skill-audit
Audit all installed skills for quality, duplicates, structural issues, and best-practice compliance. Use when asked to review, audit, lint, or check skills for problems. Triggers on "audit skills", "skill quality", "check my skills", "skill duplicates", "skill hygiene".
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bill492/unblocklabs-skill-auditWhat This Skill Does
The skill-audit tool serves as the diagnostic backbone for your OpenClaw agent environment. It acts as a comprehensive linter, quality auditor, and architectural inspector for all installed agent skills. By evaluating your library against a rigorous scoring matrix, it identifies structural weaknesses, potential conflicts, and optimization opportunities. The skill performs a deep-scan of your global, workspace, and project-level directories, mapping your repository against nine core industry-standard categories to ensure your skills are not just functional, but optimized for LLM reasoning and precision.
Installation
To integrate this utility into your development lifecycle, run the following command within your terminal or OpenClaw interface:
clawhub install openclaw/skills/skills/bill492/unblocklabs-skill-audit
Ensure that you have appropriate file-system permissions for the directories being scanned, as the agent requires read-access to your skill repository structure.
Use Cases
Use skill-audit when you notice the agent struggling to select the correct tool, or when you are refactoring your personal library. It is particularly effective for:
- Identifying 'zombie' skills that clutter your namespace but no longer serve a purpose.
- Normalizing the documentation of your skills to ensure they follow progressive disclosure patterns.
- Detecting duplicate trigger phrases across multiple skill directories.
- Auditing compliance with best practices like maintaining a 'Gotchas' section, which significantly improves agent success rates.
Example Prompts
- "I've been adding a lot of custom skills lately; can you run a skill-audit to see if any of them are redundant or missing descriptions?"
- "Perform a skill-audit and tell me which of my skills have the lowest quality scores so I can prioritize updates."
- "Hey OpenClaw, check my skills for hygiene. Are there any orphan files or outdated triggers I should clean up?"
Tips & Limitations
For best results, aim for a score of 8 or higher on the audit report. If a skill scores below 5, it is highly recommended to refactor the SKILL.md file to include specific 'trigger-oriented' language and a dedicated 'Gotchas' section. Note that this skill is a static analysis tool; it cannot determine if the code inside your scripts will successfully execute, only that the structure and documentation meet the required architectural standards for high-performance agent interaction.
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-bill492-unblocklabs-skill-audit": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution
Related Skills
browser-read-x
Extract the main X/Twitter post or article content from a page that is already open in the browser (using browser act evaluate).
cf-crawl
Crawl websites using Cloudflare Browser Rendering /crawl API. Async multi-page crawl with markdown/HTML/JSON output, link following, pattern filtering, and AI-powered structured data extraction. Use when crawling entire sites or multiple pages, building knowledge bases, extracting structured data from websites, or when web_fetch is insufficient (JS rendering, multi-page, authenticated crawls).
sub-agents
Spawn and coordinate sub-agent sessions for parallel work. Use when delegating tasks (research, code, analysis), routing to appropriate models, or managing multi-agent workflows. Trigger on "spawn", "sub-agent", "delegate", "parallel tasks", or when a task would benefit from a different model.
browser-read
Extract readable content from browser pages as markdown. Use when web_fetch fails (bot protection, auth-required pages, Twitter/X, LinkedIn) and you already have the page open in the browser.
slack-block-kit
Send rich Slack Block Kit messages — native tables, structured layouts. Use when formatting tabular data for Slack, sending Block Kit payloads, or when markdown tables render poorly in Slack.