Find Out
Research/discovery orchestrator for open-ended questions whose answer may span multiple current, external, historical, or authenticated sources and where choosing the research surface is part of the task. Use when the user explicitly invokes /find-out or asks for broad, current, multi-source research. Do not trigger for ordinary codebase, issue-tracker, document, or conversation-history investigation with a known local source, even if the user says "find out", "look into", "dig into", or "explore"; use the relevant local tool directly. Sibling of /find-skills (skills only) and /research (sourc
Install
npx skills add thatmike1/claude-skills --skill find-outgit clone --depth 1 https://github.com/thatmike1/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/find-out ~/.claude/skills/find-outPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# /find-out Turn an open-ended research question into a deliberate, multi-tool pass. The value is **routing** when the answer surface is genuinely uncertain, not wrapping routine local investigation in a research workflow. ## Activation Use this skill when at least one applies: - the user explicitly invokes `/find-out` - the question asks for broad or current research across multiple source types - the correct research surface is unclear and selecting it is a meaningful part of the task - the answer needs external citations, authenticated pages, or a combination of code, history, and current documentation Do not use it when a named repository, issue tracker, document set, or conversation history is the obvious source. A phrase such as "find out", "look into", "dig into", or "explore" is not sufficient by itself. ## The toolbox | Tool | Reach for it when | |---|---| | **`oc`** (`/web-browsing-cli`) | **first line for both search and page reading** — see oc below | | **context7** (`resolve-library-id` → `query-docs`) | library / framework / SDK / API / CLI docs — even well-known ones. Beats web search for anything versioned. | | **Exa** (`./exa.py`) | semantic search when a keyword query misses the concept; second fetch path when `oc` exits 2 | | **perplexity_ask** | quick web-grounded answer with citations; "current state of X", recent facts. **Costs prepaid credits** — not free |
Details
- Skill name
find-out- Repository
- thatmike1/claude-skills
- Path
find-out/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Find Out skill do?
Research/discovery orchestrator for open-ended questions whose answer may span multiple current, external, historical, or authenticated sources and where choosing the research surface is part of the task. Use when the user explicitly invokes /find-out or asks for broad, current, multi-source research. Do not trigger for ordinary codebase, issue-tracker, document, or conversation-history investigation with a known local source, even if the user says "find out", "look into", "dig into", or "explore"; use the relevant local tool directly. Sibling of /find-skills (skills only) and /research (sourc
How do I install the Find Out skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add thatmike1/claude-skills --skill find-out. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Find Out popular?
It lives in thatmike1/claude-skills, which has 10 GitHub stars and 1 forks.
Related skills
Afk Prompt
10thatmike1/claude-skills
Write a copy-paste prompt that hands one or more tasks (usually beads issues) to a fresh Claude instance to run autonomously while the user is away — no questions, no waiting for input. Includes picking which tasks are safe to run unattended. Use when the user says they're going AFK (shower, lunch, errand, overnight), asks "which tasks can just run without me", or wants an autonomous/batch prompt. For attended sessions the user will steer, use the live-prompt skill instead.
AI CV Scanner
10thatmike1/claude-skills
Mine Claude Code conversation history to answer questions about your AI experience. Scans session indexes, spawns parallel subagents to deep-dive relevant conversations, and drafts evidence-based answers. Use when user mentions CV, AI experience, questionnaire, scan my conversations, or needs to document their AI usage.
Arena
10thatmike1/claude-skills
Give several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.
Cue Buddy
8sensedeal/cue-skills
Use when the user wants to author / validate / debug / test / tune / pin-as-frequent a Cue 搭子(buddy) research template for a recurring scenario (corporate-credit pre-diligence, compliance snapshot, earnings review, private-fund DD, etc.) via natural conversation. Triggers: 创建搭子 / 做一个 X 搭子 / 调试模板 / 测试我的搭子 / 提交模板 / 设为常用 / design a buddy for X / mark template as frequent. Public-data tool surface only — refuse for private-data scenarios (real AML / medical diagnosis / internal accounting).
Idea to Spec
9pasqal-io/agent-marketplace
Turn a source describing a neutral-atom (Rydberg) experiment — a paper, a patent, a PDF, an arXiv ID, an idea note, or a protocol described in conversation — into a structured experiment_spec.json: register, drive, scan, observable, open questions. The spec is the input contract for spec-to-sequence, validate-emu, qpu-submit and harvest-and-analyze. Triggered by phrases like "turn this paper into a neutral-atom experiment spec", "extract the Rydberg protocol", "idea to spec".
Cue Capital Operations
8sensedeal/cue-skills
用 Cue 跑「资本运作」场景的深度研究:多源公开数据交叉、结论带来源。 Run Cue deep research for the "Capital Operations" scenario. 触发 Triggers: 资本运作、公司事件与资本运作、信披与监管 / capital operations, M&A, private placement
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.