Loading...
Loading...
Found 1,684 Skills
Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.
Stop LLM slop. A curated system prompt that cuts verbose, corporate-sounding LLM output by 56-71% (measured) while preserving information. Works bilingually (English + Chinese). Installs into your AGENTS.md as an always-on behavior modifier.
Compiles and extracts session knowledge into a living, interconnected LLM-Wiki. Instead of writing isolated logs, it identifies key entities, updates cross-referenced topic files in docs/knowledgelib/, and maintains an index and chronological log. Use this to ensure persistent, compounding project knowledge.
Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization. Use when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers, building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
· Turn notes into structured LLM prompts or improve existing prompts. Triggers: 'write a prompt', 'system prompt', 'prompt template', 'prompt engineering', 'rewrite this prompt'. Not for skills or routines.
Karpathy LLM Wiki 패턴 기반 지식 관리 스킬. 코드 프로젝트와 옵시디언 노트 모두 지원. Raw Source(코드·문서)를 읽어 docs/wiki/에 누적형 지식베이스를 구축·유지한다. "wiki", "위키", "ingest", "인제스트", "wiki 점검", "wiki lint", "wiki 업데이트", "문서화해줘", "아키텍처 설명해줘", "어떻게 동작해?" 키워드로 트리거. qmd 검색 도구와 연동하여 토큰 절약 + 높은 검색 정확도 제공.
Expert guidance for building conversational AI applications with Chainlit framework in Python. Use when (1) creating chat interfaces for LLM applications, (2) building apps with OpenAI, LangChain, LlamaIndex, or Mistral AI, (3) implementing streaming responses, (4) adding UI elements like images, files, charts, (5) handling user file uploads, (6) implementing authentication (OAuth, password), (7) creating multi-step workflows with visible steps, (8) building RAG applications with document upload, or (9) deploying chat apps to web, Slack, Discord, or Teams.
Generative Engine Optimization (GEO) — make content rank in AI search answers from ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Audits existing content, rewrites for AI citation, and produces per-engine strategy. Use when asked to "optimize for AI search", "rank in ChatGPT", "GEO audit", "improve AI citations", "rank in Perplexity", "AI Overview optimization", "AI Overview ranking", "LLM SEO", "answer engine optimization", "AEO", "get cited by AI", "GEO", "generative engine optimization", "show up in ChatGPT", "appear in AI answers", "be cited by Perplexity", "SGE optimization", "Search Generative Experience", or "make my content show up in AI answers". Distinct from regular SEO — this targets generative engines, not traditional Google rankings.
Optimize and structure context for agents and LLMs by reducing noise, prioritizing relevance, organizing memory, defining constraints, and managing token budgets.
Use ARIS (Auto-Research-In-Sleep) for autonomous ML research — idea generation, paper review, experiment automation, and cross-model collaboration with Claude Code, Codex, or any LLM agent.