Skill Testing

by MisterBrookT

Skill Testing is a Quality skill for Claude Code, published by MisterBrookT in skill2.

31 stars3 forkson MisterBrookT/skill2Added 2026/07/17+7% in starsRepository updated 2026/07/24

View source on GitHub Download repo ZIP

agent-skillsai-agentsclaude-codecodexdeveloper-toolsevalslocal-firstpythonskill-librarytesting

Install in seconds

Install Skill Testing

Copy Skill Testing into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/blackblue-labs/skill2/tree/main/skills/skill2-test ~/.claude/skills/skill2-test

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/blackblue-labs/skill2.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/skill2-test/SKILL.md in MisterBrookT/skill2
Installs to: ~/.claude/skills/skill2-test
Collection: One of 9 skills cataloged from this repository
Category: Quality — 1897 skills

What Skill Testing does

Evaluates AI agent skills in isolation to measure activation accuracy, outcome quality, and false-activation avoidance. Use for regression testing and baseline uplift evidence.

Skill Testing is cataloged under Quality on DirSkills. Skill Testing comes from a repository tagged agent-skills, ai-agents, claude-code, codex and developer-tools.

Documentation

README

Excerpt

Test Agent Skills

Measure behavior without inheriting current chat, global memory, or unrelated Skills.

Ownership

Test owns live activation, outcome, routing, and baseline evidence.
Audit owns static structure and trigger-overlap review.
Create owns Skill changes; Test never rewrites a failing Skill automatically.

Layers

Layer	Installed Skills	Measures
Target-only	Target Skill only	Activation, outcome, baseline uplift
Pack	Candidate sibling Skills	Routing and false activation

Use target-only for core outcomes. Use pack for adjacent and unrelated routing cases.

Cases

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Skill Testing

What else does MisterBrookT publish alongside Skill Testing?
Skill Testing is one of 9 skills that DirSkills catalogs from MisterBrookT/skill2, the repository it ships in. Its siblings there include Create Agent Skills, Invoice CSV Export and Report Exporter. Each one is a separate skill with its own page in this directory, installs the same way Skill Testing does, and is maintained by MisterBrookT in that same repository. The rest of the collection is listed on the MisterBrookT/skill2 page.
How does Skill Testing compare to other Quality skills?
Skill Testing ranks #1849 by stars among the 1897 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Testing against them. Open each page to compare what they document and how they install.