probe-loading

Profile skill loading behavior by measuring frontmatter visibility and resource enumeration.

2|Updated Mar 21, 2026

Search Tags:#validation #platform #resources #benchmark #canary #loading

Ready to run

npx skills add https://github.com/agent-ecosystem/agent-skill-implementation --skill probe-loading

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: probe-loading
Source: https://github.com/agent-ecosystem/agent-skill-implementation/tree/main/benchmark-skills/probe-loading
Command: npx skills add https://github.com/agent-ecosystem/agent-skill-implementation --skill probe-loading

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This benchmarking skill helps platform providers and researchers observe and measure how skill content is loaded at discovery and activation, including frontmatter visibility, content wrapping, and resource exposure.

Core Features & Use Cases

Frontmatter visibility checks: verify which YAML frontmatter fields are accessible during activation.
Content loading and wrapping: detect any content wrapping (XML/JSON) and report how the body is delivered.
Resource enumeration: confirm which directories (scripts, references, assets) are discovered and loaded.
Canary-driven testing: validate presence of canary phrases in references and assets to confirm eager loading behavior.
Use Case: run a platform audit to ensure consistent skill loading across environments.

Quick Start

Activate this skill to generate a structured loading report and verify how frontmatter visibility, content presentation, and resource enumeration occur.

Frequently Asked Questions about probe-loading

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

FAQPage Schema

How do I benchmark skill loading behavior across platforms?▼

To benchmark skill loading behavior, activate this skill to measure how frontmatter visibility, content wrapping, and resource enumeration load during activation across platforms implementing skill loading checks.

What is skill content loading and how does frontmatter visibility work?▼

Skill content loading involves measuring how frontmatter YAML fields, content body wrapping, and resource directories are exposed during activation. Frontmatter visibility checks verify which specific fields are accessible when the skill loads.

How do I validate eager loading of references and assets during skill activation?▼

Validate eager loading by using canary-driven testing to confirm the presence of canary phrases in references and assets, ensuring static references load correctly across skill directories during activation.

Does this benchmarking skill detect content wrapping like XML or JSON during activation?▼

Yes, this skill detects any content wrapping such as XML or JSON during activation and reports exactly how the body content is delivered across platforms implementing the loading checks.

Can I run a platform audit to verify resource enumeration for scripts, references, and assets?▼

Yes, you can run a platform audit to confirm which directories including scripts, references, and assets are discovered and loaded, generating a structured report on resource enumeration behavior.

What are the limitations of benchmarking skill loading across different platforms?▼

This skill applies specifically to benchmark skills with frontmatter, references, scripts, and assets. It validates loading behavior across platforms implementing skill loading checks but may not cover non-standard directory structures.