skill-writer
Write high-quality agent skills (SKILL.md files) for ClawdHub/MoltHub. Use when creating a new skill from scratch, structuring skill content, writing effective frontmatter and descriptions, choosing section patterns, or following best practices for agent-consumable technical documentation.
Why use this skill?
Learn to write high-quality SKILL.md files for OpenClaw agents. Get expert guidance on YAML frontmatter, metadata schemas, and content patterns.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/gitgoodordietrying/skill-writerWhat This Skill Does
The skill-writer is a specialized meta-skill designed to guide developers and prompt engineers in crafting high-quality, agent-consumable technical documentation known as SKILL.md files. This tool acts as an editorial assistant, ensuring your documentation follows the strict ClawdHub schema. It provides automated guidance on composing effective YAML frontmatter, structuring content for semantic search, and organizing technical instructions so that AI agents can parse and execute your skills reliably. Whether you are defining a new CLI wrapper, a data processing pipeline, or a complex automation workflow, this skill helps you distill technical intent into clear, deterministic instructions.
Installation
You can integrate this skill into your environment by executing the following command in your terminal:
clawhub install openclaw/skills/skills/gitgoodordietrying/skill-writer
Once installed, you can invoke the skill by referencing its name in your prompts, allowing you to iterate on documentation while simultaneously building your tooling.
Use Cases
- Creating New Skills: Bootstrap a new
SKILL.mdfile from scratch with correct frontmatter and semantic structure. - Optimizing Searchability: Rewrite existing skill descriptions to ensure high-accuracy retrieval in vector-based agent registries.
- Standardizing Documentation: Apply consistent section patterns (e.g., When to Use, Prerequisites, Troubleshooting) across a suite of agent skills.
- Refactoring Content: Convert messy technical notes into structured markdown suitable for agent consumption.
Example Prompts
- "I am building a skill for Docker image cleanup. Help me write a concise description that follows the [What it does]. Use when [trigger] pattern."
- "Review this
SKILL.mdfrontmatter for me. Is the metadata schema correct for a Linux-only tool that requiresjq?" - "Structure this list of 10 bash commands into a
SKILL.mdfile, including a Tips section for common errors."
Tips & Limitations
- Keep Descriptions Sharp: Always favor specific triggers over generic definitions. An agent must know exactly when to trigger your skill.
- Metadata Accuracy: Ensure your
requiresbinaries are accurate; the agent will check these before activation. - Limitations: The skill-writer is an authoring tool. It does not execute the code defined in your skills; it only validates the documentation structure. Always test your created skill in a sandboxed environment.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-gitgoodordietrying-skill-writer": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Related Skills
shell-scripting
Write robust, portable shell scripts. Use when parsing arguments, handling errors properly, writing POSIX-compatible scripts, managing temp files, running commands in parallel, managing background processes, or adding --help to scripts.
api-dev
Scaffold, test, document, and debug REST and GraphQL APIs. Use when the user needs to create API endpoints, write integration tests, generate OpenAPI specs, test with curl, mock APIs, or troubleshoot HTTP issues.
log-analyzer
Parse, search, and analyze application logs across formats. Use when debugging from log files, setting up structured logging, analyzing error patterns, correlating events across services, parsing stack traces, or monitoring log output in real time.
emergency-rescue
Recover from developer disasters. Use when someone force-pushed to main, leaked credentials in git, ran out of disk space, killed the wrong process, corrupted a database, broke a deploy, locked themselves out of SSH, lost commits after a bad rebase, or hit any other "oh no" moment that needs immediate, calm, step-by-step recovery.
data-validation
Validate data with schemas across languages and formats. Use when defining JSON Schema, using Zod (TypeScript) or Pydantic (Python), validating API request/response shapes, checking CSV/JSON data integrity, or setting up data contracts between services.