MLOps
模型部署、评估与运维
root-cause-analysis
melodic-software
Problem solving using Fishbone (Ishikawa) diagrams and 5 Whys technique. Identifies root causes systematically and recommends corrective actions.
current-date
melodic-software
Gets, checks, and verifies the current UTC date and time for unambiguous temporal reference. Use when starting tasks, verifying temporal context, ensuring date awareness before time-sensitive operations, or when incorrect date assumptions are detected.
soul
saadshahd
Use when starting any task, thinking through confidence, verifying work, or asking "what could go wrong". Triggers on every non-trivial request, "how confident", "verify this", "think through".
ask
doodledood
Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.
ask-council
doodledood
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
adk-skill
miticojo
"Build single-agent and multi-agent systems using Google's Agent Development Kit (ADK) in Python, Java, Go, or TypeScript. Use when user says 'build an agent with ADK', 'create a Gemini agent', 'multi-agent pipeline', 'agent orchestration with Google', or mentions ADK, google-adk, google agent development kit, sequential/parallel/loop agents, agent tools, callbacks, state management, agent testing, or agent deployment with Gemini. Do NOT use for LangChain, CrewAI, AutoGen, or non-ADK agent frameworks."
solo-retro
fortunto2
Post-pipeline retrospective — parse logs, score process quality, find waste patterns, suggest skill/script patches. Use after pipeline completes or when user says "retro", "evaluate pipeline", "what went wrong", "pipeline review", "check pipeline logs".
solo-pipeline
fortunto2
Launch automated multi-skill pipeline that chains skills into a loop. Use when user says "run pipeline", "automate research to PRD", "full pipeline", "research and validate", "scaffold to build", "loop until done", or "chain skills". Do NOT use for single skills (use the skill directly).
compress-prompt
doodledood
'Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.'
visionos-design-guidelines
dirnbauer
Apple Human Interface Guidelines for Apple Vision Pro. Use when building spatial computing apps, implementing eye/hand input, or designing immersive experiences. Triggers on tasks involving visionOS, RealityKit, spatial UI, or mixed reality.
golang-concurrency-patterns
bobmatnyc
"Go concurrency patterns for production services: context cancellation, errgroup, worker pools, bounded parallelism, fan-in/fan-out, and common race/deadlock pitfalls"
vvvv-fundamentals
tebjan
Explains vvvv gamma core concepts — data types, frame-based execution model, pins, pads, links, node browser, live compilation (source project vs binary reference workflows), .vl document structure, file types (.vl/.sdsl/.cs/.csproj), ecosystem overview, and AppHost runtime detection. Use when the user asks about vvvv basics, how vvvv works, the live reload model, when to patch vs code, or needs an overview of the visual programming environment.
livekit-agents
livekit
'Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: LiveKit Cloud + LiveKit Inference. REQUIRES writing tests for all implementations.'
replicate
replicate
Discover, compare, and run AI models using Replicate's API
trigger-agents
triggerdotdev
AI agent patterns with Trigger.dev - orchestration, parallelization, routing, evaluator-optimizer, and human-in-the-loop. Use when building LLM-powered tasks that need parallel workers, approval gates, tool calling, or multi-step agent workflows.
iso-42001-ai-governance
mastepanoski
AI governance audit using ISO 42001 standard. Ensures AI systems are developed and deployed responsibly with risk management, ethics, security, transparency, and compliance best practices.
powerbi-semantic-model
RuiRomano
Guide to develop Power BI Semantic Models. Use this skill when asked to connect to a semantic model for analysis or any development operation against a Power BI Semantic Model including (1) Creating new models or Direct Lake models, (2) Creating/editing measures using DAX, (3) Creating/editing tables and relationships, (4) Analyzing model best practices, (5) Deploying models to Fabric workspace, (6) Working with PBIP projects containing semantic models, (7) Troubleshooting DAX performance, (8) Refreshing semantic models in Desktop or Fabric service, (9) Create or edit TMDL code or TMDL files. Do NOT use for report layout/visual authoring (use powerbi-pbir), or workspace/pipeline administration (use fabric-cli).
dspy-4-optimizers
vamseeachanta
'Sub-skill of dspy: 4. Optimizers.'
dspy-optimization-not-improving
vamseeachanta
'Sub-skill of dspy: Optimization Not Improving (+2).'
dspy-example-1-engineering-report-analysis-pipeline
vamseeachanta
'Sub-skill of dspy: Example 1: Engineering Report Analysis Pipeline (+2).'
model-builder
armanzeroeight
Creates dbt models with proper layering (staging, marts), incremental strategies, and documentation. Use when creating dbt models, organizing data transformations, or implementing incremental models.
dspy
vamseeachanta
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
agenta
vamseeachanta
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.
demand-forecasting
kishorkukreja
When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.