Skill Acquisition logo

Skill Acquisition

Community
tkellogg
skill-acquisition

Discover, evaluate, install, and wrap external agent skills from ClawHub registry, skillflag-compliant CLI tools, and GitHub repos. Use when asked to find new capabilities, install a skill, browse what's available, or package a local skill for sharing.

Overview

Publishertkellogg
Repositoryopen-strix
Skill nameskill-acquisition
Stars
95
Forks
21
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by tkellogg on GitHub. Read the source before you install it.

Installation

Install the Skill Acquisition 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/tkellogg/open-strix/tree/main/open_strix/builtin_skills/skill-acquisition
  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/tkellogg/open-strix.git /tmp/open-strix
mkdir -p .claude/skills
cp -r /tmp/open-strix/open_strix/builtin_skills/skill-acquisition .claude/skills/skill-acquisition
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Acquisition 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 Skill Acquisition 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 Skill Acquisition 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.

Skill Acquisition

You help users discover and install agent skills from the ecosystem. There are three main sources:

  1. ClawHub — Public skill registry (clawhub.ai) with vector search, versioning, and moderation
  2. Skillflag — CLI tools that bundle their own skills via --skill list/export
  3. GitHub/Raw — Skills as folders in git repos (SKILL.md + supporting files)

When to Use This Skill

USE when:

  • User asks to find/discover/search for skills or capabilities
  • User wants to install a skill from ClawHub or a CLI tool
  • User asks "is there a skill for X?"
  • User wants to package/publish a local skill
  • User asks about what skills are available

DON'T USE when:

  • User wants to CREATE a new skill from scratch (that's skill-creator)
  • User wants to modify an existing installed skill (just edit it)

Prerequisites

Both tools run via npx — no global install needed, just npm:

bash
# ClawHub CLI (primary discovery tool)
npx clawhub --help

# Skillflag installer (for CLI-bundled skills)
npx skillflag --help

Discovery — Finding Skills

1. ClawHub Search (best for general discovery)

ClawHub uses vector search (OpenAI embeddings), so natural language queries work:

bash
# Search by description
npx clawhub search "manage docker containers"
npx clawhub search "git workflow automation"

# Browse latest/trending
npx clawhub explore                          # newest 25
npx clawhub explore --sort trending          # trending now
npx clawhub explore --sort downloads         # most popular

# Machine-readable output
npx clawhub explore --json
npx clawhub search "kubernetes" --json

2. Skillflag Discovery (for CLI tools you already have)

Any skillflag-compliant CLI tool bundles its own skills:

bash
# List skills a tool provides
<tool> --skill list

# See what a skill contains
<tool> --skill show <id>

# JSON metadata (includes digest for integrity)
<tool> --skill list --json

Known skillflag-compliant tools:

  • acpx — ACP coding agent delegation
  • Check any CLI you install: <tool> --skill list (won't break if unsupported)

3. GitHub Search (for skills not on ClawHub)

bash
# Search GitHub for SKILL.md files
gh search code "filename:SKILL.md" --limit 20

# The openclaw/skills repo archives ALL ClawHub skills
# Browse: https://github.com/openclaw/skills/tree/main/skills

Evaluation — Before Installing

Always evaluate before installing:

bash
# Inspect without installing (ClawHub)
npx clawhub inspect <slug>                   # metadata + description
npx clawhub inspect <slug> --files           # list all files in the skill
npx clawhub inspect <slug> --file SKILL.md   # read the actual skill content

# Inspect a skillflag export
<tool> --skill show <id>                 # read SKILL.md content
<tool> --skill export <id> | tar -tf -   # list files without installing

Evaluation checklist:

  1. Read the SKILL.md — does it do what you need?
  2. Check required env vars / bins (metadata.openclaw.requires)
  3. Check file count and what's included (scripts? templates?)
  4. For ClawHub skills: check install count, version history, last update
  5. For GitHub skills: check repo stars, recent activity, author reputation

Installation — Getting Skills In Place

From ClawHub

bash
# Install to your skills directory
npx clawhub install <slug> --workdir "$(pwd)" --dir skills

From Skillflag CLI Tools

bash
# Into a custom directory (open-strix agents)
<tool> --skill export <id> | npx skillflag install --dest ./skills

From GitHub / Raw

bash
# Clone just the skill directory
git clone --depth 1 <repo-url> /tmp/skill-source
cp -r /tmp/skill-source/skills/<name> ./skills/<name>
rm -rf /tmp/skill-source

After Installing

Verify the skill appears in your prompt. Skills in skills/ are automatically loaded.

Wrapping — Adapting Skills for Your Agent

Raw skills from ClawHub/skillflag may need wrapping. The pattern:

When to Wrap

  • Skill assumes capabilities your agent doesn't have (e.g., coding ability)
  • Skill needs context about WHEN to use it (delegation logic)
  • Skill's SKILL.md is a CLI reference but you need behavioral guidance
  • Multiple related skills should be combined into one coherent capability

Wrapping Pattern

Create a wrapper skill that:

  1. Has its own SKILL.md with behavioral instructions (when/how to use)
  2. Includes the original skill as a reference doc (e.g., <name>-reference.md)
  3. Adds any agent-specific context (delegation, reporting, error handling)
skills/my-capability/
  SKILL.md              <- your wrapper (behavioral instructions)
  <tool>-reference.md   <- original skill content (CLI/API reference)

Example: wrap acpx into a coding skill — SKILL.md teaches delegation behavior, acpx-reference.md has the full CLI reference.

Publishing — Sharing Skills

bash
# Login (GitHub OAuth)
npx clawhub login

# Publish a skill directory
npx clawhub publish ./skills/my-skill \
  --slug my-skill \
  --name "My Skill" \
  --version 1.0.0 \
  --tags latest \
  --changelog "Initial release"

Requirements:

  • SKILL.md must have name and description in frontmatter
  • Only text-based files (no binaries), max 50MB
  • Published under MIT-0 (free use, no attribution required)

Security Notes

  • ClawHub has moderation and security analysis
  • Skillflag exports are tar streams with path traversal protection
  • Always inspect before installing from unknown sources
  • Skills may include scripts — review them before granting execution

References

  • /.open_strix_builtin_skills/skill-acquisition/clawhub-reference.md — Full ClawHub CLI reference
  • /.open_strix_builtin_skills/skill-acquisition/skillflag-reference.md — Skillflag specification and integration guide
  • ClawHub — Browse skills in the browser
  • Agent Skills Spec — The standard format

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 Skill Acquisition AI skill do?

Discover, evaluate, install, and wrap external agent skills from ClawHub registry, skillflag-compliant CLI tools, and GitHub repos. Use when asked to find new capabilities, install a skill, browse what's available, or package a local skill for sharing.

Why use Skill Acquisition on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tkellogg/open-strix/tree/main/open_strix/builtin_skills/skill-acquisition. 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 Skill Acquisition?

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 Skill Acquisition?

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

Is the Skill Acquisition AI skill free?

Yes. It is published on GitHub by tkellogg 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 👇