evidence-driven-testing SKILL.md skillA
evidence-driven-testing from michaelshimeles/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add michaelshimeles/skills/evidence-driven-testing@v1.2Pins v1.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- michaelshimeles/skills
- Path
evidence-driven-testing/SKILL.md- Versions recorded
- 5
- Latest version
- v1.2, committed Oct 19, 2026
- First version recorded
- Sep 1, 2026
- Size
- 16,932 bytes
- Repository stars
- 1,373
- License
- none declared
Records visual proof while testing UI behavior — the agent tests the app hands-on via computer use while a screen recording with structured test/assertion annotations captures the session — then posts the video and a results summary to the requested destination. Use when changed runtime behavior needs observable verification, including headless environments (scripted screenshots and probes) and non-UI changes (measured numbers, output pairs).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Evidence-Driven Testing Record proof of behavior and deliver it to the requested destination. Choose evidence proportional to the change. Use the recorder for interactive flows, scripted captures for headless UI checks, and output pairs for CLI or API changes. Documentation-only edits need content checks and verification of runnable examples, not a recording. Reuse suitable evidence already captured in the task. Publish only to destinations included in the requested work. 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. The bundled recorder, `scripts/evidence.py`, captures the display with FFmpeg on Linux, macOS, and Windows, timestamps each annotation you add while testing, burns them into the video on stop, and verifies the result with …
Read the whole file at its exact version.
How to install
mdr add michaelshimeles/skills/evidence-driven-testing@sha256:c5800269a6abb10dThe line at the top of this page pins the label v1.2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_nya7sqeji6c5uhdu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 1, 2026 and Oct 19, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2 latest | 2026-10-19 | 69558ea | 16,932 B | A | view · diff |
| v1.2 | 2026-10-15 | ababbf7 | 16,864 B | A | view · diff |
| v1.2 | 2026-09-01 | 65f1e4d | 15,587 B | A | view · diff |
| v1.2 | 2026-09-01 | b15b203 | 15,356 B | A | view · diff |
| v1.2 | 2026-09-01 | 2dfb672 | 15,206 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16932 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
michaelshimeles/skills · 1,373 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nya7sqeji6c5uhdu GET https://markdownregistry.com/api/v1/resolve?ref=michaelshimeles/skills/evidence-driven-testing GET https://markdownregistry.com/api/v1/blob/c5800269a6abb10d6da63b468e6112082dea3b9b38077b9e1f32fa8151e3752c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.