Percy Visual Testing Agent — Testing skill for Claude Code
[Beta] Visual testing on autopilot for AI coding agents — Claude Code, Cursor, Codex, GitHub Copilot & more.
How to install Percy Visual Testing Agent
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open percy/percy-visual-testing-agent and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Percy Visual Testing Agent does
[Beta] Visual testing on autopilot for AI coding agents — Claude Code, Cursor, Codex, GitHub Copilot & more. Captures visual intent, watches Percy builds, reviews every diff against intent + code, and gates merges.
Alternatives in Testing
- Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★
- Spec Driven Develop — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub 975 ★
- Spectra App — Spec-driven development for coding agents — a desktop app, a CLI, and skills for Codex, Claude Code, Cursor, C 735 ★
README
Percy Visual Testing — Plugin for AI Coding Agents
Visual review loop for agentic UI development. Works in Claude Code, Cursor, Codex, Antigravity, GitHub Copilot, and any AI IDE that reads `AGENTS.md`.
⚠️ **Beta** — this plugin is in beta. Capabilities, commands, and behavior may change; feedback welcome via GitHub issues.
When an agent changes UI code, this plugin makes sure a Percy build runs, the diffs are checked against the agent's stated intent, and the change is rejected + iterated on if real bugs are found — all without leaving the editor.
Install
**Claude Code**
/plugin marketplace add percy/percy-visual-testing-agent
/plugin install percy-visual-testing
**Cursor · Codex · Antigravity · Gemini (Code Assist agent mode or CLI)** — any IDE that reads `AGENTS.md` (all major agents do). One command, run in your repo:
curl -fsSL https://raw.githubusercontent.com/percy/percy-visual-testing-agent/main/install.sh | bash
**GitHub Copilot** — same command with `--copilot` (adds the `/percy-*` slash commands to Copilot Chat):
curl -fsSL https://raw.githubusercontent.com/percy/percy-visual-testing-agent/main/install.sh | bash -s -- --copilot
**QA / regression-suite repo** (your automation suite lives in its own repo and you triage scheduled runs) — add `--qa` (combine with `--copilot` if you use Copilot):
curl -fsSL https://raw.githubusercontent.com/percy/percy-visual-testing-agent/main/install.sh | bash -s -- --copilot --qa
The installer only touches your repo: skills → `.percy/skills/`, a short section appended to your `AGENTS.md`, a one-line `GEMINI.md` pointer (created or appended — Gemini reads `GEMINI.md` by default, not `AGENTS.md`), and (with `--copilot`) prompts → `.github/prompts/`. Prefer manual? Copy those files from this repo — that's all it does.
Outside Claude Code/Copilot (Cursor, Codex, Antigravity, Gemini Code Assist agent mode in VS Code, Gemini CLI — any `AGENTS.md` IDE) there a
Related Skills
Traceframe
Animated architecture and system-flow diagrams for AI coding agents. A Claude Code, Codex, Cursor and Copilot
Agentic Doc Templates
Stop coding agents from losing intent or building the wrong product shape. Modular Understanding/spec/TODO doc
Archcore
Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by
Spectoflow
Agent-agnostic spec-driven development framework with a real-time local dashboard — works with Claude Code, Gi
Robotics Agent Skills
Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patte
Vindicate
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP
Related Agents
Developer Overview
code-container (container) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode
Pocketpal Design Parity Reviewer
Reviews a Figma-faithful implementation against the canonical design. Verifies committed visual-diff captures,
Agentic Auditor
PYA specialist spawned by the /pya orchestrator. Audits AI agent and LLM surfaces in an untrusted repository: