outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
pennylane
Cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry. Enables building and training quantum circuits with automatic differentiation, seamless integration with PyTorch/JAX/TensorFlow, and device-independent execution across simulators and quantum hardware (IBM, Amazon Braket, Google, Rigetti, IonQ, etc.). Use when working with quantum circuits, variational quantum algorithms (VQE, QAOA), quantum neural networks, hybrid quantum-classical models, molecular simulations, quantum chemistry calculations, or any quantum computing tasks requiring gradient-based optimization, hardware-agnostic programming, or quantum machine learning workflows.
scikit-survival
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train less than 1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
scikit-survival
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.
statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
whatdo
What should we do? Smart activity discovery with live weather, local movie showtimes, streaming recommendations, game library matching, group profiles, routines & traditions, favorites/blacklists, business hours, ratings filtering, Quick Mode for instant suggestions, calendar integration (Google Calendar + cron reminders), group invites via Telegram/message channels, and RSVP tracking. Helps you stop scrolling and start living. Use when someone says 'what to do', 'bored', 'fun', 'tonight', 'date night', 'things to do', 'activity ideas', 'entertainment', 'adventure', 'what should we do', 'need plans', 'something fun', 'stay home', 'game night', 'movie night', 'put it on the calendar', 'send invites', 'who's coming', or just seems like they need a nudge off the couch. Optional Google Places integration for real nearby suggestions with ratings, hours, and links.
glin-profanity
Profanity detection and content moderation library with leetspeak, Unicode homoglyph, and ML-powered detection. Use when filtering user-generated content, moderating comments, checking text for profanity, censoring messages, or building content moderation into applications. Supports 24 languages.
moai-domain-uiux
UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when user asks about design systems, WCAG accessibility compliance, ARIA patterns, icon libraries, dark mode theming, design tokens, or user experience research. Do NOT use for React component coding or frontend implementation (use moai-domain-frontend instead) or shadcn/ui specifics (use moai-library-shadcn instead).
llm-icon-finder
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
pretty-mermaid
Render beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library. Supports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering. Use this skill when: 1. User asks to "render a mermaid diagram" or provides .mmd files 2. User requests "create a flowchart/sequence diagram/state diagram" 3. User wants to "apply a theme" or "beautify a diagram" 4. User needs to "batch process multiple diagrams" 5. User mentions "ASCII diagram" or "terminal-friendly diagram" 6. User wants to visualize architecture, workflows, or data models
material-model-library
Biomaterial constitutive model library skill providing validated material properties for biological tissues and implant materials
shadcn-ui
shadcn/ui component library patterns. Covers CLI usage, installation, component categories, theming with CSS variables, dark mode setup, and integration with React Hook Form + Zod. Use when adding UI components, setting up design systems, or implementing forms with shadcn/ui.
pytm
Python-based threat modeling using pytm library for programmatic STRIDE analysis, data flow diagram generation, and automated security threat identification. Use when: (1) Creating threat models programmatically using Python code, (2) Generating data flow diagrams (DFDs) with automatic STRIDE threat identification, (3) Integrating threat modeling into CI/CD pipelines and shift-left security practices, (4) Analyzing system architecture for security threats across trust boundaries, (5) Producing threat reports with STRIDE categories and mitigation recommendations, (6) Maintaining threat models as code for version control and automation.
tool-use-structured-output
Use Bedrock tool_use to guarantee structured JSON outputs from Claude models. Eliminates JSON parsing failures by forcing responses through typed tool schemas.
grpo-finetuning
Implement GRPO (Group Relative Policy Optimization) fine-tuning for vision-language models on small datasets. Use when SFT underperforms or training data is limited (<1000 examples).
gemini-image
Reference guide for using google-genai Python library to generate images with gemini-3-pro-image-preview model. Use this skill when building new projects that need Gemini image generation capabilities, to understand the correct API patterns, configuration options, and best practices.
sap-hana-ml
SAP HANA Machine Learning Python Client (hana-ml) development skill. Use when: Building ML solutions with SAP HANA's in-database machine learning using Python hana-ml library for PAL/APL algorithms, DataFrame operations, AutoML, model persistence, and visualization. Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics, HANA DataFrame, ConnectionContext, classification, regression, clustering, time series, ARIMA, gradient boosting, AutoML, SHAP, model storage
transformers-convert
Use this skill when converting custom PyTorch models to Hugging Face Transformers format. Helps with: (1) Creating PretrainedConfig and PreTrainedModel classes, (2) Writing ImageProcessor/Tokenizer, (3) Compatibility testing, (4) Hub upload preparation. Use when the user wants to make their model compatible with transformers library.
ux-design-systems
Build consistent design systems with tokens, components, and theming. Use when creating component libraries, implementing design tokens, building theme systems, or ensuring design consistency. Triggers on design system, design tokens, component library, theming, dark mode.
trigger-refactor-pipeline
Refactor Salesforce triggers into handler patterns with automated test generation and deployment. Use when modernizing legacy triggers with DML/SOQL in loops or inconsistent patterns.
vite-advanced
Advanced Vite 7+ patterns including Environment API, plugin development, SSR configuration, library mode, and build optimization. Use when customizing build pipelines, creating plugins, or configuring multi-environment builds.
refui
Use when working with rEFui (refui) applications where you cannot rely on reading the library source. Covers the retained-mode + signals mental model, DOM/HTML/Reflow renderers, JSX setup (classic pragma vs automatic runtime), directives (on:/class:/style:/attr:/prop:/m: macros), HMR via refurbish/refui/hmr, debugging “UI not updating” issues, and migrating React/Vue/Solid/Svelte patterns to rEFui.
nuxt-ui-v4
Nuxt UI v4 component library for building Nuxt v4 applications. 125+ accessible components with Tailwind v4, Reka UI, dark mode, theming. Use for dashboards, forms, overlays, editors, page layouts, pricing pages, or encountering component, theming, or TypeScript errors.
design-system-creation
Creates comprehensive design systems with typography, colors, components, and documentation for consistent UI development. Use when establishing design standards, building component libraries, or ensuring cross-team consistency. Keywords: design-tokens, typography, spacing, color-palette, components, patterns, variables, dark-mode, theming, CSS-variables, accessibility, WCAG, responsive, grid-system, breakpoints, design-scale, semantic-tokens, component-library, style-guide, documentation, Figma, Storybook, brand-consistency, design-principles
maz-ui
Maz-UI v4 - Modern Vue & Nuxt component library with 50+ standalone components, composables, directives, theming, i18n, and SSR support. Use when building Vue/Nuxt applications with forms, dialogs, tables, animations, or need responsive design system with dark mode.
cli-expert
Expert in building npm package CLIs with Unix philosophy, automatic project root detection, argument parsing, interactive/non-interactive modes, and CLI library ecosystems. Use PROACTIVELY for CLI tool development, npm package creation, command-line interface design, and Unix-style tool implementation.
vite-expert
Vite build optimization expert with deep knowledge of ESM-first development, HMR optimization, plugin ecosystem, production builds, library mode, and SSR configuration. Use PROACTIVELY for any Vite bundling issues including dev server performance, build optimization, plugin development, and modern ESM patterns. If a specialized expert is a better fit, I will recommend switching and stop.
design-system-generator
Design system generator that matches natural language descriptions to design trends. Expert in Swiss Modern, Neobrutalism, Glassmorphism, and 20+ other design trends. Includes trend matching scripts and comprehensive design pattern library.
threat-modeling
Perform threat modeling for a system or feature. Use when a senior developer needs security risk assessment.
domain-modeling
Model domains and bounded contexts for complex systems. Use when a senior developer needs domain-driven design guidance.
dhi-python
Ultra-fast data validation library for Python (520x faster than Pydantic). Use when building validated data models, API request/response schemas, or configuration objects. Provides Pydantic v2-compatible BaseModel API with Zig-powered native validation.
software-frontend
Production-grade frontend engineering for Next.js/React, Vue/Nuxt, Angular, Svelte/SvelteKit, Remix, and Vite+React. Use for framework selection, App Router/RSC patterns, TypeScript strict-mode UI code, Tailwind CSS v4 + shadcn/ui, state/data flows (TanStack Query, Zustand), forms validation, testing (Vitest/Testing Library/Playwright), performance (Core Web Vitals), and accessibility (WCAG 2.2).
prompt-engineering-creative
The meta-skill that powers all other AI tools. Prompt engineering for creative applications is the art and science of communicating with AI models to produce exactly what you envision—in images, video, audio, and text. This isn't just "write better prompts." It's understanding how different models interpret language, how to structure requests for different modalities, how to iterate systematically, and how to build prompt libraries that encode your creative vision. The best prompt engineers have developed intuition for what words trigger what responses in each model. This skill is foundational—it amplifies the effectiveness of every other AI creative skill. Master this, and you master the interface to all AI creation. Use when "prompt, prompting, prompt engineering, better prompts, prompt optimization, how to prompt, prompt strategy, prompt library, prompt template, make AI understand, prompt-engineering, prompting, meta-skill, ai-creative, foundational, optimization, iteration" mentioned.
structured-output
Expert in getting reliable, typed outputs from LLMs. Covers JSON mode, function calling, Instructor library, Outlines for constrained generation, Pydantic validation, and response format specifications. Essential for building reliable AI applications that integrate with existing systems. Knows when to use each approach and how to handle edge cases. Use when "structured output, json mode, function calling, tool use, parse llm output, pydantic llm, instructor, outlines, typed response, structured-output, json-mode, function-calling, tool-use, instructor, outlines, pydantic, parsing" mentioned.
pytest-coder
Write pytest tests with fixtures, parametrization, mocking, async testing, and modern patterns. Use when creating or updating Python test files. Not for unittest — use standard library patterns instead.
Project-Wide Rename
Safely renames a .NET project (solution, projects, namespaces, directories) from one name to another. Supports Planned (clean) and Recovery (dirty) modes.
MCP Connector
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
fairchem
Expert guidance for Meta's FAIRChem library - machine learning methods for materials science and quantum chemistry using pretrained UMA models with ASE integration for fast, accurate predictions
daisyui
Tailwind CSS component library providing semantic class names for 50+ components with built-in themes, dark mode, and customization for rapid UI development.
scikit-survival
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.
geostatspy
GSLIB-inspired geostatistics library for variogram analysis, kriging, and simulation. Use when Claude needs to: (1) Calculate experimental variograms, (2) Fit variogram models, (3) Perform simple/ordinary kriging, (4) Run sequential Gaussian simulation (SGSIM), (5) Apply normal score transforms, (6) Decluster spatial data, (7) Generate multiple realizations for uncertainty.
react-frontend
React frontend standards covering hooks (useState, useEffect, useContext, custom hooks), state management (Context API, Redux, Zustand), performance optimization (memoization, lazy loading, code splitting), testing with React Testing Library, and accessibility (WCAG 2.1, ARIA) for modern SPAs
motion-one
Use when implementing Disney's 12 animation principles with Motion One (modern, lightweight animation library)
formisch
Form handling with Formisch, the type-safe form library for modern frameworks. Use when the user needs to create forms, handle form state, validate form inputs, or work with Formisch.
bubbletea
Build terminal user interfaces with Go and the Bubbletea framework. Use it to create TUI apps with the Elm architecture, dual-pane layouts, accordion modes, mouse and keyboard handling, Lipgloss styling, and reusable components. Includes production-ready templates, an effects library, and battle-tested layout patterns derived from real projects.
Vue Development
Use when planning or implementing Vue 3 projects - helps architect component structure, plan feature implementation, and enforce TypeScript-first patterns with the Composition API, defineModel for v-model bindings, Testing Library for user-behavior tests, and MSW for API mocking. Especially useful in the planning phase to guide proper patterns before writing code.