Total 50,962 skills, AI & Machine Learning has 8536 skills
Showing 12 of 8536 skills
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
어떤 주제/과제든 받아서 스스로 팀을 구성하고 조사·분석·검토·결과도출까지 처리하는 범용 에이전트 팀 오케스트레이터. "팀으로 분석해줘", "에이전트 팀으로 조사해줘", "다각도로 검토해줘", "심층 분석 부탁해", "여러 관점으로 봐줘", "think-team", "think team" 키워드로 트리거. 단순 질문이 아닌 복합적 판단, 조사, 전략 결정이 필요한 모든 상황에서 사용.
Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the Model Context Protocol (MCP) server. Use when the user asks to connect Claude Code to Grafana, set up MCP for Grafana, use Grafana tools in Cursor, query Grafana from an AI agent, configure the Grafana MCP server, or make AI agents interact with Grafana Cloud APIs. Triggers on phrases like "MCP server", "connect Claude Code to Grafana", "Grafana MCP", "AI agent Grafana", "Claude Grafana tools", "Cursor Grafana", or "agent observability".
Memoro platform help — German GDPR-first AI meeting assistant with local device recording, customizable Blueprints, and searchable Memories. Use when setting up Memoro for a team, choosing between Memoro plans (Free/Plus/Pro/Ultra), Memoro transcription quality is poor or wrong language detected, Memoro Blueprints not producing the right output format, Memoro recordings not syncing across devices, comparing Memoro vs Jamie or Granola for bot-free EU-hosted recording, or evaluating GDPR-compliant meeting note-takers hosted in Germany. Do NOT use for reviewing a specific call for coaching (use /sales-call-review) or comparing note-takers broadly (use /sales-note-taker).
Transync AI platform help — real-time AI meeting translation with near-zero latency (<0.5s) dual-screen bilingual display across 60+ languages, AI voice broadcast, AI meeting notes with summaries, custom domain terminology via AI Assistant, system audio sharing (no bot/plugin) for Zoom/Teams/Meet/WhatsApp. Use when setting up Transync AI for multilingual meetings, Transync AI translation accuracy dropping with accents or technical terms, Transync AI dual-screen display not showing translations, Transync AI meeting notes not generating summaries, choosing between Transync AI Personal Premium vs Enterprise plan, Transync AI time card top-up running out mid-meeting, Transync AI voice broadcast not working, or Transync AI vs JotMe or Talo or Langfinity for real-time meeting translation. Do NOT use for general note-taker comparison across all platforms (use /sales-note-taker) or enterprise RSI with human interpreters (use /sales-kudo or /sales-interprefy).
Coconote platform help — Quizlet's AI note-taker that records lectures and auto-generates study guides, flashcards, quizzes, and AI-narrated podcasts from recordings. Use when setting up Coconote for recording lectures and generating study materials, troubleshooting recordings that crash or fail to save on long lectures, figuring out why Coconote requires payment info before accessing the free plan, choosing between Coconote free and Pro subscription tiers, comparing Coconote to Voicenotes or AudioPen or Cleft Notes for voice capture, evaluating Coconote for student lecture note-taking across iOS and Android, or understanding why Coconote only generates one quiz and one flashcard set per note. Do NOT use for comparing AI meeting note-takers for sales teams (use /sales-note-taker) or reviewing a sales call for coaching (use /sales-call-review).
Control macOS applications with Pi agents using semantic Accessibility API targets and optional screenshots
Read production traces, identify what's failing, and build failure taxonomies using open coding and axial coding methodology. Use when debugging agent or pipeline quality, investigating "why are my outputs bad?", or before building any evaluator — error analysis must come first. Do NOT use when you already have identified failure modes and need evaluators (use build-evaluator) or datasets (use generate-synthetic-dataset).
One-shot autopilot orchestrator — runs the full spark-video pipeline (screenwriter ↔ director per-scene parallel → render chain-DAG parallel + per-clip review → stitch). User confirms at 4 gates (+ 1 mode gate at start + 1 BGM gate when bgm/ folder detected). Use when the user wants "make me an episode" in one command.
Use when the user asks "what can Cekura do", "what commands are available", "help me with Cekura", "what skills do I have", "show me Cekura features", "what's available", "how do I use Cekura", or needs guidance on which Cekura skill to use for their task. Also relevant as the entry point when a user has just installed cekura-skills for the first time.
Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for real-time alerts or ad-hoc Q&A.