-ai
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 664Claude Code +9 - 0.360score
research
chinkan
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 10Claude Code +9 - 0.353score
research
jd-solanki
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 7Claude Code +9 - 0.347score
research
tt-a1i
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillBFreshness: B★ 187Claude Code +9 - 0.346score
research
gongyijie85
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillBFreshness: B★ 24Claude Code +9 - 0.344score
research
schneidenbach
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillBFreshness: B★ 20Claude Code +9 - 0.342score
research
LatentDream
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 3Claude Code +9 - 0.341score
research
ItsEthanDev
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 2Claude Code +9 - 0.334score
research
TudeOrangBiasa
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 1Claude Code +9 - 0.332score
research
cskwork
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 3Claude Code +9 - 0.331score
research
fveracoechea
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
SkillAFreshness: A★ 1Claude Code +9
More from KenSuh
- 0.606score
gpt-5-4-prompting
KenSuh
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
humanize-korean
KenSuh
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
computer-use
KenSuh
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-scan
KenSuh
한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize
KenSuh
AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-redo
KenSuh
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능.
SkillAFreshness: A★ 3Claude Code +9
Cite this page
research skill. Agent Mart. https://agentmart.dev/skills/kensuh-research (last updated 2026-10-24)