MLOps
模型部署、评估与运维
token-optimizer
alexismunoz1
Practical guide to reduce token consumption, lower AI costs, and improve Claude Code performance through file organization, context management, and strategic model selection. Backed by real experiment data. Use when user mentions "optimize tokens", "reduce costs", "Claude is slow", "too many tokens", "token budget", "context window full", "organize codebase for AI", or "reduce token consumption". Do NOT use for general coding questions, debugging, or performance optimization unrelated to AI token usage.
azure-ai-document-intelligence-dotnet
Tryboy869
" "
jackyshen-list-methods
mebusw
This skill should be used when the user asks about "McKinsey frameworks", "MECE principle", "PREP structure", "SCQA framing", "Training from Back of Room", "TfBR", "ORID facilitation", "NLP patterns", "training methodologies", "Huawei BEM/BLM/DSTE system", "facilitation techniques", "liberating structures", "Scrum/Agile", "OKR", or requests guidance on structured problem solving, participant-centered learning, or communication patterns. This skill provides foundational methodologies referenced by other skills.
jackyshen-create-opening-remarks
mebusw
Generate engaging opening speeches, icebreakers, and introductions for workshops, training sessions, or presentations. Use when user asks for "opening remarks", "training opening", "icebreaker speech".
ai-ethics
89jobrien
Responsible AI development and ethical considerations. Use when evaluating
nuxt-models
leeovery
Domain model classes with automatic hydration, relations, and type casting. Use when creating models for API entities, defining relationships between models, casting properties to enums/dates, or creating value objects.
assessment
borisghidaglia
Fitness and nutrition assessment. Activate when users want to evaluate their training or diet, identify gaps, get an initial assessment, or ask "what am I doing wrong?" or "where should I start?"
machine-learning
89jobrien
Machine learning development patterns, model training, evaluation, and
skills
atxinsky
Create detailed implementation plan with bite-sized tasks
skills
atxinsky
"You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation."
jackyshen-create-invitation-email
mebusw
Generate compelling invitation emails for training programs, workshops, or events. Use when user asks to "write class invitation email", "create training invitation", "generate mass email for training", or mentions "course promotion email".
jackyshen-design-quiz
mebusw
Generate quiz questions, assessments, and knowledge checks for training programs. Use when user asks to "create quiz questions", "generate assessment", "make test paper", or similar requests for training evaluations after class.
likec4-architecture
timseriakov
Builds and maintains software architecture as code with LikeC4 DSL. Use when requests mention architecture diagrams, C4 context/container/component views, system landscapes, dependency maps, integration maps, or architecture generated from code. Applies to creating new .c4/.likec4 models, updating existing models, validating with LikeC4 CLI, and preparing preview/build/export outputs.
model-extraction
pluginagentmarketplace
Techniques to extract model weights, architecture, and training data through API queries
testing-methodologies
pluginagentmarketplace
Structured approaches for AI security testing including threat modeling, penetration testing, and red team operations
deepchem
hxk622
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
scvi-tools
hxk622
Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.
arboreto
hxk622
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
geniml
hxk622
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
archive-reprocessing
ilude
Flexible, version-tracked reprocessing system for archive transformations using design patterns (Strategy, Template Method, Observer). Activate when working with tools/scripts/lib/, reprocessing scripts, transform versions, archive transformations, metadata transformers, or incremental processing workflows.
esm
hxk622
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
vertex-ai-sdk
Agentient
Vertex AI SDK patterns for configuring Gemini models including generation parameters, safety settings, streaming responses, and function calling. PROACTIVELY activate for: (1) model configuration and temperature settings, (2) safety controls and streaming implementation, (3) Vertex AI endpoint selection and function calling. Triggers: "gemini config", "model parameters", "streaming response"
ARCS v9 — Claude Code Skill Contract
flashesofbrilliance
v0.4.0 2026-06-05 Observatory + Lattice capabilities: scripts/build_observatory.py (repo-agnostic timeline generator, --attribution show\ hide = strip-to-subject for clean external demos); ADR-023 superionic goal-lattice model + runtime/specs/lattice-pressure-rom.json (L7-governed pressure constants, self-tuning FORBIDDEN); scripts/lattice_sim.py structural load-test harness. Cloud crosswalk noted: /arcs-handoff is local-only — use /handoff skill in cloud; cloud setup reads `_S
agent-orchestration
Agentient
Multi-agent orchestration patterns including coordinator agents, LlmAgent vs WorkflowAgent selection, agent-as-tool pattern, and inter-agent communication via session state. PROACTIVELY activate for: (1) multi-agent systems and agent coordination, (2) sub-agent delegation and agent-as-tool implementation, (3) workflow orchestration with LlmAgent and WorkflowAgent. Triggers: "multi-agent", "orchestration", "agent team"