MLOps
模型部署、评估与运维
angular-forms
Kobolden
Build signal-based forms in Angular v21+ using the new Signal Forms API. Use for form creation with automatic two-way binding, schema-based validation, field state management, and dynamic forms. Triggers on form implementation, adding validation, creating multi-step forms, or building forms with conditional fields. Signal Forms are experimental but recommended for new Angular projects.
data-science-interactive-apps
legout
"Interactive web apps for data science: Streamlit, Panel, and Gradio. Use for prototyping ML models, creating data exploration dashboards, and sharing insights with non-technical stakeholders."
immutable-model-updates
shimo4228
"Use when designing Swift model structs that need predictable, thread-safe state updates without mutation."
llm-caching
RSHVR
Optimize LLM costs and latency through KV caching and prompt caching. Use when (1) structuring prompts for cache hits, (2) configuring API cache_control for Anthropic/Cohere/OpenAI/Gemini, (3) setting up self-hosted inference with vLLM/SGLang/Ollama, (4) building agentic workflows with prefix reuse, (5) designing batch processing pipelines, or (6) understanding cache pricing and tradeoffs.
data-engineering-ai-ml
legout
"AI/ML data pipelines: embedding generation, vector databases, RAG patterns, LLM monitoring, and batch inference workflows."
data-architecture
pluginagentmarketplace
Design data architectures with modeling, pipelines, and governance
leap-edge-sdk
glody007
Liquid AI LEAP Edge SDK for on-device AI inference on Android and iOS. This skill should be used when building mobile apps with local LLM capabilities, implementing chat interfaces with streaming responses, or deploying small language models to edge devices. Triggers on tasks involving LeapSDK, LeapClient, ModelRunner, on-device inference, or mobile AI integration.
gemini
iamladi
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
ai-product-advisor
elliottrjacobs
Advise on building AI-powered products — architecture, evals, UX, pricing, and go-to-market. Use when the user says "AI product", "building with AI", "AI strategy", "evals", "AI UX", "LLM product", "AI architecture", or needs guidance on incorporating AI into a product.
cc-context-fork
choru-k
Fork the current session and run a prompt with a different model. Full conversation context preserved. Use for "fork with haiku", "cheap query", "context fork", "delegate to haiku", "run with haiku", "fork with opus", or when you want a different model for a sub-task.
image-generation
Xiangyu-CAS
Gemini image generation and editing skill for text-to-image, image-to-image edits, multi-reference composition, and Google Search grounding. Use when creating or modifying images via Gemini (default model gemini-3-pro-image-preview) with the Python SDK.
converting-epub-images
sumik5
Converts image-based EPUB files to Japanese text via LM Studio OCR. Use when user has an EPUB composed of scanned page images and wants plain text output. For skill creation from EPUB, use authoring-skills instead.
designing-training
sumik5
Training program design and facilitation methodology covering needs analysis (participant analysis, stakeholder mapping), KSA framework, instructional design theory (ADDIE, TOTE, Gagné, mastery learning), objective setting, activity catalog, training operations (instructor, space, logistics), brain science principles (7±2 rule, long-term memory, habit formation), learner-centered facilitation (90/20/8 rule, EAT), online/hybrid delivery, skill map creation, and training material development. Use when designing training programs, facilitating workshops, creating training materials, building skill maps, or managing training operations. For behavior design→applying-behavior-design. For presentation content→improving-presentations. For design thinking process methodology (empathize/define/ideate/prototype/test)→practicing-design-thinking.
aegis-router
disi3r
"AEGIS — Neural Routing Engine for OpenClaw Agent Swarms. Dynamically routes prompts to optimal model tiers using 15-dimensional analysis."
codex
iamladi
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.3-Codex by default for state-of-the-art software engineering.
video-generation
Xiangyu-CAS
Gemini video generation with Veo 3.1 via the Python SDK. Use when generating videos from text or images, using reference images, first/last frame interpolation, or video extension, and when tuning Veo parameters (aspect ratio, resolution, duration, negative prompts, personGeneration, seed).
creating-flashcards
sumik5
Creates Anki flashcards from EPUB/PDF files by converting to markdown, auto-detecting content structure, and batch-importing via Anki MCP. Use when converting textbooks, question banks, or study materials into spaced repetition flashcards. For Anki MCP setup and direct card management, use using-anki-mcp instead.
gtm-strategist
elliottrjacobs
Build go-to-market plans including channel strategy, launch sequencing, and growth model. Use when the user says "go to market", "GTM plan", "launch strategy", "growth strategy", "how do we get customers", "distribution strategy", or needs to plan how a product reaches its market.
agent-tools
Jackiexiao
"Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok"
sam3
jakerains
Create and work with Meta SAM 3 (facebookresearch/sam3) for open-vocabulary image and video segmentation with text, point, box, and mask prompts. Use when setting up SAM3 environments, requesting Hugging Face checkpoint access, generating inference scripts, integrating SAM3 into Python apps, fine-tuning with sam3/train configs, running SA-Co or custom evaluations, or debugging CUDA/checkpoint/prompt pipeline issues.
fundamentals
pluginagentmarketplace
TypeScript type system fundamentals and basic typing patterns
applying-reasoning
Git-Fg
"Applies structured mental models to solve complex problems. Use when solving architectural decisions, root cause analysis, or strategic planning."
applying-behavior-design
sumik5
Behavioral design methodology for products that change user behavior using CREATE Action Funnel (Cue, Reaction, Evaluation, Ability, Timing) and three strategies (cheat, habit, conscious action). Use when designing product features that aim to change user habits, increase engagement, or guide users toward beneficial actions. For visual UI/UX design principles, use applying-design-guidelines instead. For training program design and facilitation methodology, use designing-training instead. For human-centered design thinking process (user research, ideation, prototyping), use practicing-design-thinking instead.
slurm
SerendipityOneInc
Submit, manage, and monitor GPU workloads on SRP's Slurm clusters with Apptainer containers