Find Install Skills logo

Find Install Skills

OrganizationPopular
omnimind-ai
find-install-skills

Find and install relevant Omnibot skills. Use when the user asks "找个 skill", "有没有这个功能的 skill", "find a skill for X", "is there a skill for X", or wants to extend the agent with an installable workflow.

Overview

Publisheromnimind-ai
RepositoryOmniBot
Skill namefind-install-skills
Stars
2K
Forks
142
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by omnimind-ai on GitHub. Read the source before you install it.

Installation

Install the Find Install 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.
  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/omnimind-ai/OmniBot.git /tmp/OmniBot
mkdir -p .claude/skills
cp -r /tmp/OmniBot/app/src/main/assets/builtin_skills/find-install-skills .claude/skills/find-install-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Find Install 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 Install 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 Install 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

CRITICAL: NEVER use npx skills add to install skills. Always use the bundled git-clone-based installer script (install_with_skills_cli.sh) for installation. npx skills find is allowed only for searching. Installation MUST go through the script.

Use this skill to discover, compare, and install skills for Omnibot.

This version is adapted from the open vercel-labs/skills idea, but the workflow is aligned with Omnibot's phone runtime, .omnibot/skills workspace, built-in skill store, and agent tools.

Local First

Before searching the internet:

  1. Use skills_list to see what is already installed or bundled.
  2. If a likely match exists but its full body is not loaded this turn, use skills_read.
  3. Prefer reusing an installed skill over recommending a duplicate.

When To Use

Use this skill when the user:

  • asks how to extend Omnibot with a new capability
  • asks "找个 skill" or "有没有这个功能的 skill"
  • asks "find a skill for X" or "is there a skill for X"
  • wants a reusable workflow for a domain such as testing, frontend, deployment, docs, or automation
  • shares a skill repository link and wants help evaluating or installing it

Discovery Workflow

  1. Identify the domain and the concrete task.
  2. On the phone agent, search for candidate skills only by running a {{OMNIBOT_TERMINAL_DISTRIBUTION}} command.
  3. Use terminal_execute to run npx skills find <query>.
  4. Search with concrete keywords such as react performance, playwright e2e, pr review, android diagnostics, or changelog.

Do not use browser search, repository browsing, or skills.sh as the primary search path for the phone agent. Skill discovery on phone should happen through the command line with npx skills find.

The phone runtime usually installs npm and can run npx skills, so npx skills find should be the default and only search path for phone skill discovery. Do not use npx skills add for installation. Use the bundled git-clone-based installer script for the final install step.

Quality Checks

Do not recommend a skill from a search snippet alone. Verify:

  • the source repository or publisher is trustworthy
  • the repository looks maintained
  • install count or adoption looks reasonable when that signal is available
  • the skill directory really contains SKILL.md
  • the workflow fits Omnibot's runtime and does not depend on unavailable tooling without warning

How To Present Options

When you find a candidate, tell the user:

  1. the skill name
  2. the source repo or path
  3. what problem it solves
  4. why it looks trustworthy
  5. whether it appears compatible with Omnibot
  6. whether you can install it now or should confirm first

Keep the list short. Usually give the best 1 to 3 options.

Installation Guidance

NEVER use npx skills add. Always use the bundled install_with_skills_cli.sh script.

Only install a skill after the user confirms.

  • Do NOT use npx skills add under any circumstances. Use the bundled installer script instead.
  • If the skill is already bundled or installed, point the user to the existing skill instead of duplicating it.
  • If the user provides a GitHub skill path, install that exact skill directory into .omnibot/skills/<skill-id>/.
  • Preserve the full skill layout: SKILL.md plus any scripts/, references/, assets/, or evals/.
  • Do not overwrite an existing skill directory without confirmation.
  • After installation, verify it appears in skills_list.

Skills CLI

  • use terminal_execute to run raw npx skills find ... only for searching candidate skills
  • for the phone agent, do not use browser search or manual website browsing as the discovery path
  • NEVER use npx skills add for installation — this is strictly forbidden; always use the bundled git-clone-based installer script
  • Omnibot does not read .agents/skills as its primary runtime skill root
  • the bundled script clones the GitHub repository directly and copies skill folders into .omnibot/skills

Use the script like this:

bash
sh <scriptsDir>/install_with_skills_cli.sh claude-office-skills/skills@excel-automation
sh <scriptsDir>/install_with_skills_cli.sh vercel-labs/skills --skill find-skills
sh <scriptsDir>/install_with_skills_cli.sh https://github.com/vercel-labs/agent-skills --skill frontend-design

The script does all of the following:

  1. parses the source into a GitHub URL and an optional skill name filter
  2. runs git clone --depth 1 to fetch the repository into a temporary directory
  3. scans for skill directories (folders containing SKILL.md)
  4. copies matched skills into Omnibot's .omnibot/skills/
  5. fails fast if the target skill already exists

Summary:

  • search: only through terminal_execute running npx skills find ...
  • install into Omnibot: use sh <scriptsDir>/install_with_skills_cli.sh ...
  • if you already know the exact package, prefer the one-line form like owner/repo@skill

When No Good Match Exists

  1. Say that no strong skill match was found.
  2. Offer to help with the task directly.
  3. If the workflow is likely to repeat, suggest creating a custom skill with skill-creator.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Find Install Skills AI skill do?

Find and install relevant Omnibot skills. Use when the user asks "找个 skill", "有没有这个功能的 skill", "find a skill for X", "is there a skill for X", or wants to extend the agent with an installable workflow.

Why use Find Install Skills on TypingMind?

Because you install it once and use it with any model. Find Install 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 Install Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/omnimind-ai/OmniBot/tree/main/app/src/main/assets/builtin_skills/find-install-skills. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Find Install 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 Install Skills?

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

Is the Find Install Skills AI skill free?

It is published on GitHub by omnimind-ai. 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 👇