Evidence-Driven Testing

by michaelshimeles

Evidence-Driven Testing is a Quality skill for Claude Code, published by michaelshimeles in skills.

538 stars92 forkson michaelshimeles/skillsAdded 2026/09/03Repository updated 2026/09/02

View source on GitHub Download repo ZIP

agent-skillsai-agentsclaude-codecode-reviewcodexcursordeveloper-workflowgreptile

Install in seconds

Install Evidence-Driven Testing

Copy Evidence-Driven 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/michaelshimeles/skills/tree/main/evidence-driven-testing ~/.claude/skills/evidence-driven-testing

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/michaelshimeles/skills.git

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

In this catalog

Source file: evidence-driven-testing/SKILL.md in michaelshimeles/skills
Installs to: ~/.claude/skills/evidence-driven-testing
Collection: One of 6 skills cataloged from this repository
Category: Quality — 1478 skills

What Evidence-Driven Testing does

Evidence-Driven Testing records annotated proof while you verify app behavior by hand or with scripted probes. Use it when a change needs verifiable evidence, such as UI flows, headless checks, or measured output for a PR or issue.

Evidence-Driven Testing is cataloged under Quality on DirSkills. Evidence-Driven Testing comes from a repository tagged agent-skills, ai-agents, claude-code, code-review and codex.

Documentation

README

Excerpt

Evidence-Driven Testing

Record annotated proof of behavior, then attach it to the PR and tracker issue.

The recording is the capture of you testing the app via computer use: start the recorder, then drive the app yourself — click, type, navigate — through each test target. Every action in the video is the test being performed live; the recording has no value as evidence unless it shows that interactive session. If the harness has no computer-use tools but a GUI exists, drive the app with cua-driver instead (see below) — it is still your live session.

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

Frequently asked about Evidence-Driven Testing

What else does michaelshimeles publish alongside Evidence-Driven Testing?
Evidence-Driven Testing is one of 6 skills that DirSkills catalogs from michaelshimeles/skills, the repository it ships in. Its siblings there include Before and After Screenshot, Code Structure and Greploop. Each one is a separate skill with its own page in this directory, installs the same way Evidence-Driven Testing does, and is maintained by michaelshimeles in that same repository. The rest of the collection is listed on the michaelshimeles/skills page.
How does Evidence-Driven Testing compare to other Quality skills?
Evidence-Driven Testing ranks #1188 by stars among the 1478 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 Evidence-Driven Testing against them. Open each page to compare what they document and how they install.