skill-stocktake

Audit Claude skill and command markdown files for overlap, staleness, and quality issues.

1|Updated Mar 6, 2026

Search Tags:#claude skills #security review #workflow management #quality audit #inventory scan #tooling automation

Ready to run

npx skills add https://github.com/khetansarvesh/ai_skills_repo --skill skill-stocktake-khetansarvesh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-stocktake
Source: https://github.com/khetansarvesh/ai_skills_repo/tree/main/skills/skill-stocktake
Command: npx skills add https://github.com/khetansarvesh/ai_skills_repo --skill skill-stocktake-khetansarvesh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It helps you systematically evaluate and keep, improve, update, retire, or merge Claude skills and commands so your skill library stays accurate, non-overlapping, and technically current.

Core Features & Use Cases

Two audit modes: Quick Scan reviews only skills changed since the last run, while Full Stocktake inventories everything and performs a holistic checklist-based evaluation.
Local caching + resumable batches: Full Stocktake stores intermediate progress in results.json and can resume if evaluation is interrupted.
Usage-aware scoring signals: Full Stocktake can incorporate 7-day and 30-day read observations to help judge real-world usefulness.
Path targeting: Evaluates global skills in ~/.claude/skills and optionally project-level skills when run from a project root that contains .claude/skills.

Quick Start

Run /skill-stocktake to perform a Quick Scan of recently changed skills and output only the diff.

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 overlap and staleness?▼

You can audit Claude skills for overlap and staleness by running an automated inventory scan that evaluates markdown files using checklist criteria and UTC mtime tracking. It identifies redundant capabilities and outdated content within your skill directories.

What is the best way to inventory markdown command files in a project?▼

The best way to inventory markdown command files is using a YAML-frontmatter-driven identification workflow. This process catalogs global and project-scoped skill directories, applying checklist evaluations to flag quality issues and detect overlapping commands.

How does resumable batch processing work for quality audits?▼

Resumable batch processing for quality audits works by caching intermediate progress in a results.json file. If the evaluation is interrupted, the system can resume the audit from the last saved state, preventing redundant scans of already evaluated skills.

Can I use a quick scan to only review recently changed skills?▼

Yes, you can use a Quick Scan to review only recently changed skills. This mode compares current file states against cached results using change detection, outputting only the diff of modifications since the last full inventory scan was performed.

Does the skill audit require jq to parse JSON results?▼

Yes, the skill audit requires jq as a dependency to parse JSON results. The evaluation workflow generates JSON outputs for both intermediate caching and final audit reports, which jq processes to extract and format the quality scoring signals.

How do usage-aware scoring signals evaluate skill usefulness?▼

Usage-aware scoring signals evaluate skill usefulness by incorporating 7-day and 30-day read observations. These usage metrics help judge real-world utility during a Full Stocktake, providing data to determine whether to keep, improve, or retire specific commands.