qa-test skillA
qa-test is agent-read markdown (skill) from teambrilliant/dev-skills: Browser-based QA verification after any implementation. Use when someone says "QA this", "test this in browser", "verify the feature", "qa test", "browser test", or after /dev-skills:execute-plan to verify acceptance criteria in a real browser. Opens Chrome via MCP, exercises each acceptance criterion, verifies via DOM snapshots, and reports pass/fail. The "closer" for every implementation — proof it works, not just that tests pass..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified before it reaches your agent: the main file against the SHA-256 recorded here, the others against the git hashes of its source commit. The deterministic audit below grades the latest version, and the same checks always give the same file the same grade.
What the file says
# QA Test Verify implemented features in a real browser. Exercise each acceptance criterion, verify via snapshots, report results. **Context-efficient design**: browser testing runs in a sub-agent so snapshot/interaction data stays out of the main thread. Main thread only sees compact pass/fail summaries. **Sub-agent rule:** Always use sub-agents for browser interaction and pre-flight exploration — these are broad, multi-step tasks that generate significant context. Fan out pre-flight and browser testing as separate sub-agents when they're independent. Handle directly only when verifying a single, specific element or reading one file for criteria. ## Modes - **Agent mode** — invoked by `/dev-skills:execute-plan` or any unattended run. No questions to the user. Login and other setup go through the harness bypass the plan names (seeded session, test token, dev auth route). If there is none and the criterion can't be reached, return `BLOCKED: <what's needed>` for that criterion to the caller instead of waiting. - **Human mode** — invoked directly by a user who's at the keyboard. Interactive setup and "fix or expected?" questions are fine. ## Process …
Read the whole file at its exact version.
How to install
mdr add teambrilliant/dev-skills/qa-test@git:20260927.b9558d0mdr add teambrilliant/dev-skills/qa-test@sha256:0fbd0ea33ba01711Pin to a label to follow the author's releases, or to a sha256 for exact bytes. Either way the resolved hash is written to mdr.lock, and mdr install fetches those bytes again and checks them, so it installs them exactly or fails.
[](https://markdownregistry.com/a/art_5weue4e4wgls4sow)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260927.b9558d0 latest | 2026-09-27 | b9558d0 | 12,836 B | A | view · diff |
| git:20260609.05883da | 2026-06-09 | 05883da | 11,796 B | A | view · diff |
| git:20260419.9e33b7c | 2026-04-19 | 9e33b7c | 12,196 B | A | view · diff |
| git:20260414.7c5f774 | 2026-04-14 | 7c5f774 | 11,444 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 (12836 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
teambrilliant/dev-skills · 6 stars · license none · pushed 2026-09-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5weue4e4wgls4sow GET https://markdownregistry.com/api/v1/resolve?ref=teambrilliant/dev-skills/qa-test GET https://markdownregistry.com/api/v1/blob/0fbd0ea33ba01711aa1dabb3bdfb4dbdddad6a20618dc44fdffbbc468f112fd8
Your agent 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.
More from teambrilliant/dev-skills
Every file in teambrilliant/dev-skills