skill-stocktake

Audit Claude skills and commands against a quality checklist.

Updated Mar 2, 2026
One-click install
npx skills add https://github.com/unju-ai/ecc --skill skill-stocktake-unju-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-stocktake
Source: https://github.com/unju-ai/ecc/tree/main/skills/skill-stocktake
Command: npx skills add https://github.com/unju-ai/ecc --skill skill-stocktake-unju-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the auditing of Claude skills and commands, ensuring they meet quality standards and are efficiently managed.

Core Features & Use Cases

  • Automated Quality Auditing: Evaluates skills against a defined checklist and AI judgment.
  • Mode Selection: Supports 'Quick Scan' for changed skills and 'Full Stocktake' for comprehensive reviews.
  • Use Case: Regularly run this skill to identify outdated, redundant, or low-quality skills in your Claude environment, maintaining a clean and effective set of tools.

Quick Start

Run /skill-stocktake to perform a quick scan of your Claude skills.

Frequently Asked Questions about skill-stocktake

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit Claude skills for quality assurance?

To audit Claude skills for quality assurance, run an automated evaluation against a defined checklist combined with AI holistic judgment to identify outdated or low-quality commands.

What is the best way to review changed Claude commands without checking everything?

Reviewing changed Claude commands is best done using a Quick Scan mode, which evaluates only modified files to ensure recent updates meet quality standards efficiently.

How do I perform a full stocktake of all Claude skills in my project?

Perform a full stocktake of all Claude skills by initiating a comprehensive review that enumerates and evaluates all skills within specified global and project-level directories.

Can I use bash scripts to extract frontmatter during a Claude skill audit?

Yes, you can use bash scripts during a Claude skill audit to handle file enumeration, extract frontmatter, and aggregate results for the quality assessment process.

Does evaluating Claude skills support detailed subagent assessments?

Yes, evaluating Claude skills supports optional subagent evaluation, allowing for detailed quality assessment beyond the standard automated checklist and holistic AI judgment.