Agent Pr Replay
This tool shows you how Claude Code actually behaves in your codebase. It takes merged human PRs as ground truth, reverse-engineers task prompts, then runs Claude Code on identical scenarios. By comparing differences, it reveals Claude's blind spots so you can train it to better match your coding style.
- Real PRs as ground truth
- Visualized AI behavior
- Auto-generated guidelines
- Reusable skill packaging
- Onboarding new team members faster
- Preventing over-engineering in bug fixes
- Identifying team-specific coding patterns
- Building custom AI coding standards
- Requires GitHub PR history
- Per-PR analysis incurs Claude API costs
openclaw/openclaw
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
f/awesome-chatgpt-prompts
f
Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
Validated by 140k users, used by Harvard professors - turn you into an AI conversation expert in 3 seconds
anthropics/skills
anthropics
Public repository for Agent Skills
Official skill repository ensures quality, ready-to-use solutions for 90% professional needs
upstash/context7
upstash
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Solves the most frustrating problem in AI coding - outdated docs and hallucinated APIs
CherryHQ/cherry-studio
CherryHQ
AI Agent + Coding Agent + 300+ assistants: agentic AI desktop with autonomous coding, intelligent automation, and unified access to frontier LLMs.
Integrates top AI services with document processing and coding features, offering commercial-grade experience for free
affaan-m/everything-claude-code
affaan-m
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
37k stars validate its practical essence, directly improving code quality and development efficiency