MLOps
Operacions d’aprenentatge automàtic
planning-marketing-budget
amogha-dalvi
Use when the user needs to derive a marketing budget from revenue targets, plan headcount for a 1-3 person team, decide what to build vs. buy vs. automate, or allocate spend across channels with ROI expectations. Use when budget is based on gut feel rather than revenue math, or resource allocation feels arbitrary.
dbt-expert
timequity
dbt best practices for models, tests, documentation, and project organization.
defining-icp-segmentation
amogha-dalvi
Use when targeting feels unfocused, CAC is too high, churn patterns suggest bad-fit customers, or the ICP lives only in the founder's head. Use when entering a new market, conversion rates are low, or sales wastes cycles on wrong-fit accounts. Use after customer research is complete and before any channel or campaign decisions.
growing-nrr
amogha-dalvi
Use when net revenue retention is below 110%, when churn patterns are reactive instead of predictive, when expansion revenue lacks systematic triggers, when onboarding fails to reach activation milestones, or when customer health scoring does not exist. Use when customer base is large enough for patterns (50-500 accounts) but retention is managed manually.
accelerating-pipeline
amogha-dalvi
Use when pipeline velocity is flat or declining, win rates are below 20 percent, sales cycles are lengthening, deals are single-threaded, or lead routing is slow. Use when MQL volume is prioritized over pipeline quality, when marketing and sales define funnel stages differently, or when signal-based engagement has not replaced linear nurture drips.
image-gen
openclaw-rocks
Generate images via Fuel proxy. No API key needed on Pro plans.
nano-banana
Nymbo
Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
marketing-system-index
amogha-dalvi
Use when starting any marketing work for a SaaS business at 1M-5M ARR, when needing to find the right marketing skill, or when planning which marketing skills to execute and in what order.
image-upscale
agntswrm
Upscales an image using AI super-resolution to increase resolution with detail generation. Use when you need to enlarge images, improve low-resolution photos, or prepare images for large-format display.
designing-gtm-strategy
amogha-dalvi
Use when the user needs to translate foundational marketing insights into an operational growth plan, select a GTM motion, prioritize channels, or create a 90-day execution plan. Use when marketing efforts feel like disconnected tactics without a coherent system connecting them to revenue targets.
fuel
openclaw-rocks
"Optimized LLM inference and agent config for OpenClaw. Multi-provider routing with automatic cheapest-provider selection, context pruning, smart compaction, cheap heartbeats, session initialization, prompt caching, and memory management — all calibrated for autonomous agents that run for hours without wasting tokens. Triggers on: 'save on inference,' 'cheaper models,' 'optimize costs,' 'LLM config,' 'model routing,' 'inference setup,' 'fuel,' 'reduce token usage,' 'context management,' or any request to make an OpenClaw agent more cost-effective."
django-model-helper
Dexploarer
Generates Django models with proper field types, relationships, and migrations. Use when creating Django models or database schemas.
data-cleaning-pipeline-generator
Dexploarer
Generates data cleaning pipelines for pandas/polars with handling for missing values, duplicates, outliers, type conversions, and data validation. Use when user asks to "clean data", "generate data pipeline", "handle missing values", or "remove duplicates from dataset".
tracking-marketing-metrics
amogha-dalvi
Use when marketing lacks a metrics hierarchy connecting activity to business outcomes, when attribution is last-click or nonexistent, when marketing and sales report different numbers, when dashboards are ignored or full of vanity metrics, or when leading indicators are not tracked. Use when decisions are made on gut feel instead of data.
jupyter-notebook-assistant
Dexploarer
Organizes, cleans, and optimizes Jupyter notebooks - removes empty cells, adds structure, extracts functions, generates documentation. Use when user asks to "clean notebook", "organize jupyter", "refactor notebook", or "jupyter best practices".
context-fundamentals
Nymbo
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
MLIP Simulation Skill
fl-sean03
Phonopy: https://phonopy.github.io/phonopy/
torch-sim Skill
fl-sean03
data-analysis skill - Analyzing torch-sim outputs
transformers-js
nico-martin
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.
continuous-monitoring
pluginagentmarketplace
Real-time monitoring and detection of adversarial attacks and model drift in production
red-team-frameworks
pluginagentmarketplace
Tools and frameworks for AI red teaming including PyRIT, garak, Counterfit, and custom attack automation
ai-ml-senior-engineer
mOdrA40
Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".
wpf-mvvm-generator
JeongHeonK
WPF MVVM code generator. Creates ViewModel, View, and Model with CommunityToolkit.Mvvm source generators. Use when scaffolding new WPF features or entities following MVVM pattern.
hytale-custom-assets
MnkyArts
Create and manage custom assets for Hytale including models, textures, sounds, particles, and asset packs. Use when asked to "add custom assets", "create textures", "make models", "add sounds", "configure particles", or "build an asset pack".