skill-audit

Analyze conversation logs to diagnose agent skill failures and plan repairs.

1|Updated Jul 22, 2026
One-click install
npx skills add https://github.com/wyattjoh/skills --skill skill-audit-wyattjoh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-audit
Source: https://github.com/wyattjoh/skills/tree/main/skills/skill-audit
Command: npx skills add https://github.com/wyattjoh/skills --skill skill-audit-wyattjoh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill resolves the frustration of agent skills failing silently or repeatedly by providing a forensic analysis of conversation history to identify the root cause of errors.

Core Features & Use Cases

  • Forensic Analysis: Scans session logs for permission denials, tool errors, and user corrections to pinpoint exactly where a skill failed.
  • Automated Recommendations: Provides actionable, step-by-step instructions to fix permission issues or workflow logic.
  • Repair Integration: Offers to automatically enter plan mode to implement the necessary fixes to the skill definition.

Quick Start

Ask the agent to audit the skill that just failed by typing audit the pr-create skill.

Frequently Asked Questions about skill-audit

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

FAQPage Schema
How do I debug an agent skill that keeps failing silently?

To debug an agent skill that keeps failing silently, you can run a forensic analysis on the conversation history to identify the root cause of errors. It scans session logs to pinpoint the exact failure.

What causes permission denials and tool errors during agent skill execution?

Permission denials and tool errors during agent skill execution are caused by workflow logic flaws or constraint mismatches. Comparing actual tool usage against defined skill constraints identifies these root causes.

How do I fix an agent skill after identifying user-correction patterns in logs?

Fix an agent skill after identifying user-correction patterns by entering plan mode to implement targeted remediation steps. The audit provides actionable, step-by-step instructions to repair workflow logic.

Does automated agent skill repair work without external dependencies?

Automated agent skill repair works without external dependencies. It relies on analyzing conversation history and tool execution logs internally to provide remediation steps for failing agent skills.

When should I audit agent skills instead of manually troubleshooting errors?

Audit agent skills instead of manually troubleshooting errors when failures repeat silently or you need to compare actual tool usage against defined skill constraints. The automated forensic analysis quickly identifies root causes.