Latest release: v0.1.2Download zip
Capabilities
Compatibility
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the contents: SKILL.md, references, and two helper scripts (init_skill.py, quick_validate.py) implement scaffolding and validation for creating OpenClaw skills. Required env vars/binaries are none, which is proportionate for a documentation + helper-script bundle.
Instruction Scope
SKILL.md and the bundled scripts instruct the agent or operator to read/write under /home/ubuntu/skills and to run the included Python scripts. This is expected for a skill-initializer/validator, but it means the skill will read and create files in that specific path (and the validator reads SKILL.md frontmatter). The SKILL.md also references packaging/sending SKILL.md via a 'message' tool (frontend delivery) which is a normal workflow but results in the skill file being transmitted to the frontend.
Install Mechanism
No install spec and no network downloads; this is an instruction-only bundle with bundled scripts. Nothing writes arbitrary external code at install-time and the included scripts are plain Python source.
Credentials
The skill declares no environment variables or credentials. The only notable environmental assumption is the hard-coded SKILLS_BASE_PATH (/home/ubuntu/skills) used by both scripts; this is a usability/portability choice rather than a request for secrets.
Persistence & Privilege
always is false and model invocation is allowed (platform default). The skill does not request persistent elevated privileges or attempt to modify other skills/configs. It writes only under its intended skill directory when run.
Assessment
This skill appears to do what it says: scaffold and validate OpenClaw skills. Before running: (1) inspect the two Python scripts locally to confirm they match the provided sources (they are simple and benign-looking), (2) be aware they read/write under /home/ubuntu/skills — adjust SKILLS_BASE_PATH if you use a different environment or want to avoid writing to that path, (3) run scripts with a non-privileged account or in an isolated environment if you have concerns, and (4) validate that sending the generated SKILL.md via your platform's message/frontend flow is acceptable for your data policy. If anything in the scripts differs from the bundle, stop and investigate further.Verification
Tags
Skill Creator 🛠️
Bundle plugin: Guide for creating or updating reusable OpenClaw skills.
What it does
Provides comprehensive guidance and helper scripts for creating effective OpenClaw skills:
- Best practices - Learn core principles for skill design
- Progressive disclosure - Keep skills concise and efficient
- Initialization script - Scaffold new skills from template
- Validation script - Verify skill structure and metadata
- Workflow patterns - Reference examples for common skill types
Installation
In OpenClaw
openclaw bundles install clawhub:@aisa/skill-creator
Usage
The skill loads automatically when you ask about creating or updating skills:
- "Help me create a new OpenClaw skill for [domain]"
- "Validate my skill package"
- "Improve this skill's design"
Helper Scripts
Note: Use
python3orpythondepending on your system.
Initialize a New Skill
python3 skills/skill-creator/scripts/init_skill.py my-new-skill
Creates a template skill at /home/ubuntu/skills/my-new-skill/
Validate an Existing Skill
python3 skills/skill-creator/scripts/quick_validate.py my-skill
python3 skills/skill-creator/scripts/quick_validate.py /home/ubuntu/skills/my-skill
(Replace python3 with python if the command is not available on your system.)
Checks:
- SKILL.md exists
- Valid YAML frontmatter
- Required fields (name, description)
Components
skill-creator/
├── .codex-plugin/
│ └── plugin.json
├── skills/
│ └── skill-creator/
│ ├── SKILL.md # Main guidance document
│ ├── scripts/
│ │ ├── init_skill.py # Skill initializer
│ │ └── quick_validate.py # Validation script
│ └── references/
│ ├── workflows.md # Workflow pattern examples
│ ├── progressive-disclosure-patterns.md
│ └── output-patterns.md
├── openclaw.plugin.json
├── package.json
└── README.md
Skill Design Principles
1. Concise is Key
Context window is a shared resource. Only add what OpenClaw doesn't already know.
2. Appropriate Freedom Levels
- High freedom - Text instructions for flexible tasks
- Medium freedom - Pseudocode for pattern-based tasks
- Low freedom - Specific scripts for fragile operations
3. Progressive Disclosure
- Metadata - Always loaded (~100 words)
- SKILL.md body - When triggered (<500 lines)
- References - As needed
4. Skill Anatomy
skill-name/
├── SKILL.md (required) # Metadata + instructions
└── Bundled Resources (optional)
├── scripts/ # Executable code
├── references/ # Documentation
└── templates/ # Output assets
Examples
See SKILL.md for complete workflow patterns and examples.
License
MIT