Advai Skill logo

Advai Skill

Organization
advai-x
advai-skill

Manages local skills with `advai skill`, including search, install, list, update, sync, unsync, uninstall, and platform path management. Invoke when user wants to add, maintain, or distribute skills.

Overview

Publisheradvai-x
Repositoryadvai-skills
Skill nameadvai-skill
Stars
78
Forks
0
Bundled files
Instructions only
LicenseMIT
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 advai-x on GitHub. Read the source before you install it.

Installation

Install the Advai Skill 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/advai-x/advai-skills/tree/main/skills/advai-skill
  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/advai-x/advai-skills.git /tmp/advai-skills
mkdir -p .claude/skills
cp -r /tmp/advai-skills/skills/advai-skill .claude/skills/advai-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Advai Skill 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 Advai Skill 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 Advai Skill 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.

Advai Skill Manager

Use this skill to manage local skills and sync them into supported agent platforms through advai skill.

When to Invoke

Invoke this skill when the user wants to:

  • Search installable skills before choosing one
  • Install a skill by name from a source provider or from a GitHub repository URL
  • List, inspect, update, or uninstall installed skills
  • Sync a skill into Cursor, Claude Code, Codex, TRAE, or another supported platform
  • Configure custom skill platforms or override global or project-relative paths
  • Troubleshoot where a skill is installed or synced

Do not use this skill for creating a brand-new skill definition from scratch unless the user specifically wants to manage that skill after creation.

Core Commands

Discover and inspect:

bash
advai skill search <query>
advai skill search <query> --source <provider>
advai skill list
advai skill info <name>

Install and update:

bash
advai skill install <skill-name>
advai skill install <skill-name> --source <provider> --version <version>
advai skill install <skill-name> --platform <key> --sync-mode copy
advai skill install <skill-name> --platform <key> --project-dir <dir>
advai skill install <github-url>
advai skill install <github-url> --skill <name> --platform <key>
advai skill update [name]

Sync and remove:

bash
advai skill sync <name> --platform <key>
advai skill sync <name> --platform <key> --platform <key>
advai skill sync <name> --platform <key> --project-dir <dir> --force
advai skill unsync <name> --platform <key>
advai skill uninstall <name>

Manage platform metadata:

bash
advai skill platform list
advai skill platform list --project-dir <dir>
advai skill platform add <key> --name <name> --path <dir> --category custom
advai skill platform add <key> --name <name> --path <dir> --project-path .agent/skills
advai skill platform override <key> --path <dir> --project-path .agent/skills
advai skill platform clear-override <key>
advai skill platform remove <key>

Preconditions

  • This skill depends on the advai CLI from https://github.com/Advai-X/advai-cli.
  • Ensure advai is installed and available on PATH.
  • Ensure the advai skill subcommand is available in the current installation.
  • If advai skill is missing, stop and guide the user to install or upgrade advai from https://github.com/Advai-X/advai-cli.
  • Start with advai skill list and advai skill platform list when the local skill state is unclear.

Operating Guidelines

  • Use advai skill search <query> before installation when the user does not already know the exact skill name.
  • Use --source <provider> to constrain installs or searches to a specific skill source.
  • Use --version <version> only when the user explicitly wants a pinned version.
  • Use a GitHub repository URL when the user wants to install directly from a repo instead of a named registry entry.
  • Use --skill <name> when a GitHub repo contains multiple skills and the user wants only one.
  • Use repeated --platform <key> flags when the user wants the same skill synced into multiple targets.
  • Use --sync-mode symlink for fast local iteration and copy for portable snapshots.
  • Use --project-dir when a platform supports project-local skill folders and the user wants repo-scoped behavior.
  • Use platform add with --project-path when defining a custom platform that supports project-local sync targets.
  • Use platform override to adjust built-in or custom paths without redefining the whole platform.
  • Use platform remove only for custom platforms; use clear-override to reset path overrides on existing platforms.
  • If advai skill is not recognized at runtime, direct the user to install or upgrade advai from https://github.com/Advai-X/advai-cli.

Examples

Search and inspect:

bash
advai skill search browser --limit 10
advai skill info advai-browser

Install and sync to a platform:

bash
advai skill install advai-browser --source github --platform trae

Install directly from a GitHub repository:

bash
advai skill install https://github.com/Advai-X/advai-skills --skill advai-browser --platform trae

Inspect platform targets for a project:

bash
advai skill platform list --project-dir /path/to/project

Add a custom platform with project-local support:

bash
advai skill platform add my-agent --name "My Agent" --path ~/.my-agent/skills --project-path .my-agent/skills

Resync a changed skill:

bash
advai skill sync my-skill --platform trae --force

Frequently asked questions

What does the Advai Skill AI skill do?

Manages local skills with `advai skill`, including search, install, list, update, sync, unsync, uninstall, and platform path management. Invoke when user wants to add, maintain, or distribute skills.

Why use Advai Skill on TypingMind?

Because you install it once and use it with any model. Advai Skill 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 Advai Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/advai-x/advai-skills/tree/main/skills/advai-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Advai Skill?

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 Advai Skill?

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

Is the Advai Skill AI skill free?

Yes. It is published on GitHub by advai-x under the MIT license. 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 👇