Is the Creating Agent Skills Skill skill free?

Yes. The skill itself is free from AgentWorkforce/relay. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Creating Agent Skills Skill SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.

How do I install Creating Agent Skills Skill?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Creating Agent Skills Skill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Creating Agent Skills Skill

Spec and rules for authoring portable SKILL.md packages for Codex, Copilot, and Amp

by AgentWorkforce · AgentWorkforce/relay

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 494b2d1

Fetched the SKILL.md raw from .agents/skills/creating-agent-skills-skill/; the directory holds only SKILL.md, so no internal file/script references to break, and I found no security smells (no curl|sh, base64, or exfiltration). For the output test I authored two SKILL.md files for a hypothetical "validate YAML" skill: a baseline from default habits produced name "YAML Validator" (uppercase+space) and description "Validates YAML files"; following the skill body produced "yaml-validating" (passed the ^[a-z0-9]+(-[a-z0-9]+)*$ name check) and a functionality-plus-use-cases description (189 chars) — the skill fixed two concrete spec violations. Docs lost a point: the "Complete Example" section shows an unrelated TypeScript type guard and several headers are empty "####" artifacts, plus it references a `skills-ref validate` CLI that is not bundled.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 4/5

What Creating Agent Skills Skill does

Provides the agentskills.io SKILL.md specification: frontmatter constraints (name and description rules), directory layout, progressive-disclosure loading, and a validation checklist for building portable Agent Skill packages. Triggers when creating or reviewing a SKILL.md for Codex CLI, GitHub Copilot, or Amp, or when checking whether skill frontmatter meets the spec.

How to install Creating Agent Skills Skill

git clone --depth 1 https://github.com/AgentWorkforce/relay.git /tmp/creating-agent-skills-skill-src
mkdir -p ~/.claude/skills
cp -R /tmp/creating-agent-skills-skill-src/.agents/skills/creating-agent-skills-skill ~/.claude/skills/creating-agent-skills-skill
# Pure-documentation skill: no scripts, deps, or API keys.
# Body references an external `skills-ref validate` CLI for optional validation; not bundled in the repo, install separately if wanted.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Creating Agent Skills Skill

/creating-agent-skills-skill Spec and rules for authoring portable SKILL.md packages for Codex, Copilot, and Amp

It also activates on plain-language prompts like these:

Create an Agent Skills package for Codex CLI
Validate this SKILL.md against the spec
Set up the directory structure for a new Amp skill

Frequently asked questions

Is the Creating Agent Skills Skill skill free?: Yes. The skill itself is free from AgentWorkforce/relay. SkillProof publishes the install command and an independent test verdict at no cost.
Does Creating Agent Skills Skill work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched the SKILL.md raw from .agents/skills/creating-agent-skills-skill/; the directory holds only SKILL.md, so no internal file/script references to break, and I found no security smells (no curl|sh, base64, or exfiltration). For the output test I authored two SKILL.md files for a hypothetical "validate YAML" skill: a baseline from default habits produced name "YAML Validator" (uppercase+space) and description "Validates YAML files"; following the skill body produced "yaml-validating" (passed the ^[a-z0-9]+(-[a-z0-9]+)*$ name check) and a functionality-plus-use-cases description (189 chars) — the skill fixed two concrete spec violations. Docs lost a point: the "Complete Example" section shows an unrelated TypeScript type guard and several headers are empty "####" artifacts, plus it references a `skills-ref validate` CLI that is not bundled.
What is the Creating Agent Skills Skill SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
How do I install Creating Agent Skills Skill?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Creating Agent Skills Skill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.