How do I install the QA Sweep skill?

Run npx skillmds@latest add awrshift/qa-sweep in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is QA Sweep safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with QA Sweep?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is QA Sweep free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published QA Sweep?

awrshift (@awrshift) published this skill. Their other Agent Skills are listed on their SkillMD profile.

QA Sweep by awrshift — Agent Skill

Name: QA Sweep
Rating: 4.5 (4 reviews)
Author: awrshift

QA Sweep

Run a multi-lens agent QA sweep of the RUNNING product: spawn `qa` agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder. Use whenever the user asks to QA, test, or probe the product from the user's side — "qa sweep", "test the UI", "walk the flows", "find inconsistencies", "check how this looks to a client" — and proactively after integrating any large UI slice, before a milestone, or when a manual walk found one bug and siblings are likely. Trigger even when the user names only one angle (e.g. "check the API errors") — pick the matching lens subset. NOT for unit testing (your test suite does that) and NOT a replacement for the integrator's own acceptance walk.

awrshift 5eea164 3.2 KB Updated Sep 10, 2026

File contents

QA Sweep — multi-lens agent QA of the live product

Read projects/<name>/qa/README.md FIRST (the protocol SSOT: environment rules · the five lens briefs · findings format · triage) — the lens briefs in agent prompts come verbatim from there, and the account/mutation policy it sets is a hard rail, not advice. If that file doesn't exist yet, create it from the layer's protocol template (${CLAUDE_PLUGIN_ROOT}/reference/qa-PROTOCOL-TEMPLATE.md in the kit repo — copy it from there if this project only adopted the layer's .claude/ files) and fill the placeholders before sweeping.

Steps

Preflight (integrator, by hand): bring up the stack the protocol names (app · API · store) · pick the account per the protocol's policy (the demo/real account = OBSERVE-ONLY always; the seeded sacrificial account = mutation QA only when the run brief grants it) · make sure nothing else is writing to the shared store during the sweep (no integration test suites, no live jobs).
Pick lenses for this run (default: user-flow + contract in parallel, then edge-state, then honesty + ux-critique). Browser lenses run CONCURRENTLY via the isolated Playwright MCP servers the protocol lists (one server per concurrent browser agent — mechanism + logged-in seed recipe in the protocol § Parallel lenses). Browser lenses: user-flow · edge-state · ux-critique. Non-browser: contract (curl) · honesty (curl + read-only store queries).
Spawn qa agents with the lens brief from the protocol § Lens briefs + the run scope (which screens/flows changed recently — QA the delta first, then one broad pass).
Verify before ticketing (the fact-check rule): reproduce every P1/P2 finding yourself (the named repro steps) before it becomes a ticket. Unreproducible → back to the agent or drop with a note. «Impressions» never become tickets directly.
Land the results: verified findings → backlog tickets (P1/P2) or a minors batch (P3) · one run record projects/<name>/qa/qa-run-YYYYMMDD.md (lenses run · coverage · findings table with verified/dropped status · pointers to tickets) · a row in the protocol's § Runs index.
Cleanup: stop dev servers, remove stray screenshots from the repo root, re-seed the sacrificial account if a mutation run dirtied it.

---name: qa-sweepdescription: Run a multi-lens agent QA sweep of the RUNNING product: spawn `qa` agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder. Use whenever the user asks to QA, test, or probe the product from the user's side — "qa sweep", "test the UI", "walk the flows", "find inconsistencies", "check how this looks to a client" — and proactively after integrating any large UI slice, before a milestone, or when a manual walk found one bug and siblings are likely. Trigger even when the user names only one angle (e.g. "check the API errors") — pick the matching lens subset. NOT for unit testing (your test suite does that) and NOT a replacement for the integrator's own acceptance walk.---# QA Sweep — multi-lens agent QA of the live productRead `projects/<name>/qa/README.md` FIRST (the protocol SSOT: environment rules · the five lens briefs ·findings format · triage) — the lens briefs in agent prompts come verbatim from there, and theaccount/mutation policy it sets is a hard rail, not advice. If that file doesn't exist yet,create it from the layer's protocol template (`${CLAUDE_PLUGIN_ROOT}/reference/qa-PROTOCOL-TEMPLATE.md` inthe kit repo — copy it from there if this project only adopted the layer's `.claude/` files)and fill the placeholders before sweeping.## Steps1. **Preflight (integrator, by hand):** bring up the stack the protocol names (app · API · store) · pick the account per the protocol's policy (the demo/real account = OBSERVE-ONLY always; the seeded sacrificial account = mutation QA only when the run brief grants it) · make sure nothing else is writing to the shared store during the sweep (no integration test suites, no live jobs).2. **Pick lenses** for this run (default: user-flow + contract in parallel, then edge-state, then honesty + ux-critique). Browser lenses run CONCURRENTLY via the isolated Playwright MCP servers the protocol lists (one server per concurrent browser agent — mechanism + logged-in seed recipe in the protocol § Parallel lenses). Browser lenses: user-flow · edge-state · ux-critique. Non-browser: contract (curl) · honesty (curl + read-only store queries).3. **Spawn `qa` agents** with the lens brief from the protocol § Lens briefs + the run scope (which screens/flows changed recently — QA the delta first, then one broad pass).4. **Verify before ticketing (the fact-check rule):** reproduce every P1/P2 finding yourself (the named repro steps) before it becomes a ticket. Unreproducible → back to the agent or drop with a note. «Impressions» never become tickets directly.5. **Land the results:** verified findings → backlog tickets (P1/P2) or a minors batch (P3) · one run record `projects/<name>/qa/qa-run-YYYYMMDD.md` (lenses run · coverage · findings table with verified/dropped status · pointers to tickets) · a row in the protocol's § Runs index.6. **Cleanup:** stop dev servers, remove stray screenshots from the repo root, re-seed the sacrificial account if a mutation run dirtied it.

Frequently asked questions