Skillget

opslane

skill
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 107 GitHub stars
Code Gecti
  • Code scan — Scanned 3 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This skill acts as a verification layer for Claude Code. It parses your project's specification, runs a browser agent against your local development server to test each acceptance criterion, and generates pass/fail results with screenshots before you push your code.

Security Assessment
The tool requires access to your local development server and relies on Playwright MCP to interact with it via an automated browser. It reads local project files to generate its configuration and writes results directly to your local filesystem. No dangerous permissions were requested, no hardcoded secrets were found, and a static code scan of its shell scripts revealed no malicious patterns. Because it launches an automated browser that navigates your local app, it handles active execution, but its scope is strictly contained to your local environment. Overall risk: Low.

Quality Assessment
The project is actively maintained, with repository activity as recent as today. It is released under the standard MIT license and has garnered over 100 stars, indicating a solid level of community trust and peer interest. The repository is well-documented with clear instructions and a defined architecture.

Verdict
Safe to use.
SUMMARY

Verification Layer for Claude Code

README.md

Verify

A verification layer for Claude Code. Reads your spec, runs a browser agent against your local dev server for each acceptance criterion, and returns pass/fail with screenshots — before you push. No CI. No infrastructure.

Install

Prerequisites

  • Claude Code with OAuth login (claude login)
  • Playwright MCP configured (see below)

Usage

Claude Code Skills

# One-time setup — auto-detects dev server, indexes app
/verify-setup

# Run verification against a spec
/verify

/verify-setup auto-detects your dev server port, indexes routes and selectors from your codebase, and writes .verify/config.json + .verify/app.json. No npm install needed.

/verify asks for your spec, reviews it for ambiguities, then verifies each acceptance criterion using Playwright MCP. Results appear inline with screenshots.

Playwright MCP Setup

claude mcp add playwright -- npx @playwright/mcp@latest --storage-state .verify/auth.json --isolated

Restart Claude Code after adding the MCP server.

Debugging failures

After a run, evidence lives in .verify/runs/<run_id>/:

# Browse raw evidence for a specific AC
ls .verify/runs/*/evidence/<ac_id>/

Each AC's evidence directory contains:

  • result.json — verdict, confidence, reasoning, steps taken
  • *.png — screenshots captured during execution

Architecture

/verify runs as a Claude Code skill using Playwright MCP for browser interaction:

  1. Spec Interpreter — reviews acceptance criteria for ambiguities, asks clarifying questions
  2. AC Extractor — parses the spec into concrete, testable acceptance criteria using seed data and known routes
  3. Browser Verification — navigates the app via Playwright MCP, checks each AC, collects screenshots
  4. Report — writes per-AC result.json and a combined verdicts.json

Dev setup

See CLAUDE.md for full dev commands, conventions, and test instructions.

Yorumlar (0)

Sonuc bulunamadi