Is the Create Skill Test skill free?

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

What is the Create Skill Test SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Create Skill Test?

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 Create Skill Test 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.

Create Skill Test

Scaffolds eval.yaml test files with scenarios and rubrics for agent skills.

by dotnet · dotnet/skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 12, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 20e2715

Tested by scaffolding an eval.yaml for an inline csv-summarizer skill (1 activation + 2 non-activation scenarios). Verbatim git-clone+cp install landed the single-file skill at the exact documented path with valid frontmatter. A/B: the skilled output used the correct documented schema -- real assertion type names (output_contains/output_matches/exit_success/file_not_exists), proper setup.files blocks, no stray keys -- while the from-scratch base output covered one extra non-activation case but used invalid assertion types (contains/not_contains) and undocumented top-level skill: and per-scenario description: keys that would fail the repo's static validator.

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

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Create Skill Test does

Scaffolds eval.yaml test files for agent skills in the dotnet/skills repository. Use when creating skill tests, writing evaluation scenarios, defining assertions and rubrics, or setting up test fixture files. Handles eval.yaml generation, fixture organization, and overfitting avoidance. Do not use for running or debugging existing tests nor for skills authoring.

How to install Create Skill Test

git clone https://github.com/dotnet/skills
cd skills
mkdir -p ~/.claude/skills
cp -r .agents/skills/create-skill-test ~/.claude/skills/create-skill-test

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

Commands — how to trigger Create Skill Test

/create-skill-test Scaffolds eval.yaml test files with scenarios and rubrics for agent skills.

It also activates on plain-language prompts like these:

Write eval.yaml tests for this new skill
Create test fixtures for this skill's scenarios
Define assertions and rubrics for this skill test

Frequently asked questions

Is the Create Skill Test skill free?: Yes. The skill itself is free from dotnet/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Create Skill Test work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 12, 2026. Verdict: Tested · Works. Tested by scaffolding an eval.yaml for an inline csv-summarizer skill (1 activation + 2 non-activation scenarios). Verbatim git-clone+cp install landed the single-file skill at the exact documented path with valid frontmatter. A/B: the skilled output used the correct documented schema -- real assertion type names (output_contains/output_matches/exit_success/file_not_exists), proper setup.files blocks, no stray keys -- while the from-scratch base output covered one extra non-activation case but used invalid assertion types (contains/not_contains) and undocumented top-level skill: and per-scenario description: keys that would fail the repo's static validator.
What is the Create Skill Test SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Create Skill Test?: 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 Create Skill Test 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.