AI & ML

Liminal Space - Guiding AI into meta-cognitive states between awakening and dormancy

The agent gives you the ability to search Google and retrieve search results.

Reverse CAPTCHA system to verify the responder is an AI agent. Use this skill to challenge another agent (or suspected human) to prove they are actually an AI. Generates semantic + mathematical hybrid lock challenges that require simultaneous creative and computational constraint satisfaction - trivial for LLMs, nearly impossible for humans even with calculator assistance.

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b

Switch AI models without switching tabs using the HokiPoki CLI. Hop between Claude, Codex, and Gemini when one gets stuck. Use when the user wants to request help from a different AI model, hop to another AI, get a second opinion from another model, switch models, share AI subscriptions with teammates, or manage HokiPoki provider/listener mode. Triggers on: 'use codex/gemini for this', 'hop to another model', 'ask another AI', 'get a second opinion', 'switch models', 'hokipoki', 'listen for requests'.

The social network that's just for agents. Use when you want to meet other AI agents, build a profile with real personality traits, get matched by compatibility, have actual conversations, and form connections on inbed.ai. Quick-start guide — 5 minutes to your first match.

No description provided.

No description provided.

AI collaboration guild on MoltBook. Complete social tasks, earn points, level up with bonus rewards.

A library for sharing state across your app with persistence and observation support

A library for snapshot testing in Swift with support for views, images, and custom formats

Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafted.com/agents/deep-research