ML Ops
Machine learning operations
oss-investment-scorecard
by kandadavid36
Evaluate whether an open source project / company is investable by a USD-denominated VC fund in the current AI cycle. ALWAYS use this skill when the user asks any of the following: - "evaluate [project] for investment" - "can we invest in [project]" - "score this open source company" - "投资评估 [项目]" - "这个开源项目值得投吗" - "给 [公司] 打分" - Any request to assess, rate, or rank an open source startup's investability - Any comparison of two or more open source companies from an investment perspective The skill produces a structured 5-dimension weighted scorecard (max 10 pts), a pass/recommend/watch verdict, and an IC-ready one-paragraph thesis. It also flags one-vote-veto conditions that cause an immediate Pass regardless of total score.
triplo-ai-expert
by tparrin
Provides comprehensive guidance on installing, configuring, and mastering Triplo AI features (SmartPrompts, Training, Knowledge Bases, Automations, Agents, models, local models, etc.). Triggers whenever user asks how to use, configure, debug, or design workflows in Triplo AI.
jenkins-pipeline-generator
by ehtbanton
Generate Jenkins pipeline files (Jenkinsfile) with declarative or scripted syntax. Triggers on "create jenkinsfile", "generate jenkins pipeline", "jenkins ci config", "jenkins build pipeline".
supabase-environments
by MildTomato
Internal guide for building the Supabase CLI environments system. Covers three-environment model, variable resolution, pull/push workflows, secret handling, branch overrides, and local file conventions. For Supabase internal development - use when implementing the env CLI subsystem or environment variable infrastructure.
Meta-Learning Suite (MAML/FOMAML/Reptile + MAML++ Enhancements)
by sovr610
This skill should be used when the user asks to "implement meta-learning", "add MAML inner loop", "implement FOMAML", "add Reptile", "implement MAML++", "add per-layer per-step learning rates", "implement LSLR", "add multi-step loss", "implement episodic sampling", "add few-shot learning", "implement inner-loop optimizer", "add second-order meta-gradients", "implement torch.func inner loop", "add higher library support", "implement adaptation curves", "add AUAC metrics", "implement meta-checkpoint format", "add derivative-order annealing", "implement episode sampler", "add Omniglot dataset", "add mini-ImageNet splits", "implement Phase 7 runner", "add meta-training loop", "implement fast adaptation", "add batch norm handling for meta-learning", "implement differentiable inner loop", or mentions MAML, FOMAML, Reptile, meta-gradients, episodic few-shot, inner-loop optimization, MAML++ enhancements, or Phase 7 meta-training in the cognitive pipeline.
domain-layer
by Nomik94
Domain Layer 설계 및 구현 가이드. Use when: Entity/Value Object/Aggregate Root 설계, 도메인 이벤트 구현, 비즈니스 로직 배치 판단, Repository Protocol 정의, Domain vs Application Service 구분, 상태 전이 로직, 도메인 예외 설계, 서비스 비대화 해결, 로직 분리. NOT for: 단순 CRUD (비즈니스 규칙 없으면 domain layer 불필요), SQLAlchemy 모델 작성, 단순 dataclass 문법.
miles-rl-training
by majiayu000
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
decision-heuristics
by kangarooking
当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/hesitate/should I
chai1
by BioTender-max
Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.
cohere-java-sdk
by RSHVR
Cohere Java SDK reference for chat, streaming, embeddings, reranking, and tool use. Use when building Java/Kotlin applications with Cohere APIs.
pricing-strategy
by jamelna-apps
When the user mentions "pricing", "price", "monetization", "subscription", "tiers", "freemium", "revenue model", or asks about how to price a product or service.
SKILL: Документирование PuzzleAI
by marozz1k2
документация docs.pxsto.re
deepagent
by htooayelwinict
Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.
Gradient Checkpointing (Activation Recomputation)
by sovr610
This skill should be used when the user asks to "enable gradient checkpointing", "reduce training memory", "activation checkpointing", "torch.utils.checkpoint", "memory-compute tradeoff", "checkpoint sequential layers", "selective checkpointing", "recomputation strategy", "activation memory profiling", "per-layer memory budget", "checkpoint_sequential", "checkpoint_wrapper", "SAC selective activation checkpointing", "SNN timestep checkpoint", "FSDP activation checkpointing", "checkpoint per timestep", "memory-efficient training", "recompute activations in backward", or needs guidance on trading compute for memory during training, per-layer memory profiling, selective recomputation strategies, or integration with distributed training wrappers.
cerebras-api
by diskd-ai
Cerebras API integration for building AI-powered applications with ultra-fast LLM inference. Use when working with Cerebras's Chat Completions API, Python SDK (cerebras_cloud_sdk), TypeScript SDK (@cerebras/cerebras_cloud_sdk), tool use/function calling, structured outputs with JSON schemas, reasoning models with thinking tokens, streaming responses, or any Cerebras API integration task. Triggers on mentions of Cerebras, Cerebras Inference, Llama on Cerebras, Qwen on Cerebras, GLM, or fast LLM inference needs.
fowler
by copyleftdev
Design systems using Martin Fowler's principles of refactoring, continuous integration, and patterns of enterprise application architecture. Emphasizes clean code, evolution over revolution, and writing code for humans first. Use when designing enterprise systems, planning refactors, or establishing engineering culture.
principal-agent
by kangarooking
当用户选择职业/组织/合作方式、困惑「为什么大公司磨洋工/小公司拼命」「该不该自己干」时调用。 核心理念: 委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人; 别让媒体洗脑你需要代理人。 不适用于: 具体薪酬谈判数字、组织架构设计细节。 Triggers: 激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive
hreng-skills
by clous-ai
Use when the user wants to assess engineering team skills, build a skills matrix, identify gaps vs. roadmap, and design training or hiring plans.
plan
by pmco23
Use after /review to transform the approved design into an atomic execution plan. Writes task groups with exact file paths, complete code examples, and named test cases with assertions. Build agents must never need to ask clarifying questions. Writes .pipeline/plan.md.
eval-frameworks
by cuba6112
Evaluation framework patterns for RAG and LLMs, including faithfulness metrics, synthetic dataset generation, and LLM-as-a-judge patterns. Triggers: ragas, deepeval, llm-eval, faithfulness, hallucination-check, synthetic-data.
pipeline-pattern-react
by progmichaelkibenko
Implements the Pipeline design pattern in React 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-style processing in the UI, parsing, formatting pipelines, or any linear transformation flow that runs to completion.
ecostral-optimizer
by wilfred-dore
Optimize any HuggingFace model to minimize energy consumption, CO₂ emissions, and inference cost using real GPU measurements and Mistral Large reasoning. Use this skill when asked to quantize a model, reduce its carbon footprint, benchmark deployment configurations (datacenter GPU, Jetson Orin, edge devices), or generate an optimization report with W&B experiment tracking.
b2b-marketing-playbook
by Gingiris-1031
Complete B2B marketing pipeline combining LinkedIn content, cold email sequences, and webinar funnels. Designed for SaaS founders doing $0–$1M ARR who need predictable lead generation. By @WeiYipei.
mamba-architecture
by majiayu000
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.