How do I install the Skill Test skill?

Run npx skillmds@latest add frabcd/skill-test in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Skill Test safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill Test?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill Test free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Skill Test?

frabcd (@frabcd) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill Test by frabcd — Agent Skill

Name: Skill Test
Author: frabcd

File contents

Port provenance: adapted from the pinned upstream source at 984023ddac0d5e27624f2baacde6105e45de375f under MIT; see the repository parity ledger for the exact path and blob.

Test a Codex skill

Evaluate a target skill as both a package and a behavior. Testing is read-only unless the user separately approves writing a report.

Static validation

Locate the skill directory and read SKILL.md plus agents/openai.yaml.
Require YAML frontmatter containing exactly name and description.
Confirm the directory name and frontmatter name match and use lowercase hyphen-case.
Confirm the description explains both what the skill does and when it should activate. Reject unsupported legacy frontmatter and broken relative links.
Confirm agents/openai.yaml has a useful display name, a 25-64 character short description, and a default prompt that explicitly names the skill.
Confirm mutating setup, installation, engine-control, catalog-refresh, and destructive enhancement workflows disable implicit invocation.
Scan for secrets, absolute developer paths, path escapes, unsupported model pins, product-specific tool declarations, and platform-only assumptions.

Run the official skill validator when it is available. Report the exact command, exit status, and diagnostics.

Forward testing

Use isolated Codex subagents with the raw skill instructions. Cover:

a direct explicit invocation;
a natural-language request that should select the skill when implicit use is enabled;
a near-miss that should route elsewhere;
a negative or unsafe request that must preserve approval and rights gates.

Do not reveal an expected answer in the test prompt. Score routing, instruction adherence, safety boundary, artifact clarity, platform neutrality, and evidence. For failures, distinguish instruction defects from missing external capabilities.

Return a concise test matrix and a prioritized improvement proposal. Do not edit the tested skill until the user approves that separate change.

Codex portability

Use the search, file-editing, shell, user-input, and subagent capabilities available in the active Codex surface. Use PowerShell syntax on Windows and POSIX syntax on macOS/Linux; do not require a Unix compatibility layer on Windows. Inherit the active model and permission mode, and do not weaken approval or sandbox boundaries.

---name: skill-testdescription: Validate skill files for structural compliance and behavioral correctness. Three modes: static (linter), spec (behavioral), audit (coverage report).---> Port provenance: adapted from the pinned upstream source at `984023ddac0d5e27624f2baacde6105e45de375f` under MIT; see the repository parity ledger for the exact path and blob.# Test a Codex skillEvaluate a target skill as both a package and a behavior. Testing is read-onlyunless the user separately approves writing a report.## Static validation1. Locate the skill directory and read `SKILL.md` plus `agents/openai.yaml`.2. Require YAML frontmatter containing exactly `name` and `description`.3. Confirm the directory name and frontmatter name match and use lowercase hyphen-case.4. Confirm the description explains both what the skill does and when it should activate. Reject unsupported legacy frontmatter and broken relative links.5. Confirm `agents/openai.yaml` has a useful display name, a 25-64 character short description, and a default prompt that explicitly names the skill.6. Confirm mutating setup, installation, engine-control, catalog-refresh, and destructive enhancement workflows disable implicit invocation.7. Scan for secrets, absolute developer paths, path escapes, unsupported model pins, product-specific tool declarations, and platform-only assumptions.Run the official skill validator when it is available. Report the exact command,exit status, and diagnostics.## Forward testingUse isolated Codex subagents with the raw skill instructions. Cover:- a direct explicit invocation;- a natural-language request that should select the skill when implicit use is enabled;- a near-miss that should route elsewhere;- a negative or unsafe request that must preserve approval and rights gates.Do not reveal an expected answer in the test prompt. Score routing, instructionadherence, safety boundary, artifact clarity, platform neutrality, and evidence.For failures, distinguish instruction defects from missing external capabilities.Return a concise test matrix and a prioritized improvement proposal. Do not editthe tested skill until the user approves that separate change.## Codex portabilityUse the search, file-editing, shell, user-input, and subagent capabilities available in the active Codex surface. Use PowerShell syntax on Windows and POSIX syntax on macOS/Linux; do not require a Unix compatibility layer on Windows. Inherit the active model and permission mode, and do not weaken approval or sandbox boundaries.

Frequently asked questions

Skill Test