skill-stocktake

Audit Claude skills and commands against a quality checklist.

Updated Jul 27, 2026
One-click install
npx skills add https://github.com/kouiso/designdiff --skill skill-stocktake-kouiso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-stocktake
Source: https://github.com/kouiso/designdiff/tree/main/.claude/skills/skill-stocktake
Command: npx skills add https://github.com/kouiso/designdiff --skill skill-stocktake-kouiso

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the auditing of Claude skills and commands, ensuring quality and consistency across your AI tools.

Core Features & Use Cases

  • Quality Auditing: Evaluates skills against a checklist and AI judgment.
  • Mode Support: Offers 'Quick Scan' for changed skills and 'Full Stocktake' for comprehensive reviews.
  • Use Case: Regularly audit your team's Claude skills to identify outdated commands, overlapping functionality, or areas needing improvement before they impact user experience.

Quick Start

Run a full audit of all Claude skills in the current project and globally.

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 and consistency?

Auditing Claude skills involves evaluating them against a checklist and AI judgment across actionability, scope fit, uniqueness, and currency. The process categorizes each skill for Keep, Improve, Update, Retire, or Merge actions to ensure quality and consistency.

What is the difference between a quick scan and a full stocktake when reviewing AI commands?

Quick Scan targets only changed skills for rapid review, whereas Full Stocktake conducts comprehensive evaluations of all skills using sequential subagent batches to identify outdated commands and overlapping functionality across the project.

When should I run a quality assurance review on my AI tools and commands?

Run a quality assurance review regularly to identify outdated commands, overlapping functionality, or areas needing improvement before they negatively impact user experience and degrade your AI tools' effectiveness.

Can I evaluate globally installed Claude skills or only those in the current project?

You can run a full audit of all Claude skills in both the current project and globally installed environments, ensuring comprehensive quality assurance coverage across your entire AI tool ecosystem.

What criteria are used to decide whether to retire or merge AI skills?

Skills are evaluated on actionability, scope fit, uniqueness, and currency to determine if they should be Retired or Merged into other skills, eliminating overlapping functionality and outdated commands.