chrome-qa-loop SKILL.md skillA
chrome-qa-loop from andersonlimahw/lemon-ai-hub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add andersonlimahw/lemon-ai-hub/chrome-qa-loop@git:20260801.d400e34Pins git:20260801.d400e34 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- andersonlimahw/lemon-ai-hub
- Path
plugins/chrome-qa-loop/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260801.d400e34, committed Aug 1, 2026
- Size
- 5,139 bytes
- Repository stars
- 17
- License
- MIT
Reusable closed loop for exploratory QA over ANY live web app via the Chrome DevTools MCP. You trigger it → Claude navigates the app with full per-screen doc context → writes one markdown report per finding → you review → hand back for triage → fixes enter a Feature-Development loop. Product-agnostic: target URL, screen manifest and report paths come from chrome-qa-loop.config.json. Trigger with "/chrome-qa-loop", "qa loop", "explore the app", "test the live app", "chrome qa".
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
# Chrome QA Loop
A reusable human-in-the-loop QA cycle, driven by Claude via the **Chrome DevTools MCP** (`chrome-devtools-mcp`). Generalized from a real implementation that QA'd VibingCash (see README) — nothing here is bound to a single product.
```
you trigger ─▶ EXPLORE (Chrome DevTools MCP) ─▶ REPORT (md per finding) ─▶ you REVIEW ─▶ TRIAGE ─▶ IMPLEMENT (feature-dev loop) ─▶ REFLECT ─▶ (back to you)
```
## Configuration (per repo)
The loop reads `chrome-qa-loop.config.json` from the target repo root. If absent, ask the operator once and persist it:
```json
{
"TARGET_BASE_URL": "https://example.com",
"SCREEN_MANIFEST": "docs/qa/PLAN.md",
"OWNER_DOCS_ROOT": "docs/features/",
"REPORTS_ROOT": "docs/qa/reports/",
"RUN_MODE": "core"
}
```
Scaffold the manifest + report contract from `templates/` in this plugin:
`PLAN.template.md`, `screen-manifest.template.md`, `report.template.md`.
## Invocation
```
/chrome-qa-loop [mode=guest|guest-smoke|guest-full|smoke|core|full] # run an exploration pass (default: core)
/chrome-qa-loop triage run=<run-id> # turn reviewed reports into tasks + PLAN stubs
```
…Read the whole file at its exact version.
How to install
mdr add andersonlimahw/lemon-ai-hub/chrome-qa-loop@sha256:b4b4c4af3cc050f5The line at the top of this page pins the label git:20260801.d400e34, 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_u73vzdzh5t2hkz22)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 1, 2026.
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 (5139 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
andersonlimahw/lemon-ai-hub · 17 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_u73vzdzh5t2hkz22 GET https://markdownregistry.com/api/v1/resolve?ref=andersonlimahw/lemon-ai-hub/chrome-qa-loop GET https://markdownregistry.com/api/v1/blob/b4b4c4af3cc050f5ee994d64c64a0ba7b9e3a08ac929a18ab6017e32fec1549c
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 andersonlimahw/lemon-ai-hub
Every file in andersonlimahw/lemon-ai-hub