user-testing SKILL.md skillA
user-testing from moonray/repoprompt-workflows is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add moonray/repoprompt-workflows/user-testing@git:20260820.63ac0b2Pins git:20260820.63ac0b2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- moonray/repoprompt-workflows
- Path
.agents/skills/user-testing/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260820.63ac0b2, committed Aug 20, 2026
- First version recorded
- Jul 10, 2026
- Size
- 4,735 bytes
- Repository stars
- 11
- License
- MIT
Use when finishing a user-facing/frontend feature, to verify it actually works for the person it's built for — not just that automated tests pass. Drives the real rendered UI via automation — browser tools (e.g. chrome-devtools) for web/HTML, platform UI automation for non-HTML native UI — through the actual user workflows, screenshotting each step and checking console/network, to catch defects unit/contract tests miss. A human hand-off is the optional gold standard. Distinct from test-quality…
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
# User Testing
## Intent
A frontend feature is not done because its automated tests pass. Automated tests assert code contracts (an element exists, an endpoint returns 200, a tab switches); they do not assert that the feature works or looks right for the person it's built for. Spec-conformance is not a substitute either — the spec itself can be wrong; only driving the real UI tells you. The primary method is tool-driven: the agent drives the real rendered UI (browser automation for web/HTML, platform UI automation for non-HTML native UI), so user testing is scalable and not dependent on a human being free. A human hand-off is the gold standard, not the only way.
## When to use
- Before declaring done (or closing) any user-facing/frontend change: a screen, tab, form, flow, layout, or anything a human sees or interacts with.
- When asked "did you user-test this?" or "does this actually work?"
- When automated tests are green but the feature has not been used as a user would use it.
## When it can't run ("when possible")
…Read the whole file at its exact version.
How to install
mdr add moonray/repoprompt-workflows/user-testing@sha256:e78c54a7cbc126e3The line at the top of this page pins the label git:20260820.63ac0b2, 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_mddrs3s3uyk2jfuv)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 10, 2026 and Aug 20, 2026, about one every 41 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260820.63ac0b2 latest | 2026-08-20 | 63ac0b2 | 4,735 B | A | view · diff |
| git:20260710.161b2ae | 2026-07-10 | 161b2ae | 4,237 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 (4735 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
moonray/repoprompt-workflows · 11 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mddrs3s3uyk2jfuv GET https://markdownregistry.com/api/v1/resolve?ref=moonray/repoprompt-workflows/user-testing GET https://markdownregistry.com/api/v1/blob/e78c54a7cbc126e385fa865a9e1e98a777782eb47b6bd2dd12de7ecdf77ea10b
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.
More from moonray/repoprompt-workflows
Every file in moonray/repoprompt-workflows