← Back to Skills Marketplace
280
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install whois
Description
Initialize and configure OpenClaw agent workspace MD files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, BOOTSTRAP.md, HEARTBEAT.md). Use when: settin...
Usage Guidance
This skill otherwise appears coherent for creating and updating OpenClaw workspace files, but stop and review before running any automatic installer. The included script suggests installing 'uv' via piping a script from https://astral.sh/install.sh — downloading and running shell scripts from an unknown domain is risky. Before using the skill: (1) Inspect the install script at the URL yourself (do not pipe blindly to sh); (2) prefer installing 'uv' via your OS/package manager or a verified release if available; (3) run the check-env script in a safe/test environment or container first; (4) back up existing AGENTS.md/SOUL.md/etc. and confirm the skill won't overwrite critical sections (SKILL.md instructs to extend not replace — follow that); (5) confirm the container and workspace paths are correct for your instance; and (6) avoid putting secrets into generated workspace MD files because they are injected into prompts every turn.
Capability Analysis
Type: OpenClaw Skill
Name: whois
Version: 1.0.0
The skill automates OpenClaw agent workspace initialization but employs several high-risk patterns. Specifically, `scripts/check-env.sh` and `SKILL.md` utilize `curl | sh` to download and execute a remote installation script for the 'uv' package manager from astral.sh. Furthermore, the skill performs broad filesystem writes and `docker exec` commands to modify core agent instruction files (like `SOUL.md` and `AGENTS.md`). While these capabilities are plausibly required for the stated purpose of workspace setup, the use of unverified remote execution and the potential for injecting malicious instructions into the agent's permanent configuration via the interactive interview phase constitute significant security risks.
Capability Assessment
Purpose & Capability
Name, description, and included templates/scripts align with the stated goal of initializing OpenClaw workspace MD files. The files (SKILL.md, templates, workspace guide) and the check-env script are coherent for generating and writing agent workspace files.
Instruction Scope
Runtime instructions are focused on interviewing the user, checking environment, and showing/writing workspace files to host or container. They require reading the existing AGENTS.md and other workspace files and run docker exec or file-write commands as expected. The SKILL.md also instructs never to include secrets and to show generated content before writing — which is responsible. However, the instructions include an optional automatic install step that downloads and executes a script from a remote host (astral.sh), which expands the skill's scope to performing network installs on the target system.
Install Mechanism
There is no formal install spec, but scripts/check-env.sh uses curl -LsSf https://astral.sh/uv/install.sh | sh to install 'uv' when run with --install. Downloading and piping an arbitrary install script from an external personal/unknown domain is a high-risk install pattern because the script will be executed with shell privileges and there is no signature or checksum verification. The rest of the skill is instruction-only and writes files via cat/docker exec (expected).
Credentials
The skill does not request environment variables, credentials, or config paths beyond reading/writing workspace files. That is proportional to the described task. Minor oddity: .claude/settings.local.json contains a permission allowing a specific git ls-files command against a local path (/Users/clawdbot/.../data/skills/agent-init/), which looks like a leftover local test/permission entry but does not itself require new credentials.
Persistence & Privilege
always is false and the skill does not claim to force-enable itself or modify other skills. It writes per-agent workspace files and uses container/host write methods as expected. No elevated persistent privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install whois - After installation, invoke the skill by name or use
/whois - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of agent-init skill for OpenClaw agent workspace setup.
- Adds interactive interview workflow to gather context before generating agent files.
- Automates creation of key workspace MD files: AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, BOOTSTRAP.md, HEARTBEAT.md.
- Supports both container and external (host) OpenClaw instances.
- Enforces use of "uv" for Python environment management; never uses pip directly.
- Protects core AGENTS.md template: always extends, never replaces critical sections.
- Displays each generated file for user confirmation before writing.
Metadata
Frequently Asked Questions
What is agent-init?
Initialize and configure OpenClaw agent workspace MD files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, BOOTSTRAP.md, HEARTBEAT.md). Use when: settin... It is an AI Agent Skill for Claude Code / OpenClaw, with 280 downloads so far.
How do I install agent-init?
Run "/install whois" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is agent-init free?
Yes, agent-init is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does agent-init support?
agent-init is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created agent-init?
It is built and maintained by teamclaw (@szsip239); the current version is v1.0.0.
More Skills