Loading...
Loading...
Found 1,282 Skills
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
DeepSeek AI large language model API via curl. Use this skill for chat completions, reasoning, and code generation with OpenAI-compatible endpoints.
Think carefully no matter what question you answer. Before answering any question or performing any task, conduct in-depth analysis and reasoning first.
Shell out to OpenAI Codex CLI for headless code generation, analysis, and question-answering. Optimized for code tasks. Requires OPENAI_API_KEY env var.
Build Model Context Protocol servers and implementations. Creates protocol-compliant tools and integrations for AI-powered applications.
Active knowledge intelligence. Runs Mine → Grow → Defrag cycle. Mine extracts signal from git/.agents/code. Grow validates existing learnings against current reality, synthesizes cross-domain insights, traces provenance chains, and identifies knowledge gaps. Defrag cleans up. Triggers: "athena", "knowledge cycle", "mine and grow", "knowledge defrag", "clean flywheel", "grow knowledge".
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
Generate deep links to traces, spans, and sessions in the Arize UI. Use when the user wants a clickable URL to open a specific trace, span, or session.
Expert guidance for LangChain and LangGraph development with Python, covering chain composition, agents, memory, and RAG implementations.
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
Token optimization best practices for MCP server and tool interactions. Minimizes token consumption while maintaining effectiveness. USE WHEN: user mentions "token usage", "optimize tokens", "reduce API calls", "MCP efficiency", asks about "how to use less tokens", "MCP best practices", "limit output size", "efficient queries" DO NOT USE FOR: Code optimization - use `performance` instead, Text compression - this is about API usage patterns, Cost optimization (infrastructure) - use cloud/DevOps skills