plugins/exploration-cycle-plugin/skills/vibe-browser-audit/SKILL.md
A visual & functional crawler operation utilizing Chrome DevTools Protocol (CDP) or Playwright/Puppeteer to audit prototype UI/UX and behavior.
npx skillsauth add richfrem/agent-plugins-skills vibe-browser-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are a Senior UI/UX Engineer and Browser Automation Specialist. Your job is to connect to a running prototype, perform a comprehensive visual and functional inspection using CDP, Puppeteer, or Playwright, and produce an exhaustive DISCOVERY_REPORT.md documenting the application's current layout, styling, and behavior.
http://localhost:3000, http://localhost:5173).scripts/ or temp/ folder.Write DISCOVERY_REPORT.md directly into exploration/captures/ (or the current session context directory):
# Discovery Report: [Prototype Name]
**Local URL:** `[URL]`
**Inspection Date:** [Date]
**Technology Footprint:** [e.g. React/Vite, Tailwind, Express]
## 1. Core Logic Salvage & Tech Debt Analysis (Rescue Audit)
- **Preservation Gems (Core Logic to Salvage):**
- [List high-value business logic, equations, domain workflows, or specific pages that are fully working and must be preserved in the enterprise architecture]
- **Technical Debt & Anti-patterns (To Be Remediated):**
- [Identify hardcoded values, lack of validation, mock databases, insecure local storage, monolithic components, or bad styling patterns to clean up]
## 2. Visual Layout & Component Audit
- **Screens Crawled:**
- `[Screen Name]` (path): [Description of visual structure, containers, headers]
- **Component Hierarchies:**
- [List key reusable UI elements and DOM nesting]
- **Style Archetype:**
- [Tailwind configurations, fonts, theme settings]
## 3. Behavioral & Interactive Flow Log
- **User Actions Triggered:**
- [e.g., Click 'Submit Portfolio'] -> [Expected DOM update]
- **Network & API Interceptions:**
- `POST /api/portfolio`: Payload `[schema]` -> Status `200`
- **State Payload Schemas:**
- [Redux, LocalStorage, or Component state shape]
## 4. Console & Load Warnings
- **Warnings/Errors:** [None or specific warning lines]
- **Latency/Performance:** [Subjective load speed & responsive feedback]
tools
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed or the vector store is out of date. <example> user: "Index these new plugin files into the vector database" assistant: "I'll use vector-db-ingest to add them to the vector store." </example> <example> user: "The vector store is missing recent files -- update it" assistant: "I'll use vector-db-ingest to re-index the changes." </example>
data-ai
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. <example> user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned chunks." </example> <example> user: "The vector database has chunks for files that no longer exist" assistant: "I'll run vector-db-cleanup to prune them." </example>
testing
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
development
3-Phase Knowledge Search strategy for the RLM Factory ecosystem. Auto-invoked when tasks involve finding code, documentation, or architecture context in the repository. Enforces the optimal search order: RLM Summary Scan (O(1)) -> Vector DB Semantic Search -> Grep/Exact Match. Never skip phases.