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.
delta-live-tables
vivekgana
Delta Live Tables (DLT) pipeline patterns and examples for building declarative, self-healing data pipelines with automatic quality enforcement and lineage tracking.
transformation-workflow
hummbl-dev
Practical application guide for HUMMBL's 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes when to use each transformation, combination patterns, analysis templates, output formats, real-world examples, and common pitfalls. Essential for applying mental models effectively in problem-solving and analysis.
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".
codex-cli
rafaelcalleja
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
advanced-evaluation
ken-cavanagh-glean
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
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.
run-gemini
LostAbaddon
向助手发出协助请求，适用于长文阅读理解、网络搜索、网页读取、文章翻译、网页与前端界面制作等任务场景。
ML Monitoring Skill
vivekgana
Lakehouse Monitoring
hummbl-framework
hummbl-dev
Complete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes model selection guidance, application methodology, and validation checklist. Version 1.0-beta definitive reference.
subagent-configuration
rafaelcalleja
This skill should be used when the user asks to "configure a subagent", "create a custom agent", "set up agent tools", "configure permissionMode", "add agent skills", or mentions subagent fields like tools, model, or permissionMode. Provides comprehensive guidance on subagent configuration options and best practices.
context-degradation
ken-cavanagh-glean
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
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.
MLflow Tracking Skill
vivekgana
Databricks MLflow Guide
devops-deployer
ajianaz
Comprehensive DevOps and deployment workflow that orchestrates infrastructure automation, CI/CD pipelines, container orchestration, and cloud deployment. Handles everything from infrastructure as code and pipeline setup to monitoring, scaling, and disaster recovery.
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"
c4-model-architecture-diagrams
Agentient
[STUB - Not implemented] C4 model diagrams for layered architecture visualization (Context, Container, Component, Code). PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]
deepagents-overview
christian-bromann
Understanding Deep Agents framework - what they are, how to create them with createDeepAgent, and the agent harness architecture with built-in middleware for planning, filesystems, and subagents.
flash-attention
tylertitsworth
"Flash Attention, FlashInfer, SDPA backends, PagedAttention, and attention kernel selection/configuration. Use when choosing or configuring attention backends for training or inference (FlashAttention-2/3, FlashInfer, SDPA, xFormers, PagedAttention, Ring Attention, FlexAttention/FlexDecoding, varlen_attn)."
@tank/typescript
tankpkg
"Advanced TypeScript patterns for type-safe applications. Triggers: typescript, TS, type, interface, generic, union, discriminated union, branded type, utility type, conditional type, mapped type, template literal, infer, satisfies, as const, tsconfig, strict mode, type guard, type narrowing, type-safe."