MLOps
模型部署、评估与运维
growth-modeling
SkeneTechnologies
When the user wants to build quantitative growth models -- including loop-based models, sensitivity analysis, revenue forecasting, or unit economics. Also use when the user says "growth forecast," "revenue model," "CAC LTV," "growth projections," or "financial model." For growth loops, see growth-loops. For PLG metrics, see plg-metrics.
plg-strategy
SkeneTechnologies
When the user wants to assess PLG readiness, design a product-led growth strategy, choose between freemium and free trial, evaluate PLG maturity, or plan a hybrid PLG + sales model. Also use when the user says "should we do PLG," "PLG vs sales-led," "growth motions," "PLG audit," or "go-to-market strategy." For specific mental models, see plg-mental-models. For growth loop design, see growth-loops.
plg-mental-models
SkeneTechnologies
When the user needs mental models or frameworks for PLG decisions -- including product-channel fit, time-to-value, network effects, habit loops, or pricing psychology. Also use when the user asks "what framework should I use," "how should I think about this," or references a specific model like "adjacent user theory" or "bowling alley framework." For comprehensive PLG strategy, see plg-strategy. For growth loops, see growth-loops.
usage-based-pricing
SkeneTechnologies
When the user wants to design or implement usage-based, consumption, or metered pricing -- including credit systems, overage handling, or billing infrastructure. Also use when the user says "pay per use," "metered billing," "credit system," "usage pricing," or "consumption pricing." For broader pricing strategy, see pricing-strategy. For expansion, see expansion-revenue.
ml-adoption-playbook
SeuPut0705
End-to-end methodology for AI agents and software engineers to add machine learning algorithms to existing non-ML codebases. Covers problem framing, data readiness, architectural decoupling, and baseline model integration. Use when adding a machine learning capability to a codebase that has none, from problem framing through a baseline model.
product-led-sales
SkeneTechnologies
When the user wants to layer sales onto a PLG motion, build PQL scoring, design sales handoffs from product usage signals, or plan a hybrid PLG + sales model. Also use when the user says "product-led sales," "PQL," "PQA," "when to add sales to PLG," or "enterprise PLG." For broader PLG strategy, see plg-strategy. For expansion revenue, see expansion-revenue.
tinybird-typescript-sdk-guidelines
tinybirdco
Tinybird TypeScript SDK for defining datasources, pipes, and queries with full type inference. Use when working with @tinybirdco/sdk, TypeScript Tinybird projects, or type-safe data ingestion and queries.
frontend-design
b1rdmania
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
mle-workflow
SeuPut0705
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
model-evaluation-benchmark
rysweet
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
scanpy
tondevrel
Scalable toolkit for analyzing single-cell gene expression data. Built on top of Anndata, focusing on clustering, trajectory inference, and visualization.
pytorch-deployment
tondevrel
Advanced sub-skill for PyTorch focused on model productionization and deployment. Covers TorchScript (JIT/Tracing), ONNX export, LibTorch (C++ API), and inference optimization (Quantization, Pruning).
pytorch-research
tondevrel
Advanced sub-skill for PyTorch focused on deep research and production engineering. Covers custom Autograd functions, module hooks, advanced initialization, Distributed Data Parallel (DDP), and performance profiling.
photutils
tondevrel
An Astropy coordinated package for detecting and performing photometry of astronomical sources. Provides tools for background estimation, source detection (DAOFIND, IRAF), aperture photometry, and PSF (Point Spread Function) fitting. Use when working with astronomical image analysis, star/galaxy detection, measuring brightness (photometry), background subtraction, PSF fitting, aperture photometry, centroiding, or isophotal analysis.
cobrapy
tondevrel
Constraints-Based Reconstruction and Analysis for Python. Used for modeling large-scale metabolic networks in microorganisms.
pyomo
tondevrel
Python Optimization Modeling Objects. A high-level framework for formulating, solving, and analyzing optimization models. Supports Linear Programming (LP), Mixed-Integer Linear Programming (MILP), and Non-Linear Programming (NLP). Part of the COIN-OR project. Use for mathematical optimization, linear programming, mixed-integer programming, non-linear programming, strategic planning, process engineering, energy systems, supply chain optimization, stochastic programming, and solver integration with IPOPT, SCIP, Gurobi, CPLEX, or GLPK.
fastapi-streamlit
tondevrel
Dual skill for deploying scientific models. FastAPI provides a high-performance, asynchronous web framework for building APIs with automatic documentation. Streamlit enables rapid creation of interactive data applications and dashboards directly from Python scripts. Load when working with web APIs, model serving, REST endpoints, interactive dashboards, data visualization UIs, scientific app deployment, async web frameworks, Pydantic validation, uvicorn, or building production-ready scientific tools.
pytorch
tondevrel
Leading deep learning framework. Provides Tensors and Dynamic Computational Graphs with strong GPU acceleration. Widely used for research, neural networks, and differentiable programming.
powerbi-semantic-model
RuiRomano
Guide to develop Power BI Semantic Models. Use this skill when asked to connect to a semantic model for analysis or any development operation against a Power BI Semantic Model including (1) Creating new models or Direct Lake models, (2) Creating/editing measures using DAX, (3) Creating/editing tables and relationships, (4) Analyzing model best practices, (5) Deploying models to Fabric workspace, (6) Working with PBIP projects containing semantic models, (7) Troubleshooting DAX performance, (8) Refreshing semantic models in Desktop or Fabric service, (9) Create or edit TMDL code or TMDL files. Do NOT use for report layout/visual authoring (use powerbi-pbir), or workspace/pipeline administration (use fabric-cli).
ortools
tondevrel
Google Optimization Tools. An open-source software suite for optimization, specialized in vehicle routing, flows, integer and linear programming, and constraint programming. Features the world-class CP-SAT solver. Use for vehicle routing problems (VRP), scheduling, bin packing, knapsack problems, linear programming (LP), integer programming (MIP), network flows, constraint programming, combinatorial optimization, resource allocation, shift scheduling, job-shop scheduling, and discrete optimization problems.
dispatch
bassimeledath
"Dispatch background AI worker agents to execute tasks via checklist-based plans. Use when the user says 'dispatch' to delegate work to background agents, e.g. 'dispatch sonnet to review this', 'dispatch opus to fix the bug', 'dispatch a worker to research X'."
strategy-business-transition
spikeHongg
Analyze an A-share company's strategy, business evolution, and transformation progress. Use this skill when assessing whether a listed company is truly completing a business transition, whether legacy assets still drag results, and which milestones can confirm or falsify management's strategic narrative. All outputs must include accessible source links.
aeon
plurigrid
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
active-inference-robotics
plurigrid
"Second-order skill synthesizing Patrick Kenny's discrete active inference framework with K-Scale's JAX/MuJoCo robotics stack for predictive coding in robot locomotion"