An opinionated framework and tool for designing, building, and publishing professional-grade Openclaw Skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skillcraft
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install skillcraft using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Skillcraft?
Skillcraft provides a structured design sequence for developers looking to extend the capabilities of their AI agents. It focuses specifically on Openclaw Skills integration, covering everything from message routing and cron scheduling to memory persistence and frontmatter gating. Instead of generic programming advice, it offers a scaffold for architecting skills that are universal or particular to a specific local environment.
By following the Skillcraft sequence, developers can effectively package scripts, conversation patterns, and repeated instructions into reusable modules. Whether you are wrapping a CLI tool or building a complex monitoring agent, this skill ensures your Openclaw Skills are optimized for discovery and performance.
Skillcraft Use Cases
- Creating new Openclaw Skills from scratch using a professional design sequence.
- Extracting ad-hoc functionality from existing scripts into reusable agent skills.
- Packaging repeated instructions or conversation patterns for consistent agent behavior.
- Designing complex automations involving cron jobs and subagent handoffs.
- Preparing skills for publishing on ClawHub with proper metadata and installation specs.
How Skillcraft Works
- Inventory existing scripts or instructions to determine what functionality should be modularized.
- Define the core problem, success criteria, and whether the skill should be universal or specific to a local setup.
- Discover necessary Openclaw features like browser tools, canvas UI, or node devices to enhance the skill.
- Select an architectural pattern such as a CLI wrapper, API wrapper, or monitor based on the skill's purpose.
- Generate a design specification including file structure, state management, and Openclaw Skills frontmatter.
- Implement the skill by creating the directory, writing scripts, and testing against example scenarios.
Skillcraft Setup
Ensure your Openclaw environment is active. To begin using Skillcraft to build new Openclaw Skills, simply invoke the agent with a prompt like "make a new skill for [functionality]".
# Standard directory structure for a new skill
mkdir -p my-new-skill/patterns
touch my-new-skill/SKILL.md
Configure your skill's frontmatter in SKILL.md to include necessary metadata for Openclaw Skills discovery.
Skillcraft Data Schema & Taxonomy
Skillcraft organizes Openclaw Skills using a specific directory and metadata structure:
| Component | Description |
|---|---|
| SKILL.md | The core definition file containing YAML frontmatter and instructions. |
| {baseDir}/patterns/ | Directory for architectural templates like api-wrapper or cli-wrapper. |
| {baseDir}/state.json | Internal state storage that travels with the skill. |
| User-facing context and persistent memory. | |
| frontmatter | Metadata identifying dependencies (bins, env) and installation steps. |
Skillcraft Advanced Features
- Multi-platform filtering using OS-specific gates in the metadata.
- Support for complex installation specs including brew, npm, uv, and go.
- Integrated subagent handoff for complex script subcomponents.
- Automatic slash command dispatch for user-invocable skills.
- Custom path resolution using the {baseDir} token for portable Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Moegirl Wiki ACG Encyclopedia Search
A specialized search tool for accessing the Moegirl Wiki encyclopedia to retrieve anime, manga, and gaming character data.
safe-exec
A security wrapper that protects AI agents from prompt injection by isolating untrusted shell command outputs using UUID-based boundaries.
Wreckit Skill (jmanhype Fork)
An advanced autonomic software factory skill for Clawdbot optimized for ephemeral VM execution and high-concurrency development loops.
Denario Skill
An automated scientific research framework that handles the end-to-end pipeline from idea generation to paper compilation.
TOS Vectors Skill
A high-performance vector database skill for managing embeddings, similarity searches, and retrieval-augmented generation.
Smart Memory Query
A proactive memory retrieval skill that optimizes search queries to ensure AI agents maintain project continuity and context.
METADATA
Featured*
