Cursor's create-verification-skill makes agents run your app and film proof
gaganghotra_ · x · 2026-10-07
A shared Cursor official plugin skill, create-verification-skill, generates a project-local verification skill that drives your app like a real user — launching it, exercising features, and capturing screenshots/videos as evidence.
Key points:
- Works for any language/framework and any surface (web UI, CLI, API); output goes to .cursor/skills/verify-<app>/, written for a cold-starting agent, not humans
- Methodology: interview the repo, not the user — infer app surface and run commands from the codebase, ask the user only what can't be observed
- The quoter notes they now primarily review agent work via VM-run videos and screenshots
A directly reusable pattern for making coding agents self-verify changes.
More from coding & agent
- OpenClaw memory already works with self-hosted EmbeddingGemma, but lacks multimodal embeddings — steipete · 2026-10-07
- Blenderbox: open-source multiplexer giving coding agents isolated headless Blender sessions — tobowers · 2026-10-07
- Models aren't the bottleneck: report maps 4 levels of agentic software development — rseroter · 2026-10-07
- Fireworks launches Nexus: smart routing to open models cuts coding AI bills in half with 95%+ cache hits — sophiamyang · 2026-10-07
- YC's Paxel analyzed 3.4M AI coding sessions — and privacy questions follow — AaronBergman18 · 2026-10-07
- EmbeddingGemma can already self-host into OpenClaw memory via Ollama or OpenAI-compatible APIs — osanseviero · 2026-10-07