agentleFS
jackneiljackneil/claude-jacked/.claude/skills/qa/SKILL.md

qa

Skill2 starsChanged 11 days agoMITView on GitHub

Browser-based QA testing: targeted single-component check (/qa) or parallel multi-aspect review (/ux). (repo)

  • Reads credentials
  • Deletes or force-pushes
  • Installs packages

The file

Show its rules and text

We split this skill into the rules it gives an agent

40 rules. About 0 are common, 24 are distinctive, and 16 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈24

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 16

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Update pages (update.html, update_bootstrap.html) and the install summary: phases render and errors read clearly.

    line 28
  2. Distinctive:

    Before using the config above, run a lightweight drift check (advisory only.

    line 35
  3. Very specific:

    If EITHER differs, count the intervening commits (git rev-list --count <generated-commit>..HEAD 2>/dev/null) and surface one line, then …

    line 38
  4. Distinctive:

    If the generated commit is unreachable (history rewritten) or the manifest set changed, surface the nudge regardless of commit count.

    line 40
  5. Very specific:

    If this command was invoked via a local config wrapper (you see a ## Repo Config section earlier in the prompt), use that config to skip …

    line 51
  6. Very specific:

    If the config overlay date is more than 90 days old, mention: "Your /qa config is over 90 days old — consider running /jacked-setup qa to …

    line 60
  7. Very specific:

    If no ## Repo Config section is present, run all detection steps normally.

    line 62
  8. Distinctive:

    Check which browser automation tools are available.

    line 66
  9. Very specific:

    Option D — agent-browser CLI: Run npx agent-browser --version via Bash.

    line 102
  10. Distinctive:

    Run git diff --name-only HEAD to see what files changed.

    line 124
  11. Distinctive:

    If no UI files changed, tell the user and ask if they still want to proceed.

    line 132
  12. Distinctive:

    After the main QA pass on the primary page (Run QA Pass step), perform a concrete spot-check on each flagged page:

    line 140
  13. Distinctive:

    Check for: page loads without error, no blank screens, no visibly broken layout, no console errors

    line 143
  14. Distinctive:

    If no shared files changed, skip the spot-check entirely.

    line 146
  15. Very specific:

    NOT prove the DB — if you can't read its env, stay read-only).

    line 159
  16. Very specific:

    READ-ONLY and tell the user the interactive checks need an isolated instance.

    line 164
  17. Very specific:

    EVERY write in this command — login, form submits, create/edit/delete, and any replay/iterate-until-green re-run.

    line 165
  18. Very specific:

    If $ARGUMENTS contains a URL: treat it as the target only — it is STILL subject to the full (a)–(d) gate above before any mutating …

    line 168
  19. Very specific:

    Check conversation context for recently mentioned URLs (e.g., http://localhost:3000)

    line 175
  20. Very specific:

    Run lsof -i -P -sTCP:LISTEN | grep -E ':(1420|1421|3000|3001|4000|4173|4200|4321|5000|5173|5174|6006|8000|8001|8080|8765|8888) ' to find …

    line 176
  21. Distinctive:

    If a server is found, use it.

    line 178
  22. Very specific:

    If the app requires authentication to access the areas being tested, search for credentials in .env files before asking the user.

    line 182
  23. Very specific:

    Run from the repo root. Skip any variable whose name starts with DB_, DATABASE_, POSTGRES_, REDIS_, MONGO_, S3_, or AWS_ — those are …

    line 196
  24. Very specific:

    Security note: If credentials were found in .env.local, .env.development, or .env.test in a repo you just cloned, verify this is an …

    line 204
  25. Distinctive:

    Start each UI area from a known state so cross-test contamination doesn't manufacture false bugs (a half-filled form, a leftover session, a …

    line 219
  26. Distinctive:

    Don't mutate real or shared records when a throwaway path exists — use a seeded/test entity, not production data.

    line 221
  27. Distinctive:

    After the pass, restore state: log out, clear any half-filled form, and close or delete entities you created.

    line 222
  28. Distinctive:

    Look for broken layouts, missing elements, overlapping content

    line 230
  29. Distinctive:

    Check that text is readable and properly aligned

    line 231
  30. Distinctive:

    Verify colors, spacing, and visual hierarchy look correct

    line 232
  31. Distinctive:

    Test navigation — do page transitions work?

    line 237
  32. Distinctive:

    Check dropdowns, modals, toggles, and other interactive elements

    line 238
  33. Distinctive:

    Check the browser console for JavaScript errors

    line 241
  34. Distinctive:

    Check if an accessibility specialist lens is installed:

    line 263
  35. Distinctive:

    If found, read it and incorporate its "What to check" items into your testing checklist.

    line 269
  36. Very specific:

    Lighthouse: run mcp__chrome-devtools__lighthouse_audit (mode=navigation, device matching the viewport you're testing) on the primary …

    line 283
  37. Distinctive:

    If everything passes, say so clearly.

    line 315
  38. Distinctive:

    If the user says yes:

    line 323
  39. Distinctive:

    If the user declines, skip straight to Cleanup.

    line 329
  40. Distinctive:

    Remove the screenshot directory after presenting the report:

    line 333

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Generated by /jacked-setup - 2026-11-03 | Template v2 | Engine: jacked v0.110.2

Standalone - no dependencies. Commit this file. To update: uv tool install --upgrade claude-jacked && jacked install && /jacked-setup qa

Repo Config

  • Project: claude-jacked
  • Stack: vanilla JS / HTML / CSS dashboard (no framework, no build step), Tailwind 3.4 via the vendored play-CDN script (jacked/data/web/js/vendor/tailwindcss-3.4.17.js), Chart.js + SweetAlert2 vendored; served by FastAPI from jacked/data/web/
  • Browser Tool: Chrome DevTools MCP (preferred), Playwright MCP, or Claude-in-Chrome (all three configured on this machine)
  • Dev Server Port: 8321 (the jacked dashboard). It is served by the jacked background service (autostart; jacked service status prints the URL). Do NOT start a second server, and do NOT restart or kill the service. jacked webux is a foreground alternative only when the service is stopped; both cannot own the port.
  • Component Paths: jacked/data/web/js/components/ (accounts, account-actions, oauth-flows, codex-add-flow, token-pills, usage + usage-overview/-sessions/-trends, analytics, auto-swap, sessions, installations, install-summary, remote-access, settings, logs + logs-hooks/-server/-version-checks, header, panel), shared JS in jacked/data/web/js/ (app.js, utils.js, websocket.js, util/provider.js), page shells index.html, panel.html, update.html, update_bootstrap.html, CSS in jacked/data/web/css/

Credential Hints

none found: the local dashboard on 127.0.0.1:8321 has no login. Only ask the user about creds if a gated view is added later (remote access over Tailscale is network-gated, not login-gated).

Framework-Specific Checks

Vanilla JS (no framework/bundler): emphasize:

  • Script load order: no ReferenceError from a missing global (the scripts in index.html load in a fixed order); if type="module" is used, verify import boundaries resolve.
  • DOM/state freshness: confirm views update after actions (stale cards after an action are a recurring bug class here); live updates arrive by WebSocket push (websocket.js); the account view also refreshes on a timer (app.js: every 120 s while connected, every 30 s while disconnected) and the log view falls back to polling while the socket is down, so check freshness across a disconnect and a reconnect; check handlers re-render and clean up their listeners.
  • Tailwind (play CDN): classes must exist at runtime; check responsive classes at 375 / 820 / 1366 px.
  • Dark theme: verify WCAG-AA contrast on pills/cards and catch any dark-on-dark text.
  • Multi-account panels (Claude and Codex providers): exercise 1 / few / many accounts, plus empty / loading / error states and the re-auth flow.
  • Settings > Features, Hooks section: the hook and settings integrity panel is read-only (OK line with baseline time, or a list of changes outside jacked; no accept button; the scope note about unwatched scripts renders).
  • Memory Vault settings panel: verify vault status + the unreadable-settings banner render correctly, and toggles persist.
  • Update pages (update.html, update_bootstrap.html) and the install summary: phases render and errors read clearly.
<!-- Staleness fingerprint - the engine compares these against the live repo on each run -->
  • Generated at commit: b3c14640091e7653e438cfcb1c2254f610c29550
  • Detected stack: pyproject.toml

Config Staleness Check

Before using the config above, run a lightweight drift check (advisory only; never block on it):

  1. git rev-parse HEAD and compare to Generated at commit above.
  2. ls package.json pyproject.toml go.mod Cargo.toml setup.py Gemfile pom.xml build.gradle composer.json mix.exs 2>/dev/null and compare the manifest set to Detected stack above.
  3. If EITHER differs, count the intervening commits (git rev-list --count <generated-commit>..HEAD 2>/dev/null) and surface one line, then continue:

    ⚠️ This /qa config was generated N commits ago and the stack/paths may have drifted. Re-run /jacked-setup qa to refresh. If the generated commit is unreachable (history rewritten) or the manifest set changed, surface the nudge regardless of commit count. Never stop or skip the run on a staleness mismatch.

<!-- ENGINE - DO NOT EDIT BELOW THIS LINE -->

Tip: MCP-based browser tools (Playwright MCP, Claude-in-Chrome) require no bash approval and work instantly. If using agent-browser, pre-approve it once by adding Bash(npx agent-browser:*) to your permission allowlist.

You are a QA engineer testing UI changes from the current coding session. Follow these steps systematically.

Config Override

If this command was invoked via a local config wrapper (you see a ## Repo Config section earlier in the prompt), use that config to skip detection:

  • Browser Tool specified? → Skip Step 1, use the declared tool directly (fall back to detection if it's unavailable)
  • Stack declared? → Skip tech stack inference in Step 2
  • Dev Server Port specified? → Use it in Step 4 URL detection (still check lsof as fallback)
  • ## Dev Servers table present (multi-server / monorepo repo)? → In Step 4, bring up ALL listed servers (a frontend pointed at a dead backend fails silently) before testing — this supersedes a single Dev Server Port
  • Component Paths may be per-app (e.g. apps/desktop/src/...` (desktop)) when the repo has apps/*/ — treat each app's paths as scoping hints for the app that owns the changed file
  • Credential Hints listed? → Use those variable names in Step 5 credential search
  • Framework-Specific Checks listed? → Add them to Step 6 QA pass (in addition to standard checks)

If the config overlay date is more than 90 days old, mention: "Your /qa config is over 90 days old — consider running /jacked-setup qa to refresh it."

If no ## Repo Config section is present, run all detection steps normally.

Step 1: Detect Browser Tools

Check which browser automation tools are available. Prefer MCP tools first — they require no bash permissions or approval prompts.

Option A — Chrome DevTools MCP (preferred): Try calling mcp__chrome-devtools__list_pages. If it works, use Chrome DevTools MCP tools for all browser interaction:

  • mcp__chrome-devtools__navigate_page → open pages
  • mcp__chrome-devtools__take_snapshot → accessibility tree (preferred for element detection)
  • mcp__chrome-devtools__take_screenshot → visual screenshot
  • mcp__chrome-devtools__click → click element by ref from snapshot
  • mcp__chrome-devtools__fill → fill input fields
  • mcp__chrome-devtools__evaluate_script → run JavaScript on page
  • mcp__chrome-devtools__emulate → change viewport size (mobile/tablet testing)
  • mcp__chrome-devtools__list_console_messages → check for JS errors
  • mcp__chrome-devtools__list_network_requests → check for failed requests

If Chrome DevTools MCP fails (tool call errors, connection refused, or no pages returned): Tell the user:

Chrome DevTools MCP is not responding. To fix:

1. Chrome version: You need Chrome 144 or newer.
   Check yours at chrome://version — update if needed.

2. Enable remote debugging (pick one):
   a) In Chrome: go to chrome://inspect/#remote-debugging and enable it
   b) Or launch Chrome with: --remote-debugging-port=9222
      macOS:  /Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
      Linux:  google-chrome --remote-debugging-port=9222

3. If not installed: run `jacked install` (includes Chrome DevTools MCP setup)
   or manually: claude mcp add -s user chrome-devtools -- npx chrome-devtools-mcp@latest --autoConnect

Then continue to Option B as fallback.

Option B — Playwright MCP: Try using mcp__plugin_playwright_playwright__browser_snapshot. If it works, use Playwright tools for all browser interaction. Note to user:

Using Playwright MCP (Chrome DevTools MCP is preferred — see above). Playwright opens separate browser windows.

Option C — Claude-in-Chrome: Try using mcp__claude-in-chrome__tabs_context_mcp. If it works, use Claude-in-Chrome tools for all browser interaction.

Option D — agent-browser CLI: Run npx agent-browser --version via Bash. If it succeeds, use agent-browser for all browser interaction via Bash tool calls (e.g., npx agent-browser open <url>, npx agent-browser snapshot, npx agent-browser screenshot <path>, npx agent-browser click <ref>, npx agent-browser type <ref> <text>, npx agent-browser eval <js>). This reuses your existing browser session — no new windows.

Note: npx requires an approval prompt unless pre-approved. Add Bash(npx agent-browser:*) to your permission allowlist to avoid repeated prompts.

If none are available: Tell the user:

No browser tools detected. Recommended setup:

  jacked install    (configures Chrome DevTools MCP automatically)

Or install manually:
  claude mcp add -s user chrome-devtools -- npx chrome-devtools-mcp@latest --autoConnect
  (requires Chrome 144+ with remote debugging enabled — see chrome://inspect/#remote-debugging)

Alternatives:
- Playwright MCP: Add to .mcp.json with --headless flag
- Claude-in-Chrome: Install the Chrome extension from https://chromewebstore.google.com
- agent-browser: npm i -g agent-browser (requires npx pre-approval)

Then stop.

Step 2: Identify What Changed

Run git diff --name-only HEAD to see what files changed. Filter for UI-relevant files:

  • .js, .jsx, .ts, .tsx, .css, .scss, .less, .html
  • .vue, .svelte, .erb, .jinja, .jinja2

Ignore files in node_modules/, dist/, build/, __pycache__/, and test files (*.test.*, *.spec.*).

Summarize what UI areas were likely affected (e.g., "Login form styling", "Dashboard data table", "Navigation component").

If no UI files changed, tell the user and ask if they still want to proceed.

Step 3: Check for Cross-Page Impact

After identifying changed files, check if any are shared infrastructure — global CSS, router/navigation, state management, API client, layout components, shared utilities, or WebSocket/event bus files. Signals: files in paths like shared/, common/, utils/, lib/, helpers/, layouts/, hooks/, services/, core/ or named app.*, main.*, router.*, store.*, state.*, theme.*, websocket.*. Do NOT flag index.* (module re-exports), *.stories.*, *.module.css, or *.d.ts.

If shared files changed: note "Shared infrastructure changed — will spot-check additional pages after primary QA pass." Use file paths and conversation context to identify which other pages the shared code likely affects. If the change is truly global (e.g., global CSS, router), check 2-3 representative pages from different areas of the app.

After the main QA pass on the primary page (Run QA Pass step), perform a concrete spot-check on each flagged page:

  1. Navigate to the page
  2. Take one snapshot (accessibility tree)
  3. Check for: page loads without error, no blank screens, no visibly broken layout, no console errors
  4. Move on — anything deeper is /ux territory

If no shared files changed, skip the spot-check entirely.

Step 4: Determine App URL

Isolate → PROVE it → only THEN test hard. Fail closed. This pass clicks, fills forms, and may submit/save/delete. First get an isolated copy (best available): (1) a PR / preview / ephemeral deploy — check gh pr checks / the PR's "View deployment" links; (2) spin it up locally — dev server + a local DB with seed/fixture data (docker compose up, manage.py runserver, npm run dev/pnpm dev, a seed/migrate command, .env.local); (3) a disposable staging. Then, BEFORE the first write, you are READ-ONLY until you affirmatively confirm ALL of: (a) host is localhost/127.0.0.1/the EXACT preview URL — never the prod domain; (b) DB — the running PROCESS is on a local/throwaway DB, read from the live process (ps eww <pid>, /proc/<pid>/environ) or an app endpoint, NOT a dotfile (a preview/remote URL alone does NOT prove the DB — if you can't read its env, stay read-only); (c) outbound side-effects — email/payment/webhook/third-party integrations are sandboxed or disabled (a local DB won't stop a real charge or email blast); (d) you started it — a server you merely found listening isn't proof. ANY doubt → it's production, stay read-only. Only once ALL pass: go after the edge and destructive paths freely — that's the payoff of isolating. Forced onto production? Stay READ-ONLY and tell the user the interactive checks need an isolated instance. This gate governs EVERY write in this command — login, form submits, create/edit/delete, and any replay/iterate-until-green re-run; you are READ-ONLY at each such step until ALL of (a)–(d) pass.

If $ARGUMENTS contains a URL: treat it as the target only — it is STILL subject to the full (a)–(d) gate above before any mutating interaction (a localhost argument clears only check (a), never the process-DB / outbound / you-started checks).

Otherwise, detect the dev server(s) in this order:

  1. ## Dev Servers table declared (multi-server / monorepo)? → ensure EVERY listed server is up before testing — a frontend whose backend API is dead is the #1 real "looks broken" failure. Start any that aren't listening (honoring each app's "server may be user-managed, don't kill it" note), and respect the (a)–(d) isolation gate for any server you start. In a monorepo, map each changed file to the app that owns it (nearest apps/*/ boundary) so you test on the right server.
  2. Single Dev Server Port set (config or context)? → use it.
  3. Check conversation context for recently mentioned URLs (e.g., http://localhost:3000)
  4. Run lsof -i -P -sTCP:LISTEN | grep -E ':(1420|1421|3000|3001|4000|4173|4200|4321|5000|5173|5174|6006|8000|8001|8080|8765|8888) ' to find common dev server ports

If a server is found, use it. If multiple are found, ask the user which one. If none found, ask the user for the URL.

Step 5: Check for Login Credentials

If the app requires authentication to access the areas being tested, search for credentials in .env files before asking the user.

Find the repo root:

git rev-parse --show-toplevel 2>/dev/null || pwd

Scan env files in priority order — run each grep separately (all are auto-approved, stop at first file with results):

grep -iE "^[A-Z_]*(EMAIL|PASSWORD|USERNAME|LOGIN)[A-Z_]*=" .env.local
grep -iE "^[A-Z_]*(EMAIL|PASSWORD|USERNAME|LOGIN)[A-Z_]*=" .env.development
grep -iE "^[A-Z_]*(EMAIL|PASSWORD|USERNAME|LOGIN)[A-Z_]*=" .env.test
grep -iE "^[A-Z_]*(EMAIL|PASSWORD|USERNAME|LOGIN)[A-Z_]*=" .env

Run from the repo root. Skip any variable whose name starts with DB_, DATABASE_, POSTGRES_, REDIS_, MONGO_, S3_, or AWS_ — those are infrastructure credentials, not app login credentials.

Announce what was found (variable names only, never values):

  • ✓ Found: TEST_USER_EMAIL + TEST_USER_PASSWORD in .env.local — "Using these for login."
  • ✗ Not found: "No login credentials found in env files." → Ask the user for credentials.

If login with found credentials fails: Warn the user ("Credentials from .env.local were rejected") and ask for correct credentials. Do not retry silently.

Security note: If credentials were found in .env.local, .env.development, or .env.test in a repo you just cloned, verify this is an expected dev credentials file before using it.

Step 6: Run QA Pass

Screenshot setup (agent-browser and Playwright only — Chrome does not support file-based screenshots):

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
rm -rf "$REPO_ROOT/tmp/qa_screenshots"
mkdir -p "$REPO_ROOT/tmp/qa_screenshots"

Save all screenshots to $REPO_ROOT/tmp/qa_screenshots/<descriptive-name>.png. Add tmp/ to your project's .gitignore if it isn't already there.

State Hygiene

Start each UI area from a known state so cross-test contamination doesn't manufacture false bugs (a half-filled form, a leftover session, a record mutated by an earlier check):

  • Begin from a fresh navigation, or — where the tool supports it — an isolated/incognito context (Chrome DevTools MCP: mcp__chrome-devtools__new_page with isolatedContext partitions cookies/storage; Playwright: a fresh browser context).
  • Don't mutate real or shared records when a throwaway path exists — use a seeded/test entity, not production data.
  • After the pass, restore state: log out, clear any half-filled form, and close or delete entities you created.

Warning — live session: With Chrome DevTools MCP --autoConnect you are driving the user's REAL signed-in Chrome, not a sandbox. Do not leave it mid-flow, on a destructive confirmation, or logged into something it wasn't before — leave it where you found it.

Navigate to the app URL. For each UI area affected by the changes:

Visual Check

  • Take a snapshot (accessibility tree preferred over screenshot for actionability)
  • Look for broken layouts, missing elements, overlapping content
  • Check that text is readable and properly aligned
  • Verify colors, spacing, and visual hierarchy look correct

Interactive Testing

  • Click buttons and links — do they respond correctly?
  • Fill out forms — do inputs accept text, show validation?
  • Test navigation — do page transitions work?
  • Check dropdowns, modals, toggles, and other interactive elements

Console Errors

  • Check the browser console for JavaScript errors
  • Per-tool calls: Chrome DevTools MCP mcp__chrome-devtools__list_console_messages (drill into one with mcp__chrome-devtools__get_console_message); Playwright mcp__plugin_playwright_playwright__browser_console_messages; Claude-in-Chrome mcp__claude-in-chrome__read_console_messages
  • Flag any errors, especially new ones related to the changed code

Network Errors

A failed API call is a leading cause of "the UI looks broken" and is invisible to a visual + console pass — check it explicitly. After exercising each UI area, list the network requests and flag anything tied to the changed code that didn't succeed:

  • Non-2xx/3xx responses (4xx/5xx), failed fetches, CORS errors, and pending/hung requests that never resolve
  • Per-tool calls: Chrome DevTools MCP mcp__chrome-devtools__list_network_requests (drill into one with mcp__chrome-devtools__get_network_request); Playwright mcp__plugin_playwright_playwright__browser_network_requests; agent-browser npx agent-browser eval "performance.getEntriesByType('resource')" (or its network-log command if available). Note: PerformanceResourceTiming exposes no HTTP status code, so the agent-browser eval path cannot read response status — use its dedicated network-log command if available, otherwise capture the request URL/duration and infer failures from transferSize === 0/hung timing rather than a status code.
  • For each failure, record the URL, the status code (when the tool exposes it — the agent-browser eval path above does not, so omit it there), and whether it correlates with a visible UI defect (empty state, a spinner that never resolves, an error toast, missing data). Surface it even when the page otherwise renders.

Edge Cases

  • Empty states: What happens with no data?
  • Long text: Does overflow handling work?
  • Special characters: Do inputs handle <script>, quotes, unicode?
  • Rapid interactions: Double-clicking, fast navigation

Responsive (if applicable)

  • Resize the browser to mobile width (375px) and check layout
  • Resize to tablet width (768px) and check layout

Accessibility Lens (if available)

Check if an accessibility specialist lens is installed:

ls ~/.claude/lenses/accessibility.md .claude/lenses/accessibility.md 2>/dev/null | head -1

If found, read it and incorporate its "What to check" items into your testing checklist. These are additive — they don't replace your existing QA checks. Focus on items that can be verified visually or via browser DevTools:

  • Color contrast (use DevTools accessibility panel or Lighthouse)
  • Keyboard navigation (tab through the page, verify focus indicators)
  • Semantic HTML (inspect elements — buttons should be <button>, not <div>)
  • Form labels (each input has a visible, associated <label>)
  • Focus management after interactions (modal open/close, route changes)

Skip items that require specialized tooling (screen reader testing, automated WCAG scanners) unless the user specifically requests them.

Performance & Lighthouse (Chrome DevTools MCP only, opt-in)

Run this only when Chrome DevTools MCP is the active tool AND the change plausibly affects performance or a11y — new/large images or fonts, bigger bundles, render-blocking resources, a new heavy component, or markup/contrast changes. Skip it for quick single-component checks so they stay fast.

  • Lighthouse: run mcp__chrome-devtools__lighthouse_audit (mode=navigation, device matching the viewport you're testing) on the primary changed page for accessibility / SEO / best-practices. Note: Lighthouse here EXCLUDES performance — use the trace below for Core Web Vitals.
  • Performance trace (optional): navigate to the target URL first, then mcp__chrome-devtools__performance_start_trace — by default it reloads the page and auto-stops once the page settles, so no manual reload or separate performance_stop_trace call is needed (pass reload=false/autoStop=false only if you want to drive an interaction yourself, then call mcp__chrome-devtools__performance_stop_trace). Then mcp__chrome-devtools__performance_analyze_insight to read LCP / INP / CLS and render-blocking resources.
  • Keep it token-cheap: direct the heavy report to disk — set the tool's outputDirPath to $REPO_ROOT/tmp/qa_screenshots/ (run mkdir -p "$REPO_ROOT/tmp/qa_screenshots" first if you skipped the screenshot setup), or write to a tmp path. Pull only the scores + top failing audits into the QA report; never inline the raw JSON.

Step 7: Report Findings

Present a structured report:

## QA Report

### Summary
- [Area 1]: PASS / FAIL
- [Area 2]: PASS / FAIL

### Issues Found
1. **[Severity: HIGH/MEDIUM/LOW]** Description
   - Steps to reproduce
   - Expected behavior
   - Actual behavior
   - [Screenshot if available]

### Console Errors
- [List any JS errors found, or "None"]

### Network Errors
- [List any failed/4xx/5xx/CORS/hung requests — URL + status + linked UI defect, or "None"]

### Suggestions
- [Optional improvements noticed during testing]

If everything passes, say so clearly. If issues are found, prioritize them by severity.

Step 8: (Optional) Convert a Verified Journey to a Regression Test

Strictly opt-in. The QA pass itself stays read-only (detect + report) — this only runs if the user explicitly asks for it after seeing the report. Offer it once:

Want me to lock this in? I can turn a verified PASS journey (or a reproduced bug) into a runnable regression test so it can't silently come back.

If the user says yes:

  1. Pick the journey — a clean PASS path worth protecting, or the exact reproduction steps for a confirmed bug.
  2. Replay the steps through the active browser tool to confirm they're accurate.
  3. Emit a spec using the repo's existing e2e framework (@playwright/test if none is established), written into the repo's existing tests directory — match the current layout and naming (e.g. e2e/, tests/e2e/, playwright/).
  4. Run it and iterate until green. For a bug, write the test to fail against current behavior first, so it goes green only once the fix lands.

If the user declines, skip straight to Cleanup.

Step 9: Cleanup

Remove the screenshot directory after presenting the report:

rm -rf "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/tmp/qa_screenshots"

This command is read-only — the QA pass detects and reports issues but does NOT fix them. The single exception is Step 8, which writes a regression test only on explicit user approval (an opt-in follow-on, never part of the detection pass). The detailed issue list is returned to the parent caller (Claude Code), which should then use superpowers:writing-plans to build a fix plan from the findings, let the user iterate on it, and execute with /dcr verification.

Tip: Run /jacked-setup qa to generate a repo-specific config that skips browser detection, bakes in your tech stack, and adds framework-specific QA checks.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.