skill-stocktake

Audit Claude skills against a standardized quality checklist and produce verdicts.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/sakamoto-family-smile/agent_monorepo --skill skill-stocktake-sakamoto-family-smile
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-stocktake
Source: https://github.com/sakamoto-family-smile/agent_monorepo/tree/main/.claude/skills/ecc/skill-stocktake
Command: npx skills add https://github.com/sakamoto-family-smile/agent_monorepo --skill skill-stocktake-sakamoto-family-smile

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes scripts (resource) components.

What problem does it solve?

Auditing Claude skills and their commands for quality is a structured process facilitated by a standardized checklist and AI holistic judgment, reducing drift across projects.

Core Features & Use Cases

  • Quick Scan: re-scan only recently changed skills using a results.json to focus efforts where changes occurred.
  • Full Stocktake: perform a complete evaluation of all skills with an inventory and per-skill verdicts, consolidating results in a single authoritative file.
  • Output & governance: provide UTC-timestamped results.json with evaluated_at and usage signals to support audits and compliance.

Quick Start

Run /skill-stocktake from the repository root to inventory Claude skills and evaluate them against the quality checklist.

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 across multiple projects?

You can audit Claude skills for quality by running a full stocktake that inventories global and project-level skills, evaluates them against a standardized checklist, and outputs per-skill verdicts in a consolidated results file.

What is the best way to check only recently changed Claude skills for quality drift?

Running a quick scan checks only recently changed Claude skills by referencing an existing results.json file, allowing you to target quality audits specifically where modifications occurred without re-evaluating the entire inventory.

Can I use jq to parse the results of a Claude skill inventory audit?

Yes, you can use jq to parse the output, as this audit requires jq as a dependency to process the consolidated results.json file containing UTC-timestamped evaluations and aggregated usage signals.

Does this skill stocktake tool support compliance and governance reporting?

The skill stocktake supports AI governance and compliance reporting by generating an authoritative results.json file with evaluated_at UTC timestamps and usage signals, providing an auditable trail of skill quality evaluations.

How do I inventory all global and project-level Claude commands before an audit?

To inventory all Claude commands, run the full evaluation mode from the repository root, which automatically discovers both global and project-level skills and builds a comprehensive inventory before applying the quality checklist.