ML Ops
Machine learning operations
domain-layer
by atopile
"Instructions for electronics-specific logic and build processes: netlists, PCBs, build steps, and exporters. Use when implementing or modifying build steps, exporters, PCB generation, or BOM/netlist output."
authentication-flow
by ThibautBaissac
Implements authentication using Rails 8 built-in generator. Use when setting up user authentication, login/logout, session management, password reset flows, or securing controllers.
rails-architecture
by ThibautBaissac
Guides modern Rails 8 code architecture decisions and patterns. Use when deciding where to put code, choosing between patterns (service objects vs concerns vs query objects), designing feature architecture, refactoring for better organization, or when user mentions architecture, code organization, design patterns, or layered design.
animaworks-guide
by xuiltul
Complete reference for animaworks commands and CLI. Covers server operations (start/stop/restart/status/reset), chat and messaging (chat/send/board), Anima management (list/info/create/enable/disable/delete/restart/set-model/set-role/reload/audit), model information (models list/info/show), heartbeat/cron, logs/cost, task management (task add/update/list), config management (config get/set/list), RAG index management (index), asset operations (optimize-assets/remake-assets), animaworks-tool external tool execution, and background task monitoring (check_background_task/list_background_tasks). "command", "usage", "CLI", "animaworks", "start", "stop", "restart", "send", "create Anima", "change role", "change model", "status", "info", "model list", "model info", "logs", "cost", "task", "config", "background task", "task status"
transcribe-tool
by xuiltul
Audio transcription tool. Convert audio files to text using Whisper models. "transcribe" "speech to text" "whisper" "STT" "audio"
subordinate-management
by xuiltul
Process management for subordinate Anima: pause, resume, model change, background model change, restart, task delegation, status confirmation, and auditing. "pause", "stop", "resume", "wake", "disable", "enable", "change model", "background model", "restart", "delegate task", "check subordinate status", "pause", "resume", "process management", "stop subordinate", "dashboard", "audit"
image-gen-tool
by xuiltul
Image and 3D model generation tool. Character fullbody, bustup, chibi, and 3D model generation. NovelAI/Flux/Meshy support. "image generation" "fullbody" "bustup" "chibi" "3D model" "avatar"
nnunet-segmentation
by jaechang-hits
"Train and deploy automated medical image segmentation models using nnU-Net's self-configuring framework that auto-selects optimal architecture, preprocessing, and training for any modality. Supports CT, MRI, microscopy, and ultrasound with 2D, 3D full-res, 3D low-res, and cascade configurations. Pipeline: convert dataset → plan and preprocess → train (5-fold cross-validation) → find best configuration → predict → ensemble. Use when classical segmentation fails and annotated training data is available."
scikit-survival-analysis
by jaechang-hits
"Survival analysis and time-to-event modeling with scikit-survival. Cox proportional hazards (standard/elastic net), Random Survival Forests, Gradient Boosting, SVMs for censored data. C-index (Harrell/Uno), Brier score, time-dependent AUC evaluation. Kaplan-Meier, Nelson-Aalen, competing risks. scikit-learn Pipeline/GridSearchCV compatible. For frequentist regression use statsmodels; for Bayesian survival use pymc; for simpler parametric models use lifelines."
ai-engineer
by tao12345666333
Expert knowledge in AI/ML development, model deployment, and MLOps practices
paper-assembly
by lingzhi227
Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assembling a complete paper from components.
paper-to-code
by lingzhi227
Convert an ML research paper into a complete, runnable code repository. 3-stage pipeline from Paper2Code — Planning (UML + dependency graph) → Analysis (per-file logic) → Coding (dependency-ordered generation). Use for reproducing paper methods.
Oracle
by simota
AI/MLè¨è¨ã»è©ä¾¡ã®å°éã¨ã¼ã¸ã§ã³ããããã³ããã¨ã³ã¸ãã¢ãªã³ã°ãRAGè¨è¨ãLLMã¢ããªã±ã¼ã·ã§ã³ãã¿ã¼ã³ãAIå®å ¨æ§ãè©ä¾¡ãã¬ã¼ã ã¯ã¼ã¯ãMLOpsãã³ã¹ãæé©åãã«ãã¼ã
Aether
by simota
AITuber（AI VTuber）システムの企画から実装・運用までを一貫支援するフルスタック・オーケストレーター。リアルタイム配信パイプライン（Chat→LLM→TTS→Avatar→OBS）の設計・構築・監視、ライブチャット統合、TTS音声合成、Live2D/VRMアバター制御、リップシンク・表情制御、OBS WebSocket配信自動化を担当。
escalation-governance
by athola
'NEVER escalate without investigation first. This is the Iron Law. Use
architecture-paradigm-microkernel
by athola
'Minimal core system with plugin-based feature extensibility for platform
qwen-delegation
by athola
Qwen CLI delegation workflow implementing delegation-core for Alibaba's
architecture-paradigms
by athola
Interactive selector and router for architecture paradigms. Use when
architecture-paradigm-pipeline
by athola
'Consult this skill when designing data pipelines or transformation workflows.
gemini-delegation
by athola
Gemini CLI delegation workflow implementing delegation-core for Google's
Clay
by simota
AI 3Dモデル生成エージェント。Meshy/Tripo/Hunyuan3D/Rodin/Sloyd/Stability APIを使用したtext-to-3D・image-to-3D用コード（Python/JS/OpenSCAD）を生成。ゲームパイプライン統合、LOD、リトポロジー、UV、QC検証を担当。
deseq2-differential-expression
by jaechang-hits
"Differential expression analysis for bulk RNA-seq using R/Bioconductor DESeq2. Negative binomial GLM with empirical Bayes shrinkage, Wald and LRT tests, multi-factor designs, interaction terms, Salmon tximeta import, apeglm LFC shrinkage, MA/volcano/heatmap visualization. The R gold standard for DE analysis with native Bioconductor integration. Use pydeseq2-differential-expression for Python-based pipelines; use edgeR for TMM normalization."
event-modeling
by lexler
Designs systems using Event Modeling.
Cron Manager Skill
by aAAaqwq
Telegram æ¨é: ~/clawd/skills/telegram-push/telegram-push.sh