Evidence-Driven Testing

What it does

When your agent uses it

• Proving a UI change works before merging, with a video instead of prose
• Attaching test evidence to a pull request and its tracker issue
• Documenting a non-UI change with measured numbers or before-and-after output

Example prompts

• “Test the new checkout flow hands-on, record it with annotations and post the video to the PR.”
• “Record evidence that the dark-mode toggle survives a page reload and attach it to the issue.”
• “This change has no UI. Capture before-and-after output for the parser fix as evidence for the PR.”

Requirements

• Python 3 with ffmpeg and ffprobe (libx264 and the ass filter)
• A GUI environment the agent can drive, or the cua-driver CLI
• An authenticated browser session for the app under test
• The GitHub CLI or an equivalent to post evidence
• Compatibility (from SKILL.md): Screen-recording path requires a GUI environment the agent can drive — built-in computer use, or the cua-driver CLI (trycua/cua) when the harness has no computer-use tools — plus an authenticated browser session for the app under test. The bundled recorder (scripts/evidence.py) runs on Linux (X11 via x11grab, Wayland via wf-recorder), macOS (avfoundation, needs Screen Recording permission) and Windows (gdigrab) and needs Python 3 plus ffmpeg + ffprobe built with libx264 and the ass filter. The headless path requires only a running app and a scriptable browser (e.g. Playwright via npx). Posting evidence requires gh (GitHub CLI) or equivalent.

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Prepare the screen
2. 2Start recording
3. 3Test via computer use, annotating as you go
4. 4Stop and review
5. 5Post the evidence

What it can do on your machine

Read from SKILL.md and the folder at commit 4b72f46. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • git
  • npx
  • gh

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Screen-recording path requires a GUI environment the agent can drive — built-in computer use, or the cua-driver CLI (trycua/cua) when the harness has no computer-use tools — plus an authenticated browser session for the app under test. The bundled recorder (scripts/evidence.py) runs on Linux (X11 via x11grab, Wayland via wf-recorder), macOS (avfoundation, needs Screen Recording permission) and Windows (gdigrab) and needs Python 3 plus ffmpeg + ffprobe built with libx264 and the ass filter. The headless path requires only a running app and a scriptable browser (e.g. Playwright via npx). Posting evidence requires gh (GitHub CLI) or equivalent.

  From compatibility in the SKILL.md frontmatter.

Context cost

Evidence-Driven Testing loads about 3.9k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 1,819 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~123

When it runs · the whole SKILL.md, loaded when a task matches

~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,819 words (~3,880 tokens).

name

evidence-driven-testing

compatibility

Screen-recording path requires a GUI environment the agent can drive — built-in computer use, or the cua-driver CLI (trycua/cua) when the harness has no computer-use tools — plus an authenticated browser session for the app under test. The bundled recorder (scripts/evidence.py) runs on Linux (X11 via x11grab, Wayland via wf-recorder), macOS (avfoundation, needs Screen Recording permission) and Windows (gdigrab) and needs Python 3 plus ffmpeg + ffprobe built with libx264 and the ass filter. The headless path requires only a running app and a scriptable browser (e.g. Playwright via npx). Posting evidence requires gh (GitHub CLI) or equivalent.

metadata.version

1.2

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in evidence-driven-testing of michaelshimeles/skills.

• SKILL.md
• scripts/evidence.py

Open the folder on GitHubat commit 4b72f46

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in michaelshimeles/skills, which our catalogue first saw on October 7, 2026.

• boringcomputers/goshen-email.claude/skills/evidence-driven-testing