skills.rest
frabcd
frabcdCOMMUNITY
Explore all skills by this author →
GitHub

skill-test

Validate Codex skill files for structural compliance and behavioral correctness.

13|Updated Jul 30, 2026
Search Tags:#quality assurance#linting#codex#skill validation#frontmatter#behavioral testing#subagent testing
One-click install
npx skills add https://github.com/frabcd/codex-ai-game-studio --skill skill-test-frabcd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-test
Source: https://github.com/frabcd/codex-ai-game-studio/tree/main/plugins/ai-game-studio/skills/skill-test
Command: npx skills add https://github.com/frabcd/codex-ai-game-studio --skill skill-test-frabcd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Skill authors need a way to verify that a Codex skill is structurally valid and behaves correctly before shipping it, but manual review misses frontmatter errors, broken links, and routing failures. ## Core Features & Use Cases - Static Validation: Lints SKILL.md frontmatter, directory naming, agents/openai.yaml metadata, and scans for secrets, absolute paths, and platform-only assumptions. - Behavioral Testing: Runs forward tests with isolated subagents covering explicit invocation, natural-language routing, near-miss rejection, and unsafe request handling. - Coverage Audit: Produces a concise test matrix with a prioritized improvement proposal while keeping the tested skill unchanged until approved. - Use Case: Before publishing a new skill to a plugin marketplace, run this skill to confirm the frontmatter is compliant, implicit invocation routes correctly, and no credentials or developer paths leaked into the package. ## Quick Start Use the skill-test skill to validate the skill in my target directory and report a test matrix with any compliance failures.

Frequently Asked Questions about skill-test

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

FAQPage Schema
How do I validate a Codex skill before publishing it?▼

Run static validation on the skill directory to check SKILL.md frontmatter for exactly name and description, confirm lowercase hyphen-case naming matches the directory, and verify agents/openai.yaml metadata. Then run forward tests with subagents to confirm routing and safety behavior.

What does skill frontmatter validation check?▼

It requires YAML frontmatter containing exactly name and description, confirms the description explains both what the skill does and when it activates, and rejects unsupported legacy frontmatter fields and broken relative links.

How do I test that a skill triggers on the right prompts?▼

Use forward testing with isolated subagents covering a direct explicit invocation, a natural-language request that should select the skill, a near-miss that should route elsewhere, and an unsafe request that must preserve approval gates.

Does skill validation modify the skill being tested?▼

No, testing is read-only unless the user separately approves writing a report. The tested skill is never edited until the user approves that as a separate change.

What security issues does skill linting detect?▼

The scan detects secrets, absolute developer paths, path escapes, unsupported model pins, product-specific tool declarations, and platform-only assumptions that would break portability across Windows, macOS, and Linux.

Related Skills

Explore More Software Engineering Skills→
openaiopenai
120.5k

skill-creator

Create or update Codex skills with scoped instructions and supporting resources.

Official
Intermediate
beam-ai-teambeam-ai-team

share-skill

Validate and package local skills into bundles for Airtable upload.

Official
Intermediate
metric-space-aimetric-space-ai
2

security-posture

Collect host posture data and write findings to a SQLite database.

Official
Intermediate
AztecProtocolAztecProtocol
449

debug-e2e

Coordinates interactive debugging sessions for failed end-to-end CI tests via subagents.

Official
Advanced