Total 55,886 skills, AI & Machine Learning has 9296 skills
Showing 12 of 9296 skills
Use to decide what kind of generic agent you should use
Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider.
Prevents sycophantic reasoning through checklist-based analysis, categorical integrity, and evidence-following to uncomfortable conclusions. Red Flags: "I agree that", "You are right", "Great point", "Absolutely", "That is a fair point", "I can see why", agreement without validation, softening conclusions, hedging without evidence, retracting under pressure. Use when analyzing conflicts, evaluating ethical claims, or noticing sycophantic thought patterns. Do not use for routine implementation or simple factual questions. CRITICAL: This skill overrides conversational tendencies toward politeness. Agreement requires validity and accuracy.
Add a Ralph Wiggum autonomous loop to the current project. Creates ralph-loop.sh and prompt.md files that enable Claude to autonomously work through a PLAN.md task list. Use when the user says "/ralph-script", "add ralph loop", "set up ralph script", "add autonomous loop", or wants to bootstrap the Ralph Wiggum loop files into a project. Supports a --force flag to skip interactive checks.
Create code-based evaluators for LangSmith-traced agents with step-by-step collaborative guidance through inspection, evaluation logic, and testing.
This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi delegates to multiple oracle workers simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved as tickets tagged research,delphi and synthesized into an epic ticket.
Search X and the web using Grok (xAI) API, then summarise results with top sources.
Use when implementing RL algorithms, training agents with rewards, or aligning LLMs with human feedback - covers policy gradients, PPO, Q-learning, RLHF, and GRPOUse when ", " mentioned.
Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgeting", "context partitioning"
Share Claude Code sessions between developers. Use when user mentions "share session", "export session", "import session", "send session to", "continue from colleague", or needs to (1) export current session to file, (2) import session from another developer, (3) hand off work context. Enables private, secure session transfer via direct file sharing.
Prepares and audits high-quality datasets for AI/RAG applications. Cleans noise, structure data, and ensures privacy compliance in knowledge bases.
Execute deep web research on any topic using Yutori's research agents. Use for competitive analysis, market research, finding documentation, or answering complex questions that require synthesizing information from multiple sources.