A comprehensive framework for writing and publishing standardized Markdown-based skills that AI coding agents use to execute tasks and follow technical instructions.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skill-writer
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install skill-writer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Skill Writer provides the essential specification for developing SKILL.md files, the primary format for extending the capabilities of AI coding agents. By defining a strict schema for frontmatter and content organization, it ensures that your technical documentation is not only human-readable but also optimized for machine consumption. Utilizing Openclaw Skills standards allows developers to create a library of actionable knowledge that agents can discover through semantic search and execute with high precision.
This framework focuses on task-oriented documentation rather than abstract concepts. It guides developers through the process of defining triggers, requirements, and multi-platform support, ensuring that every piece of technical advice is accompanied by runnable code examples. This structured approach is critical for building reliable agent workflows in modern development environments.
To begin developing and managing your Openclaw Skills, you need the Molthub CLI. Use the following commands to search for existing skills or publish your own:
# Search for existing skills to avoid slug collisions
npx molthub@latest search "your-skill-slug"
# Publish a new skill to the registry
npx molthub@latest publish ./skills/my-skill \
--slug my-skill \
--name "My Skill" \
--version 1.0.0 \
--changelog "Initial release"
Openclaw Skills follow a strict organizational schema to ensure agents can parse and execute the contained instructions effectively.
| Component | Format | Description |
|---|---|---|
| Frontmatter | YAML/JSON | Contains name, description, and metadata for registry indexing. |
| Metadata | JSON | Defines emoji, requires.anyBins (CLI dependencies), and os support. |
| When to Use | List | 4-8 bullet points describing concrete trigger scenarios for the agent. |
| Content | Markdown | Task-oriented sections with language-specific (e.g., bash, python) code blocks. |
| Tips | List | 5-10 actionable insights focusing on gotchas and non-obvious behaviors. |
Loading
A technical guide and toolset for optimizing agent skill discoverability through semantic search alignment and description engineering.

A comprehensive auditing framework and scoring system for evaluating the quality, structure, and actionability of AI agent skill files.

A professional toolkit for building reliable, portable, and production-ready Bash and POSIX shell scripts.

A comprehensive security scanner for auditing codebases, detecting leaked secrets, and identifying infrastructure vulnerabilities.

A comprehensive command-line resource for designing, querying, migrating, and optimizing SQLite, PostgreSQL, and MySQL databases without ORM overhead.

A comprehensive guide and toolset for managing SSH tunnels, secure port forwarding, and bastion host configurations.








































