MLOps

aidr

pc-style

Offload context-heavy but low-complexity codebase work to Aider through a thin CLI wrapper. Use when another AI agent should avoid loading large repository context for tasks like discovery, repetitive refactors, cross-file version bumps, and broad search/explain passes. Supports safe read-only scanning, scoped edit runs, model-mode routing, and setup/model diagnostics.

prompt-engineer

pateljig4545

Transform rough prompts/ideas into production-ready LLM prompts. Use when crafting, refining, or optimizing prompts for any AI model (Claude, GPT, Llama, etc.) with advanced techniques like CoT, constitutional AI, RAG optimization.

reading-metaskill

kangarooking

当用户想养成阅读习惯、问「读什么书/怎么读」「如何学习新领域/怎么入门某学科」时调用。 核心理念: 阅读是终极元技能; 读你所爱直到爱上阅读, 没有读完义务; 读原著与经典优先; 以教促学; 每天1-2小时即可进入极少数人行列。 不适用于: 具体某本书的书评、考试备考资料选择。 Triggers: 阅读/读书/怎么学习/入门/原著/书单/reading/how to learn

oatda-generate-video

devcsde

Use when the user wants to generate videos using AI models through OATDA's unified API. Supports MiniMax, Google Veo, Alibaba Wan, ZAI, and OpenAI Sora. Video generation is asynchronous.

pytorch-training

congmnguyen

PyTorch model-building conventions and a neural-net training debug checklist. Use this skill whenever writing or reviewing PyTorch code that defines a model (nn.Linear, nn.Conv2d, BatchNorm) or trains one (training loop, optimizer, LR schedule), and ESPECIALLY when debugging training problems — loss not converging, loss stuck or flat, suspiciously slow learning, "hockey stick" loss curves, or a model that seems to ignore its inputs. Also consult it before starting any from-scratch training run, even if the user doesn't mention debugging.

capa-officer

nimeshgurung

Senior CAPA Officer specialist for managing Corrective and Preventive Actions within Quality Management Systems. Provides CAPA process management, root cause analysis, effectiveness verification, and continuous improvement coordination. Use for CAPA investigations, corrective action planning, preventive action implementation, and CAPA system optimization.

SKILL.md — task-router

manthis

```

senior-data-scientist

nimeshgurung

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

local-ai-agents

microsoft

dbs-diagnosis

Pluviobyte

dontbesilent 商业模式诊断。两种模式：问诊（消解你的问题）和体检（拆解你的商业模式）。 触发方式：/dbs-diagnosis、/问诊、「帮我看看商业模式」「诊断一下我的业务」「我有个商业问题」 Business model diagnosis using dontbesilent's ontological framework. Two modes: consultation (dissolve your question) and checkup (analyze your business model). Trigger: /dbs-diagnosis, "diagnose my business model", "I have a business question"

streams-mcp-tools

jwongmongodb

Build, operate, and debug Atlas Stream Processing through the MongoDB MCP Server. Use when user says "set up a Kafka pipeline", "deploy a stream processor", "add a connection to my workspace", "why is my processor failing", "stop my processor", "delete my workspace", "show me my Streams workspaces", or any task involving Atlas Stream Processing workspaces, connections, or processors. Do NOT use for general MongoDB queries, Atlas cluster management, or non-Streams Atlas operations.

ai-news-radar

HUANGYming

Summarize current AI news by searching for recent developments across model releases, product launches, research, regulation, funding, and major industry moves. Use when the user wants a concise snapshot of what is happening in AI right now.

token-cost

EvilFreelancer

Use when the user invokes /token-cost or asks for the floor / bedrock / self-cost / "real" price of LLM tokens on a self-hosted server — the physical lower bound from electricity plus hardware amortization, NOT the market API price. The skill measures power draw and generation speed ON the server (nvidia-smi, streaming benchmark) and asks for electricity tariff, hardware cost and amortization period, then prints cost per 1M input/output tokens. Triggers: "сколько на самом деле стоит токен", "цена самохоста", capacity and break-even planning.

openclaw-groq-orpheus-tts

ahmedeid5

Fast and FREE Arabic (Saudi) & English AI voices. Generous 100 requests per day via Groq API. Professional, high-quality generative TTS using Orpheus models.

Inference Optimization

sovr610

This skill should be used when the user asks to "optimize inference", "speed up predictions", "add caching", "batch inference", "async inference", "reduce inference latency", "profile inference", "memory efficient inference", "inference pipeline", "warm up model", "KV cache", "inference throughput", "latency benchmark", "optimize forward pass", or needs guidance on inference performance optimization, caching strategies, batch processing, async execution, or latency profiling for the brain_ai system.

Sleep Consolidation Cycle (Offline Replay + Synaptic Homeostasis + Systems Consolidation)

sovr610

This skill should be used when the user asks to "add sleep cycle", "memory consolidation", "offline replay", "synaptic homeostasis", "sleep-wake cycle", "memory replay consolidation", "sharp wave ripple replay", "slow wave sleep computation", "dream-like generative replay", "synaptic downscaling", "interleaved replay", "systems consolidation", "hippocampal-cortical transfer", "offline training phase", "implement sleep consolidator", "add NREM replay phase", "add REM generative phase", "implement experience replay scheduler", "add weight downscaling", "implement complementary learning systems", "add fast-to-slow transfer", "implement two-phase training", "add sleep phase to training orchestrator", "implement priority replay sampling", "add compressed replay", "implement dream replay from world model", "add pseudo-rehearsal", "implement capacity restoration", "add synaptic renormalization", or mentions sleep consolidation, offline consolidation phase, NREM structured replay, REM creative recombination, sharp-wave ripple compressed replay, synaptic homeostasis hypothesis, Tononi-Cirelli downscaling, complementary learning systems, hippocampal-cortical transfer, fast-to-slow knowledge distillation, dream-like generative replay, pseudo-experience generation, two-phase wake-sleep training, replay priority sampling, capacity restoration, or sleep-wake integration with training orchestrator in the cognitive pipeline.

database-migrations

Dsantiagomj

Database schema migrations and change management. Covers Prisma migrations, schema versioning, rollback strategies, and safe production deployments. Trigger: When creating database migrations, when modifying schemas, when deploying database changes, when handling rollbacks.

veo-video-gen

cgk-platform

Generate videos with Veo 3.1 (Google), Kling 3.0 (Kuaishou), or Sora 2 (OpenAI). Supports text-to-video AND image-to-video with customizable duration, aspect ratio, resolution, person generation, and multi-video batch output. Video extension/continuation up to ~3 minutes. Automatically uploads to Slack.

codex-subagent

yuanxiao0115

Spawn Codex subagents via background shell to offload context-heavy work. Use for: deep research (3+ searches), codebase exploration (8+ files), multi-step workflows, exploratory tasks, long-running operations, documentation generation, or any other task where the intermediate steps will use large numbers of tokens.

reading-metaskill

kangarooking

当用户想养成阅读习惯、问「读什么书/怎么读」「如何学习新领域/怎么入门某学科」时调用。 核心理念: 阅读是终极元技能; 读你所爱直到爱上阅读, 没有读完义务; 读原著与经典优先; 以教促学; 每天1-2小时即可进入极少数人行列。 不适用于: 具体某本书的书评、考试备考资料选择。 Triggers: 阅读/读书/怎么学习/入门/原著/书单/reading/how to learn

regulatory-affairs-head

nimeshgurung

Senior Regulatory Affairs Manager expertise for HealthTech and MedTech companies. Provides strategic regulatory guidance, submission management, regulatory pathway analysis, global compliance coordination, and cross-functional team leadership. Use for regulatory strategy development, submission planning, regulatory risk assessment, and team coordination activities.

screenshot

naohainezha

Take screenshots of the screen using macOS screencapture. Use when users ask to see the screen, debug UI, or capture what's displayed. Resize before returning to avoid blowing up model context.

eve-agentic-app-design

Incept5

Layer agentic capabilities onto a full-stack Eve app — agents, teams, multi-model inference, memory, events, chat, and coordination. Use when designing an app where agents are primary actors, not afterthoughts.

piping-design

boudjadayoucef-sketch

Skill for developing industrial piping software in Python, including piping components, 3D routing, isometric drawings, P&ID data, CAD/BIM interoperability, MTO/BOM and QA/QC.