Dsh Verify — Testing skill for Claude Code
The quality gate for agent-built web apps.
How to install Dsh Verify
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open 263311487-ux/dsh-verify and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Dsh Verify does
The quality gate for agent-built web apps. Real-browser acceptance checks — CLI, MCP (Claude Code / Cursor / Copilot), GitHub Action. Agents self-test and pass; real browsers tell the truth.
Alternatives in Testing
- OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
- Ext Apps — Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP serve 1.9k ★
- Spectra App — Spec-driven development for coding agents — a desktop app, a CLI, and skills for Codex, Claude Code, Cursor, C 735 ★
README
dsh-verify
[中文](README.zh.md) | English
**Witness** — The browser is the judge. The quality gate for agent-built web apps. Agents say done; the browser proves it. *(Witness is the product name; `dsh-verify` is the package name — same thing.)*
[](https://github.com/263311487-ux/dsh-verify/actions/workflows/ci.yml) [](https://www.npmjs.com/package/dsh-verify) [](https://glama.ai/mcp/servers/263311487-ux/dsh-verify) [](https://github.com/awesome-dsh-plugin/awesome-dsh-plugin) [](https://github.com/263311487-ux/dsh-verify/stargazers) [](https://github.com/263311487-ux/dsh-verify/actions/workflows/self-acceptance.yml)
*If Witness catches something for you, ⭐ [star the repo](https://github.com/263311487-ux/dsh-verify) — it's how this project stays alive.*
**You asked an AI to build a web app. It said "done." Does it actually work?**
`dsh-verify` opens a real browser and checks — so you never have to take the agent's word for it.


The quality gate for **agent-built web apps**. Works with any agent — DeepSeek Harness (dsh), Claude Code, Cursor, Copilot, Codex — and with any CI. You write what a human would check in a browser; a real browser executes it and returns a `PASS`/`FAIL` verdict with receipts (screenshots + diff images).
No LLM judges the outcome. **The browser is the judge.**
![Same task, same AI, two builds — only a real browser te
Related Skills
AI Built App Checklist
24 checks for apps built with Lovable, Bolt, Cursor, Replit, v0, Base44 or Claude Code: leaked keys, open data
Electron Stagewright
Drive Electron apps the way Playwright drives browsers — MCP server for AI agents.
Dsh Agent Bridge
Data-driven agent bridge plugin for DeepSeek Harness: JSON recipes, cross-platform launcher, recipe wizard, se
MVP Builder Skill
Claude Code skill for building production-quality web apps and MVPs from scratch. Full workflow: spec → brandi
Debug Kit
🧩 Agent Skill: drive, inspect & test apps across 9 platforms (macOS/iOS/Android/Web/Electron/Flutter/RN/Tauri
Phased Engineering Pipeline
Claude Code skill for building software with AI agents: seven roles, vertical-slice phases, deterministic chec
Related Agents
Phyll Reviewer
Fresh-eyes UX reviewer for apps built with AI. Walks the app as a first-time end user with Phyll's browser too
Landing Visual Reviewer
Use for the Polish Loop's visual pass (landing-page core), after landing-builder's initial build — screenshots
Soul Introspector
Explores the agent's identity, soul state, and self-knowledge. Use when the user asks "who are you", "tell me