Audit a live web page in five phases (catalog, click, trace, classify, report) to identify mock data, hardcoded values, LLM-generated metrics, and broken endpoints. Outputs a markdown report with REAL/MOCK/LLM/HARDCODED/BROKEN/UNKNOWN verdicts per visible value.
SkillScore88Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/28/2026
What it changes
Passed 20 of 23 test cases with the skill, and 7 of 23 without it.
Without skill29%
With skill88%
Checks it passed that the model alone missed
Classify order ID ORD-9999 as MOCK.
Classify the revenue metric as UNKNOWN.
Auto-detect the v0 stack from the target URL.
and 18 more in the full report
14 fixed7 passed either way3 still failing0 broke
Pass-rate lift
+58 pp
Tokens
+52%
Agent turns
0%
Response time
-62%
Model gemini-3.6-flashMeasured 8/28/2026v121 of 24 cases passed with skill · 23 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
After navigating to https://analytics.bolt.new/live during Phase 2 cataloging, how long should the browser wait for network idle before taking screenshots and cataloging elements?
What was checked, without and with the skill
Checked
Without skill
With skill
Set the maximum network idle wait time to 10 seconds.
Missed
Passed
case-20 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md128 linessingle file
MockHunter — Live Page Reality Check
Overview
MockHunter is a Claude Code skill that audits a live web page and tells you, for every visible value, whether it is real, mocked, LLM-generated, hardcoded, broken, or unknown. It is built for vibe-coded apps (Lovable, Bolt, v0, Replit, AI Studio, Cursor Composer) where the UI may look complete but the data layer often is not. It uses Playwright MCP to drive a real browser, then traces each visible value through the network and DOM to its source.
This skill adapts the upstream CodeShuX/mockhunter project (community source).
When to Use This Skill
Use when auditing an AI-generated UI to find out which values are actually wired up
Use when reviewing a contractor or teammate's deliverable before sign-off
Use before showing a vibe-coded MVP to a customer or investor
Use when a dashboard "looks too clean" — every metric uniformly round, all timestamps clustered, no variance — and you suspect seeded data
How It Works
Phase 1: Setup & Smart Questions
Greet the user, ask for the target URL
Auto-detect the stack from the URL (*.lovable.app, *.bolt.new, *.v0.app, *.replit.app, aistudio.google.com, otherwise Custom)
Ask 3-5 targeted questions: auth mode (public / localhost / form / skip), DB access (optional), suspicions, page goal
Confirm the audit plan before proceeding
Phase 2: Navigate & Catalog
browser_navigate to the target URL
Handle auth per chosen mode (form-login: fill fields, click submit)
Wait for network idle (max 10s)
Take full-page screenshot, capture accessibility snapshot