通过 Pilot Shell 以规范驱动的质量门禁运行 Claude Code

Wrap Claude Code sessions in a spec, approval, and verification workflow before risky implementation work lands.

Prerequisites

Claude Code, curl, bash, macOS/Linux/WSL2

Installation

Requirements and caveats from upstream:
- RED: Write the failing test via an existing public entry point → run, must fail with the documented symptom.
- | Language Servers | Real-time diagnostics for Python (basedpyright), TypeScript (vtsls), Go (gopls). Auto-installed, auto-configured |

Basic usage or getting-started notes:
- ### How real engineers run Claude Code.
- Run pilot for Spec-Driven Development with /spec, or pilot bot for 24/7 automations.
- Verify End-to-End: The primary correctness signal. Run the actual program with the original input (Claude Code Chrome → Chrome DevTools MCP → playwright-cli → agent-browser for UI; CLI / API / REPL / job trigger f...

• Source: https://github.com/1991513ccie-png/skills
• Extracted from upstream docs: https://raw.githubusercontent.com/maxritter/pilot-shell/HEAD/README.md

Documentation

• https://pilot-shell.com/docs