Find Skills logo

Find Skills

Community
AgentTeam-TaichuAI
find-skills

MANDATORY: When a user asks to install, find, search, or add ANY skill (e.g. 'install hello-world skill', 'find a skill for X', 'add a skill'), you MUST first run `skills find <query>` to search the skills ecosystem. NEVER create a skill from scratch without searching first. Even if the name sounds simple, always search — it may already exist as a published skill.

Overview

PublisherAgentTeam-TaichuAI
RepositoryScienceClaw
Skill namefind-skills
Stars
670
Forks
73
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AgentTeam-TaichuAI on GitHub. Read the source before you install it.

Installation

Install the Find Skills AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AgentTeam-TaichuAI/ScienceClaw/tree/master/ScienceClaw/backend/builtin_skills/find-skills
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AgentTeam-TaichuAI/ScienceClaw.git /tmp/ScienceClaw
mkdir -p .claude/skills
cp -r /tmp/ScienceClaw/ScienceClaw/backend/builtin_skills/find-skills .claude/skills/find-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Find Skills in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Find Skills on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Find Skills is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Find Skills

This skill helps you discover and install skills from the open agent skills ecosystem.

CRITICAL RULES

  1. ALWAYS search first: When a user asks to install/find/add ANY skill, your FIRST action must be running skills find <query> in the sandbox.
  2. NEVER create from scratch without searching: Even for simple-sounding skills like "hello-world", search first.
  3. Use the CLI directly: The skills CLI is pre-installed globally in the sandbox. Use skills directly (NOT npx skills — npx causes unnecessary download prompts).
  4. Install to session workspace: Use HOME=<workspace_dir> skills add ... -g -y --agent '*' so skills land in the current session's workspace (visible in the task file viewer).
  5. Call propose_skill_save: After installing and testing a skill, ALWAYS call the propose_skill_save tool with the skill name so the user can choose to save it permanently.

When to Use This Skill

Use this skill when the user:

  • Asks to install a skill (e.g., "install hello-world skill", "安装一个 skill")
  • Asks to find or search for a skill (e.g., "find a skill for X", "找一个 skill")
  • Mentions a skill by name (e.g., "hello-world skill", "react testing skill")
  • Asks "how do I do X" where X might be a common task with an existing skill
  • Says "find a skill for X" or "is there a skill for X"
  • Asks "can you do X" where X is a specialized capability
  • Expresses interest in extending agent capabilities
  • Wants to search for tools, templates, or workflows

What is the Skills CLI?

The Skills CLI (skills) is pre-installed globally in the sandbox. It is the package manager for the open agent skills ecosystem.

IMPORTANT: Always use skills directly, NEVER use npx skills (npx will try to re-download and prompt for confirmation).

Key commands:

  • skills find [query] - Search for skills by keyword (use this FIRST)
  • HOME=<workspace_dir> skills add <package> -g -y --agent '*' - Install a skill to session workspace
  • skills list -g - List installed skills
  • skills check - Check for skill updates

Browse skills at: https://skills.sh/

How to Help Users Find Skills

Step 1: Check Locally Installed Skills FIRST

Before searching the online ecosystem, check if a matching skill is already installed locally. Locally installed skills are listed in your system prompt under "Available Skills" and live at /skills/<name>/SKILL.md.

  • If the user mentions a skill by name (e.g., "hello-world") and it appears in your available skills list → use it directly. Read its SKILL.md for instructions. No need to search online.
  • If the user wants to modify an existing local skill → skip find-skills entirely and go to skill-creator (phase 2 in the Skill Policy).
  • Only proceed to Step 2 if no local skill matches.

Step 2: Understand What They Need

When no local skill matches, identify:

  1. The domain (e.g., React, testing, design, deployment)
  2. The specific task (e.g., writing tests, creating animations, reviewing PRs)
  3. Whether this is a common enough task that a skill likely exists

Step 3: Search the Online Ecosystem

Run the find command with a relevant query:

bash
skills find [query]

For example:

  • User asks "how do I make my React app faster?" → skills find react performance
  • User asks "can you help me with PR reviews?" → skills find pr review
  • User asks "I need to create a changelog" → skills find changelog

The command will return results like:

Install with skills add <owner/repo@skill>

vercel-labs/agent-skills@vercel-react-best-practices
└ https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices

Step 4: Present Options to the User

When you find relevant skills, present them to the user with:

  1. The skill name and what it does
  2. The install command they can run
  3. A link to learn more at skills.sh

Example response:

I found a skill that might help! The "vercel-react-best-practices" skill provides
React and Next.js performance optimization guidelines from Vercel Engineering.

To install it:
skills add vercel-labs/agent-skills@vercel-react-best-practices

Learn more: https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices

Step 5: Install to Session Workspace

If the user wants to proceed, install the skill into the session workspace so it appears in the task file viewer. Use HOME=<workspace_dir> to redirect the global install path:

bash
HOME=<workspace_dir> skills add <owner/repo@skill> -g -y --agent '*'

Replace <workspace_dir> with your actual workspace directory (from the system prompt).

  • HOME=<workspace_dir> — redirects -g install to <workspace_dir>/.agents/skills/
  • -g installs globally (user-level, relative to HOME)
  • -y skips confirmation prompts
  • --agent '*' skips the interactive agent selection (REQUIRED in sandbox)

IMPORTANT: Never omit any of these flags. Without --agent '*' the command will hang waiting for interactive input.

Step 6: Test the Installed Skill

After installation, test the skill by reading its SKILL.md/TEMPLATE.md and following its instructions.

  • If it works → call propose_skill_save(skill_name="<skill-name>") to let the user save it permanently. Done!
  • If it does NOT fit the user's needs → do NOT keep trying to fix or adapt it. Uninstall it and go back to Step 4 to try the next candidate from the search results.

Step 7: Bail-Out — When to Stop Searching

Stop searching and escalate to skill-creator (create from scratch) when ANY of these is true:

  1. No results: skills find returned zero matches.
  2. Exhausted candidates: You have tried 2–3 different skills and none fit.
  3. Poor relevance: All search results are clearly unrelated to what the user needs.

When bailing out:

  1. Briefly tell the user: "I couldn't find a suitable existing skill. I'll create one from scratch."
  2. Read /builtin-skills/skill-creator/SKILL.md and follow it to create the skill.
  3. NEVER loop endlessly on an unsuitable skill. Move on.

Common Skill Categories

When searching, consider these common categories:

CategoryExample Queries
Web Developmentreact, nextjs, typescript, css, tailwind
Testingtesting, jest, playwright, e2e
DevOpsdeploy, docker, kubernetes, ci-cd
Documentationdocs, readme, changelog, api-docs
Code Qualityreview, lint, refactor, best-practices
Designui, ux, design-system, accessibility
Productivityworkflow, automation, git

Tips for Effective Searches

  1. Use specific keywords: "react testing" is better than just "testing"
  2. Try alternative terms: If "deploy" doesn't work, try "deployment" or "ci-cd"
  3. Check popular sources: Many skills come from vercel-labs/agent-skills or ComposioHQ/awesome-claude-skills

When No Skills Are Found

If no relevant skills exist after searching:

  1. Acknowledge that no existing skill was found.
  2. Immediately escalate to skill-creator: read /builtin-skills/skill-creator/SKILL.md and follow it to create the skill from scratch.
  3. Do NOT ask the user whether to proceed — just start creating. The user already expressed intent by asking for the skill.

Frequently asked questions

What does the Find Skills AI skill do?

MANDATORY: When a user asks to install, find, search, or add ANY skill (e.g. 'install hello-world skill', 'find a skill for X', 'add a skill'), you MUST first run `skills find <query>` to search the skills ecosystem. NEVER create a skill from scratch without searching first. Even if the name sounds simple, always search — it may already exist as a published skill.

Why use Find Skills on TypingMind?

Because you install it once and use it with any model. Find Skills is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Find Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgentTeam-TaichuAI/ScienceClaw/tree/master/ScienceClaw/backend/builtin_skills/find-skills. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Find Skills?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Find Skills?

As many as you like. As long as a model supports skills, you can use Find Skills with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Find Skills AI skill free?

It is published on GitHub by AgentTeam-TaichuAI. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇