41건 · 관련도순
Guide a workshop one question at a time with visible progress and clear answer options. The skill adapts to supplied context, handles interruptions and pauses, and closes with a summary of decisions and actionable choices.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Plan how multiple agents should work together. Choose between dependency-based tasks and repeated work cycles, define ownership and acceptance criteria, identify safe parallel work, and decide how to handle results, interruptions, or revised goals.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Breaks a long-running goal into small, tracked actions and records observable evidence for each success criterion. Checkpoints preserve progress so the agent can resume after interruptions and verify completion against the current work.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Configure fault detection and recovery for distributed training in Megatron Bridge. The skill covers slow GPU detection, automatic restarts, job interruption handling, and checkpoint saving, with configuration examples and guidance for investigating hangs or failed recovery.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Reconstruct where you were and what's next after an interruption, so a broken focus doesn't cost you the whole thread. Use when asked where was I, I got interrupted and lost my place, help me pick back up, or I forgot what I was doing. Produces a quick rebuild of the task's state from what you remember (what you'd done, what you were mid-thought on), the single next action to re-enter it, and a 'breadcrumb' habit for next time — cutting the expensive re-immersion cost that interruptions inflict, especially on ADHD brains.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and interruptions", or wants to check whole-conversation behavior before shipping. Covers text and audio mode and what each catches, running against a local or deployed agent, degraded-audio flags, automating a pre-release run, and triaging failures with list, view and export. For writing the scenarios use writing-livekit-scenarios. Not the default for a bare "test my agent", which goes to debugging-livekit-agents. Use this skill when the user names simulations, scenarios, a run, CI, or shipping.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Protect, design, and measure focused work — block defence, session structure, interruption budgets, and deep-work ratio. Use when the calendar is fragmented, focus blocks keep getting eaten, or output has stalled.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Integrate approved character clips into a game's movement and combat systems, including turn compensation, gait phase, event timing and interruptions. Use after animation authoring or to repair runtime transitions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Builds session-scoped temporary memory palaces for extended conversations. Use when tracking state across interruptions in a multi-step project.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting, or participate in a video conference.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Apply evidence-first engineering discipline to any agent-built software project: fact discovery before action, evidence-calibrated status reporting, explicit change boundaries and stage gates, controlled confirmation for risky or external actions, sensitive-information redaction for anything shared publicly, and resumable continuity after interruptions. Use when users ask an agent to take over an existing codebase, deliver a feature across stages, verify whether work is actually complete, judge release readiness, or keep conclusions honest about what is proven versus assumed. This foundation skill is domain-neutral; vertical suites (for example mini-program engineering) build on it by adding domain facts and platform rules.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design focus modes that actually protect attention: Do Not Disturb schedules, app filtering, notification tiers, and context-specific setups. Use when interruptions fragment your day or 'do not disturb' never stays on.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or non-JobSet application issues.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle, TPU memory, node readiness, multi-host TPU node pool availability, host maintenance or preemption interruptions, and calculating MTTR or MTBI metrics for GKE TPUs. Don't use for general non-TPU GKE workload monitoring or non-metric TPU debugging.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Read-only measurement of an agent's autonomy debt from its approvals log: how many times it asked the human for permission in a window, how many asks expired unanswered, and which classes they fall into (machine noise, login or 2FA, physical UAC, money). Use to find asks the agent should have decided itself and to cut needless interruptions. Triggers: /ask-debt, autonomy debt, how often do I ask, expired asks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.