MLOps
Operacions d’aprenentatge automàtic
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.
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.
rollback
pmco23
Use to undo a completed build. Reads .pipeline/plan.md to identify which files were created or modified by each task group, presents a checklist for confirmation, removes or restores confirmed files, and resets .pipeline/build.complete. Requires .pipeline/build.complete.
seedance-ark-experience
yinfan-ivan
专门针对 Seedance 2.0 模型的提示词优化助手，帮助用户在火山方舟体验中心生成高质量 AI 视频。提供逐步引导式提示词构建、Seedance 2.0 新特性使用指导、火山方舟操作教学。
m14-mental-model
lywa1998
"Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why does Rust, help me understand, confused about, learning Rust, explain like I'm, ELI5, intuition for, coming from Java, coming from Python, 心智模型, 如何理解所有权, 学习 Rust, Rust 入门, 为什么 Rust"
consult-session-hygiene
simnova
"Running long-lived superagent/peer consult threads without losing them. Token-per-call retirement budget, the no_visible_content fire alarm, why resume pricing is regressive, and the restore-stall signature. Load before resuming any consult thread or when a consult goes quiet."
Data Models & Schema
tachfineamnay
Complete Prisma schema reference with all models, relations, and business logic.
hiring-pipeline-pro
zester4
End-to-end hiring pipeline operations beyond a single role brief: requisition, sourcing, pipeline stages, SLAs, candidate experience, and decision hygiene. Use with onboarding-pro for post-accept settle-in. Does not invent legal terms.
design
pmco23
Use after /brief to transform a brief into a formal design document. Performs first-principles analysis, classifies constraints, grounds all recommendations in live library docs via Context7 and web search, then iterates until alignment. Writes .pipeline/design.md.
reset
pmco23
Use to reset the pipeline to a specific phase. Removes downstream artifacts while preserving upstream ones. Detects current phase, offers reset targets, confirms before deleting. No gate — always available when a pipeline is active.
cohere-best-practices
RSHVR
Production best practices for Cohere AI APIs. Covers model selection, API configuration, error handling, cost optimization, and architectural patterns for chat, RAG, and agentic applications.
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"
torchserve
cuba6112
Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver, inference-api)
google-genai
yharuto0917
"Comprehensive toolkit for working with Google's Gemini API using the Google GenAI SDK. Use when Claude needs to: (1) Generate, summarize, or analyze text using Gemini models, (2) Process images, audio, or video with multimodal capabilities, (3) Extract structured data using function calling or structured outputs, (4) Implement streaming text generation, (5) Build chat applications with context, or (6) Integrate Gemini API into any project. Includes example scripts, API reference, best practices, and detailed guides for multimodal processing and function calling."
eve-fullstack-app-design
Incept5
Architect a full-stack application on Eve Horizon — manifest-driven services, managed databases, build pipelines, deployment strategies, secrets, and observability. Use when designing a new app, planning a migration, or evaluating your architecture.
huggingface-hub
niyatna
"HuggingFace hf CLI: search/download/upload models, datasets."
3d-cv-labeling-2026
slurpyb
Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).
pydantic
ingpdw
Activated when the user wants to create a data model, validate data, serialize JSON, create Pydantic models, add validators, define settings, or create request/response schemas. Covers Pydantic v2 BaseModel, Field, validators, data validation, JSON schema generation, serialization, deserialization, and settings management.
hytopia-camera
Abstrucked
Helps control camera perspectives in HYTOPIA SDK games. Use when users need first-person/third-person views, camera tracking, zoom effects, or cinematic cameras. Covers PlayerCamera, camera modes, offsets, and FOV.
flow-contracts
tweety53
The flow pipeline itself plus its contract definitions — the three states and their transitions, the state file shape, project configuration, Jira integration, follow-up issues, plan provenance, the build-green tag, and workspace isolation. Load the one file you need; each is canonical for its own contract, and a run never loads a rationale appendix. Referenced by the stubs in rules/flow-manual-review.mdc.