NodeBenchAI: Skill for Claude Code

.claude/skills/live-qa-dogfood-loop/SKILL.md

live-qa-dogfood-loop is a skill for Claude Code from HomenShum/NodeBenchAI. It costs 17 tokens per session (1,452 once invoked), scanned A, original, MIT.

A user-interface quality-checking loop that takes screenshots of an app's main pages and interactions, sends them to Gemini 3 Pro for review, and records the findings.

In plain words
What is it for?
Capturing eight specified app views, scoring each surface, listing strengths and issues by severity, and saving the results and review history.
Why use it?
It provides repeatable visual checks for layout and interaction problems across desktop and mobile screens.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is HomenShum/NodeBenchAI's own configuration. It tells Claude Code how to work on NodeBenchAI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NodeBenchAI configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/ui/liveQaJudge.mjs --baseURL=http://127.0.0.1:5191.

Reuse

Borrowing it

Nothing to install: this file belongs to HomenShum/NodeBenchAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HomenShum/NodeBenchAI/main/.claude/skills/live-qa-dogfood-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for live-qa-dogfood-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/homenshum/nodebenchai/live-qa-dogfood-loop.svg)](https://agentmods.dev/skills/homenshum/nodebenchai/live-qa-dogfood-loop)
Your own site
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/live-qa-dogfood-loop"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/live-qa-dogfood-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.01452
Opus 5 $0.00009 $0.00726
Sonnet 5 $0.00003 $0.00290
Haiku 4.5 $0.00002 $0.00145

Measured 7d ago against content hash c6b36137c07b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

live-qa-dogfood-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/live-qa-dogfood-loop/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live QA Dogfood Loop

Self-conducting improvement loop that uses Gemini 3 Pro vision to screenshot, judge, fix, and re-judge all 5 app surfaces until top-market quality.

Quick start

# Ensure dev server is running on port 5191
npm run dev

# Run the QA judge (single pass)
GEMINI_API_KEY=$(grep GEMINI_API_KEY .env.local | cut -d= -f2) \
  node scripts/ui/liveQaJudge.mjs --baseURL=http://127.0.0.1:5191

# Results land in .tmp/live-qa-judge/<timestamp>/
# History tracked in .tmp/live-qa-history.json

What the judge evaluates

8 screenshot captures per run:

  1. home/?surface=home (desktop 1440x900)
  2. home-interaction — after clicking first card on home
  3. chat/?surface=chat with a pre-loaded query + lens
  4. reports/?surface=reports
  5. reports-interaction — after clicking first report card
  6. nudges/?surface=nudges
  7. me/?surface=me
  8. mobile-home/?surface=home at 375x812

Each screenshot is sent to Gemini 3 Pro (gemini-3-pro-preview) with a structured prompt requesting:

  • Per-surface score (1-10)
  • Strengths (what works)
  • Issues with severity (P1/P2/P3), category, description, fix, and element

Scoring

Grade S: 95+ (top market quality)
Grade A: 90-94
Grade B: 80-89
Grade C: 70-79
Grade D: 60-69

Self-improvement loop protocol

Phase 1: Run judge, capture baseline

node scripts/ui/liveQaJudge.mjs --baseURL=http://127.0.0.1:5191

Phase 2: Fix P1s first (each P1 = ~6 points)

  • Read .tmp/live-qa-judge/<latest>/gemini-judge-response.json
  • For each P1: trace root cause (not symptom), fix the cause
  • Common P1 patterns:
    • Toast overlap — adjust Sonner position or z-index in src/main.tsx
    • Unreadable text — increase contrast: --rd-ink-faint -> --rd-ink-soft
    • Broken layout — check CSS grid/flex alignment

Phase 3: Fix P2s (each P2 = ~2 points)

  • Low contrast — darken --text-muted / brighten --rd-ink-faint in dark mode
  • Badge urgency — increase border opacity + add subtle glow for act-now badges
  • Mobile viewport — compact or make dismissible promo cards
  • Button states — distinct disabled (opacity 0.35 + grayscale) vs active states

Read the full file on GitHub · 149 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 149 lines · 17 tokens per session scan A c6b36137c07b

Subscribe to this mod's changes

live-qa-dogfood-loop is a skill published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,452 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

screen-reader-testing

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

wshobson/agents · 39 tokens

e2e-testing-patterns

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

wshobson/agents · 51 tokens

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

VoltAgent/voltagent · 52 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

relay-80-100-workflow

Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…

AgentWorkforce/relay · 121 tokens

browser-testing-with-screenshots

Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.

AgentWorkforce/relay · 32 tokens