skill-debug

Diagnose skill discovery, loading, and usage via local telemetry and dashboards.

24|2|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/yknothing/skills-refiner --skill skill-debug-yknothing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-debug
Source: https://github.com/yknothing/skills-refiner/tree/main/skills/skill-debug
Command: npx skills add https://github.com/yknothing/skills-refiner --skill skill-debug-yknothing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams understand local evidence about skill discovery, loading, and usage to improve observability and governance.

Core Features & Use Cases

  • Three-layer observability framework: discovery diagnostics, activation tracing, and a dashboard to correlate signals with outcomes.
  • Activation canary management: inject, strip, and observe lightweight canaries within skills to determine if instructions are being followed.
  • Local telemetry and context: interpret signals in relation to canonical skill identities, working directories, and symlink distributions for accurate diagnostics.

Quick Start

Run the three-layer workflow to probe discovery surfaces, inject canaries, and view the observability dashboard.

Frequently Asked Questions about skill-debug

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

FAQPage Schema
How do I trace local skill discovery and activation signals for observability?

You can trace local skill activation by running a three-layer observability workflow that probes discovery surfaces, injects canaries, and correlates signals with outcomes on a dashboard.

What is activation canary management and how does it diagnose instruction usage?

Activation canary management injects lightweight canaries into skills to observe if instructions are being followed, providing local telemetry to determine skill health.

Can I use this diagnostics framework to monitor an entire skill ecosystem locally?

Yes, you can apply this diagnostics framework to individual skills or entire ecosystems across local surfaces and working directories to support observability and governance.

How do I interpret telemetry signals in relation to canonical skill identities?

Interpret telemetry signals by mapping them against canonical skill identities, working directories, and symlink distributions to ensure accurate local diagnostics and reproducibility.

Does skill observability require sending telemetry data to external services?

No, skill observability keeps all telemetry local and reproducible, enforcing frontmatter standards and identity-based tracing without relying on external data collection.