verify

About verify

opslane-verify A verification layer for Claude Code. Reads your spec doc, runs one browser agent per acceptance criterion against your local dev server, and returns pass/fail with screenshots and video — before you push. No CI. No infrastructure. How it works Spec Interpreter — reviews each AC for testability gaps, asks clarifying questions Planner — extracts testable acceptance criteria from the annotated spec Agents — one Claude + Playwright agent per AC, runs against your dev server Judge — reviews screenshots and traces, returns pass/fail per AC Report — prints results; failures include screenshot links and session recordings Installation Prerequisites Claude Code with OAuth login () Playwright MCP Install macOS only: (for ) Usage always asks for your spec upfront, then walks you through any clarifying questions before running. Debugging failur

Quick Facts

Compatible Skills

These tools work well together with verify for enhanced workflows:

• code-sensei — semantic(0.52)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)
• claude-skills — semantic(0.61)+complementary+rare_topics+similar_pop+shared_platform (65%)
• quantum-loop — semantic(0.40)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
• ai-marketing-claude-code-skills — semantic(0.37)+complementary+same_lang+similar_pop+shared_platform (63%)
• odin-claude-plugin — semantic(0.47)+complementary+rare_topics+similar_pop+shared_platform (60%)

More Claude Skill Tools

Explore other popular claude skill tools:

• oh-my-openagent ⭐ 44.5k
• get-shit-done ⭐ 43.3k
• claude-mem ⭐ 42.1k
• awesome-claude-code ⭐ 33.8k
• agents ⭐ 32.5k
• nanoclaw ⭐ 25.8k
• claude-code-templates ⭐ 23.8k
• opcode ⭐ 20.8k
• planning-with-files ⭐ 17.1k
• marketingskills ⭐ 17.1k

Popular TypeScript Agent Tools

• openclaw ⭐ 339.8k · Codex Skill
• n8n ⭐ 181.5k · MCP Server
• dify ⭐ 134.9k · MCP Server
• gemini-cli ⭐ 99.4k · MCP Server
• servers ⭐ 82.4k · AI Tool

Frequently Asked Questions