MLOps
模型部署、评估与运维
geniml
YuukiAS
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
m09-domain
lywa1998
"CRITICAL: Use for domain modeling. Triggers: domain model, DDD, domain-driven design, entity, value object, aggregate, repository pattern, business rules, validation, invariant, 领域模型, 领域驱动设计, 业务规则"
wandb-weave-ft-retrospective
Haruk1y
Analyze W&B, Weave, and local fine-tuning evaluation artifacts, then produce a concrete next-run improvement plan with data, prompt, and training actions. Use after each SFT or eval cycle.
grill-me
TurboSnails
一个用来打磨计划或设计的持续追问式访谈。
coloring-book
bedardandy
Create a personalized printable kids' coloring book (PDF) starring specific children, family members, and pets doing their favorite things — themed pages or a story-mode narrative for ages 3-6. Use when the user asks for a coloring book, coloring pages, or a personalized activity/story book for kids. Triggers on "coloring book", "coloring pages", "make a book for [kid]", "story coloring book".
ai-image-generation
Jackiexiao
"Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image"
pipeline-pattern-nodejs
progmichaelkibenko
Implements the Pipeline design pattern in Node.js for data transformation. Use when the user mentions pipeline pattern, or when you need a fixed sequence of stages that each transform data and pass to the next—ETL, parsing, data processing, or any linear transformation flow that runs to completion.
jupyter-live-kernel
niyatna
"Iterative Python via live Jupyter kernel (hamelnb)."
Event-Driven Pipeline Skill
groupthinking
Zero data loss during failures
Active Inference Agent (Generative Model + EFE + Empowerment)
sovr610
This skill should be used when the user asks to "implement active inference", "add EFE computation", "implement expected free energy", "add empowerment estimation", "implement generative model", "add latent state encoder", "implement transition model", "add preference model", "implement planning rollouts", "add CEM planner", "implement amortized policy", "add pymdp backend", "implement offline RL", "add Minari integration", "implement pragmatic value", "add epistemic value", "implement instrumental value", "add action selection", "implement belief updating", "add world model training", "implement POMDP planning", "add rollout engine", "implement latent imagination", "add horizon normalization", "implement cross-entropy method planning", "add preference learning", "implement variational empowerment", or mentions active inference, expected free energy decomposition, POMDP planning, empowerment estimation, latent imagination, or decision-as-inference in the cognitive pipeline.
mech-interp
Pranav-Karra-3301
Mechanistic interpretability skill for understanding neural network internals. Use when: (1) Working with TransformerLens, nnsight, or SAELens (2) Analyzing attention patterns, circuits, or features (3) Training or analyzing sparse autoencoders (SAEs) (4) Activation patching, logit lens, or direct logit attribution (5) Understanding model internals ("what is this head doing?") (6) Setting up a mech interp research project Triggers: "mech interp", "mechanistic interpretability", "TransformerLens", "SAE", "sparse autoencoder", "activation patching", "logit lens", "circuits", "features", "attention heads", "residual stream", "nnsight", "nnterp", "superposition", "polysemantic", "monosemantic", "ablation", "probing", "induction head"
Compiler & Kernel Fusion (torch.compile) Integration
sovr610
This skill should be used when the user asks to "enable torch.compile", "add compilation to training", "kernel fusion", "TorchDynamo integration", "TorchInductor optimization", "reduce-overhead mode", "max-autotune mode", "fix graph breaks", "compile health check", "shape stabilization", "dynamic shapes for compile", "bucketing for torch.compile", "compile allowlist", "compile blocklist", "compile smoketest", "CUDA graphs for training", "maybe_compile wrapper", "debug recompiles", "TORCH_LOGS compile", "compile + DDP", "compile + FSDP", "torch.compiler.disable", or needs guidance on torch.compile integration, shape management, compilation debugging, or safe fallback patterns.
xiaoyuzhou-podcast-transcriber
nanzhipro
"Downloads Xiaoyuzhou podcasts, transcribes using FunASR, and generates raw, structured, and optimized text files. Invoke when user provides a Xiaoyuzhou episode link."
angular-component-inputs
araujomartin
Modern function-based component inputs and models using Angular Signals API. Trigger: When defining component inputs, when migrating from decorators, when working with reactive component APIs, when implementing two-way binding.
DreamerV3-Style RSSM World Model
sovr610
This skill should be used when the user asks to "implement DreamerV3 RSSM", "build a recurrent state space model", "create Block GRU sequence model", "implement unimix categorical", "add symlog twohot prediction heads", "implement KL balancing loss", "free nats clipping", "world model loss function", "imagination rollout for actor-critic", "straight-through categorical estimator", "implement prior and posterior networks", "DreamerV3 world model", "symlog transform", "twohot encoding 255 bins", "prevent codebook collapse", "DreamerV3 numerical stability", "scale-invariant reward prediction", "world model imagination", "RSSM prior posterior KL divergence", "Block GRU with RMSNorm", "categorical latent state 32x32", or needs guidance on implementing DreamerV3-style world models with the full set of numerical stability techniques (symlog, twohot, unimix, KL balancing).
circleci-config-generator
ehtbanton
Generate CircleCI configuration files with workflows, orbs, and deployment. Triggers on "create circleci config", "generate circleci configuration", "circleci pipeline", "circle ci setup".
V-JEPA 2 Data Pipeline
sovr610
This skill should be used when the user asks to "load video dataset", "implement video transforms", "data augmentation for V-JEPA", "video decoding with decord", "clip sampling", "frame padding", "RandAugment for video", "motion shift augmentation", "random erasing", "video normalization", "YAML config parsing", "dataset registry", "distributed sampler", "weighted sampling", "multi-source dataset", "video DataLoader", "worker seeding", or needs guidance on video data loading, augmentation pipelines, configuration management, or dataset engineering for V-JEPA 2.
tinker-api
dinequickly
Guide for using the Tinker API for LLM training. Use when working with Tinker training workflows, RL environments, supervised fine-tuning, model sampling, rendering, or any Tinker API operations.
sqlalchemy
Nomik94
SQLAlchemy 2.0 async infrastructure pattern reference. Use when: DB model definition, Base model setup, table mapping, relationship config, session management, AsyncSession, sessionmaker, connection pool, query patterns (select, join, subquery, pagination), Mixin (Timestamp, SoftDelete), N+1 prevention (selectinload, joinedload), transaction management, nested transaction, savepoint, generic repository pattern, BaseRepository[ModelType]. NOT for: domain entity design (domain-layer skill), Alembic migrations.
Global Workspace Competition + Broadcast + Working Memory with Ignition Dynamics
sovr610
This skill should be used when the user asks to "implement global workspace", "add workspace competition", "implement ignition dynamics", "add broadcast adapters", "implement working memory", "add CfC/LTC memory", "implement attention competition", "add token staging", "implement slot construction", "add deterministic tie-breaking", "implement iterative rounds", "add convergence detection", "implement ignition gate", "add lock-in prevention", "implement broadcast to temporal", "add broadcast to symbolic", "implement broadcast to decision", "add workspace slots", "implement capacity-limited selection", "add novelty scoring", "implement winner decay", "add slot dropout", "implement ignition cooldown", "add feedback collection", "implement workspace state persistence", "add truncated BPTT support", "implement GRU fallback for workspace", "add workspace telemetry", or mentions global neuronal workspace theory, multi-modal token competition, ignition threshold dynamics, workspace broadcast packets, or CfC/LTC working memory in the cognitive pipeline.
live-workshop
janineagu4049
Set up a JupyterBook-based workshop journal with live audio transcription, keyword extraction, and structured knowledge base. Use when attending lectures, workshops, or meetings that need real-time note-taking and organized output.
movie-maker
LongStories
Docs-first AgentSkill for generating 10-60s mini-movies locally. Provides rules for scripts, shotlists, timing, prompting, providers, rendering (ffmpeg/remotion), and sharing to clawtube.
Auto Orchestrator Skill
smouj
OpenClaw skill: auto-orchestrator
cohere-rerank
RSHVR
Cohere reranking reference for two-stage retrieval, semantic search improvement, and RAG pipelines. Covers Rerank v4 models, structured data reranking, and LangChain integration.