← Back to Skills Marketplace
Agent Creator
by
maverick-software
· GitHub ↗
· v1.0.0
· MIT-0
392
Downloads
0
Stars
15
Active Installs
1
Versions
Install in OpenClaw
/install agent-creator
Description
Create a new AI agent identity (SOUL.md, IDENTITY.md, AGENTS.md) and package it as a .skill file ready to upload to ClawHub. Use when a user wants to create,...
README (SKILL.md)
Agent Creator
Generates the three core identity files for a new OpenClaw agent, packages them as a .skill file, and optionally publishes to ClawHub.
Workflow
Step 1 — Gather Agent Details
Ask the user (or infer from context) for:
| Field | Example |
|---|---|
| Name | Aria |
| Emoji | ✨ |
| Nature | AI companion — sharp, reliable, with genuine care |
| Vibe | Warm but direct. Smart without being showy. |
| Serving | Solo founders who need a reliable thinking partner |
| Slug | aria (auto-derived from name; user can override) |
| Version | 1.0.0 |
Minimum required: name, nature, vibe. Everything else has sensible defaults.
Step 2 — Generate & Package
Run the bundler script:
python3 ~/.openclaw/workspace/skills/agent-creator/scripts/create_agent_bundle.py \
--name "Aria" \
--emoji "✨" \
--nature "AI companion — sharp, reliable, with genuine care" \
--vibe "Warm but direct. Smart without being showy." \
--serving "Solo founders who need a reliable thinking partner" \
--slug aria \
--version 1.0.0 \
--output-dir ~/.openclaw/workspace/skills/dist
This produces ~/.openclaw/workspace/skills/dist/aria.skill.
Step 3 — Upload to ClawHub (optional)
If the user wants to publish:
# Login first (one-time)
clawhub login
# Publish
clawhub publish ~/.openclaw/workspace/skills/dist/aria.skill \
--slug aria \
--name "Aria" \
--version 1.0.0 \
--changelog "Initial release"
Step 4 — Install on a Target Agent (optional)
To apply the identity to a running OpenClaw agent, copy the workspace files:
# Extract the skill
unzip -o ~/.openclaw/workspace/skills/dist/aria.skill -d /tmp/aria-skill
# Copy to target agent workspace
cp /tmp/aria-skill/aria/assets/workspace-template/SOUL.md /path/to/workspace/
cp /tmp/aria-skill/aria/assets/workspace-template/IDENTITY.md /path/to/workspace/
cp /tmp/aria-skill/aria/assets/workspace-template/AGENTS.md /path/to/workspace/
# Restart the gateway
systemctl --user restart openclaw-gateway # or delay-restart for VPS
Output Structure
The .skill file contains:
{slug}/
├── SKILL.md ← Install instructions for the agent
└── assets/
└── workspace-template/
├── SOUL.md ← Personality & values
├── IDENTITY.md ← Name, emoji, avatar
└── AGENTS.md ← Operational rules & memory system
Template Placeholders
The templates in assets/workspace-template/ use {{PLACEHOLDER}} tokens:
| Token | Filled With |
|---|---|
{{AGENT_NAME}} |
Agent's name |
{{AGENT_EMOJI}} |
Agent's emoji |
{{AGENT_NATURE}} |
One-line nature description |
{{AGENT_VIBE}} |
Personality vibe |
{{AGENT_SLUG}} |
URL-safe slug |
{{AGENT_AVATAR}} |
Avatar path (default: not yet set) |
{{DATE}} |
Today's date |
Notes
- Output dir defaults to
~/.openclaw/workspace/skills/dist/— create it if needed - Slug must be lowercase letters, digits, and hyphens only
- The
.skillfile is a zip archive — inspect withunzip -l {file}.skill - For VPS agents, use
(sleep 3 && systemctl restart openclaw.service) &before sending final reply
Usage Guidance
This skill appears coherent for creating and packaging agent identity files and does not request credentials or perform remote installs. Before using it: (1) review the generated SOUL.md / AGENTS.md / IDENTITY.md contents to ensure they don't instruct the agent to access or exfiltrate sensitive files; (2) be cautious about the AGENTS.md line 'Don't ask permission. Just do it.' — consider editing it to require user consent for external or sensitive actions; (3) inspect the produced .skill ZIP before publishing to ClawHub; (4) only run the documented systemctl restart steps if you have proper access and have tested in a safe environment; and (5) avoid uploading to public registries until you’ve validated the skill contents for your security/privacy requirements.
Capability Analysis
Type: OpenClaw Skill
Name: agent-creator
Version: 1.0.0
The agent-creator skill is a legitimate developer utility designed to generate and package AI agent identity files (SOUL.md, IDENTITY.md, AGENTS.md). The included Python scripts (create_agent_bundle.py, package_skill.py, and quick_validate.py) contain security-conscious features, such as path-traversal checks and a scanner that warns users if hardcoded API keys are detected in the generated bundles. While the documentation suggests commands for restarting system services (systemctl), these are contextually appropriate for installing a new agent identity and do not show evidence of malicious intent.
Capability Assessment
Purpose & Capability
Name/description, templates (SOUL.md, IDENTITY.md, AGENTS.md), and scripts all align with building and packaging an agent identity .skill file. The presence of local packaging scripts is expected for this task. No unrelated environment variables, binaries, or external services are required by the skill itself.
Instruction Scope
SKILL.md instructs the user/agent to generate templates, package a .skill, optionally publish with the clawhub CLI, and copy files into agent workspaces, including restarting the gateway. The AGENTS.md template explicitly tells an agent to read workspace files (SOUL.md, USER.md, memory/*.md) — which is expected for an identity package — but also contains a concerning phrase ('Don't ask permission. Just do it.') that encourages the agent to act without consent. The restart/systemctl steps are documented as manual/administrative actions; they are within scope but require local privileges and caution.
Install Mechanism
No install spec, no network downloads, and packaging uses only local Python scripts and the stdlib (zipfile, tempfile). The packager includes reasonable checks (no symlink following, avoids packaging files outside the skill root). No high-risk install behavior found.
Credentials
The skill declares no required env vars, no primary credential, and the code does not attempt to read credentials or call external APIs. quick_validate has a fallback YAML parser to avoid hard dependency on PyYAML, which is benign. There are no requests for unrelated secrets or config paths.
Persistence & Privilege
always is false and the skill is user-invocable (normal). The skill does not request persistent or system-wide privileges. However, SKILL.md advises restarting system services (systemctl) when applying identity changes — this is a normal administrative operation but requires user privileges and care. The AGENTS.md guidance to 'Don't ask permission' increases risk if an agent follows it autonomously.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-creator - After installation, invoke the skill by name or use
/agent-creator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: generates SOUL.md, IDENTITY.md, AGENTS.md and packages them as a .skill file ready for ClawHub upload
Metadata
Frequently Asked Questions
What is Agent Creator?
Create a new AI agent identity (SOUL.md, IDENTITY.md, AGENTS.md) and package it as a .skill file ready to upload to ClawHub. Use when a user wants to create,... It is an AI Agent Skill for Claude Code / OpenClaw, with 392 downloads so far.
How do I install Agent Creator?
Run "/install agent-creator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Creator free?
Yes, Agent Creator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Creator support?
Agent Creator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Creator?
It is built and maintained by maverick-software (@maverick-software); the current version is v1.0.0.
More Skills