623 posts
Create guarded macOS .app and Windows .lnk launchers for DeepSeek Harness and local web apps / 为 DeepSeek Harness 和本地 Web 应用创建桌面快...
A permission-aware Agent Skill for reproducible, auditable batch episode collection across VLA, policy, world-model, and embodied benchmark...
Adversarial multi-agent code review — a committee of specialist reviewers that catches what single-pass AI review misses.
A terminal script manager and launcher — Put any script, prompt, or program in one library; skit turns its inputs and flags into a TUI menu,...
86 agent-executable skill packs converted from RefoundAI’s Lenny skills (unofficial). Works with Codex + Claude Code.
Cognitive Operating System for AI Agent (Skill.md) Self-thinking Multi-agent reasoning Meta-cognition Self-evolution
Growth marketing skills for Claude Code, Cursor, and any AI agent: SEO, CRM, marketing automation, inbox triage, and pre-launch QA. Paste on...
Automated CI/CD setup for GitHub Actions — one command, tests + deploy to AWS, Vercel, or any server.
Claude Code Toolkit — reproducible skills, agents and hooks for Claude Code, with a security-gated catalog, automated upstream updates and v...
Public, versioned Agent Skills to safely bootstrap and sync Claude Code, Codex, Qwen Code, OpenCode, Pi, OpenClaw, and more.
可验证、可回读、可复跑的小红书采集与飞书回填 Agent Skill
Installable Claude Code plugins for AI product evaluation, model routing, guarded loops, and MCP migration decisions.
