How do I install the Metaclaw Manager skill?

Run npx skillmds@latest add yetone/metaclaw-manager in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Metaclaw Manager safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Metaclaw Manager?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Metaclaw Manager free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Metaclaw Manager?

yetone (@yetone) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Metaclaw Manager by yetone — Agent Skill

Name: Metaclaw Manager
Author: yetone

File contents

MetaClaw Manager

This skill enables MetaClaw to manage its own configuration and state through natural language commands.

Configuration File

MetaClaw uses metaclaw.toml for configuration. The file is located in the project root or can be specified via --config.

Reading Configuration

To check current settings, read the metaclaw.toml file:

ReadFile: metaclaw.toml

Modifying Configuration

Use EditFile to modify specific settings in metaclaw.toml. Common modifications:

Change LLM model:

[llm]
model = "claude"  # Options: claude, gpt4, gemini, azure, huggingface, or full provider/model string

Adjust agent behavior:

[agent]
max_iterations = 25
sandbox = "basic"  # Options: none, basic, docker

Enable/disable channels:

[channels.slack]
enabled = true

[channels.discord]
enabled = false

Environment Variables

API keys and secrets are stored in .env (never in metaclaw.toml). Common variables:

ANTHROPIC_API_KEY - Anthropic Claude
OPENAI_API_KEY - OpenAI GPT
GEMINI_API_KEY - Google Gemini
SLACK_BOT_TOKEN / SLACK_APP_TOKEN - Slack
DISCORD_BOT_TOKEN - Discord
TELEGRAM_BOT_TOKEN - Telegram

Skill Management

List installed skills:

metaclaw skill list

Install a skill:

metaclaw skill install <url-or-path>

Create a new skill:

metaclaw skill create <name> --desc "description"

Skills are stored in:

Project: .metaclaw/skills/
User: ~/.metaclaw/skills/

Channel Management

List channels:

metaclaw channel list

Start server with channels:

metaclaw start

Diagnostics

Check system status:

metaclaw version
pip show metaclaw

Test LLM connection:

from metaclaw.llm import LLMProvider
provider = LLMProvider(model="claude")
# await provider.chat(messages=[{"role": "user", "content": "test"}])

Guidelines

Never store API keys in metaclaw.toml - always use .env
When changing models, verify the API key env var is set
When enabling channels, guide the user through token setup
Back up metaclaw.toml before making changes
Test changes by restarting the agent

---name: metaclaw-managerdescription: Self-management skill for MetaClaw - configure LLM models, channels, skills, and all settings through natural languagelicense: MIT---# MetaClaw ManagerThis skill enables MetaClaw to manage its own configuration and state through natural language commands.## Configuration FileMetaClaw uses `metaclaw.toml` for configuration. The file is located in the project root or can be specified via `--config`.### Reading ConfigurationTo check current settings, read the `metaclaw.toml` file:```ReadFile: metaclaw.toml```### Modifying ConfigurationUse EditFile to modify specific settings in `metaclaw.toml`. Common modifications:**Change LLM model:**```toml[llm]model = "claude" # Options: claude, gpt4, gemini, azure, huggingface, or full provider/model string```**Adjust agent behavior:**```toml[agent]max_iterations = 25sandbox = "basic" # Options: none, basic, docker```**Enable/disable channels:**```toml[channels.slack]enabled = true[channels.discord]enabled = false```## Environment VariablesAPI keys and secrets are stored in `.env` (never in `metaclaw.toml`). Common variables:- `ANTHROPIC_API_KEY` - Anthropic Claude- `OPENAI_API_KEY` - OpenAI GPT- `GEMINI_API_KEY` - Google Gemini- `SLACK_BOT_TOKEN` / `SLACK_APP_TOKEN` - Slack- `DISCORD_BOT_TOKEN` - Discord- `TELEGRAM_BOT_TOKEN` - Telegram## Skill Management**List installed skills:**```bashmetaclaw skill list```**Install a skill:**```bashmetaclaw skill install <url-or-path>```**Create a new skill:**```bashmetaclaw skill create <name> --desc "description"```Skills are stored in:- Project: `.metaclaw/skills/`- User: `~/.metaclaw/skills/`## Channel Management**List channels:**```bashmetaclaw channel list```**Start server with channels:**```bashmetaclaw start```## Diagnostics**Check system status:**```bashmetaclaw versionpip show metaclaw```**Test LLM connection:**```pythonfrom metaclaw.llm import LLMProviderprovider = LLMProvider(model="claude")# await provider.chat(messages=[{"role": "user", "content": "test"}])```## Guidelines- Never store API keys in metaclaw.toml - always use .env- When changing models, verify the API key env var is set- When enabling channels, guide the user through token setup- Back up metaclaw.toml before making changes- Test changes by restarting the agent

Frequently asked questions

Metaclaw Manager