Reverse-engineer design systems, tokens, and components from live products or screenshots

Étendez les capacités des ensembles de compétences Recherche cognitive Azure à l’aide de modèles Azure Machine Learning.

A relentless AI agent skill for destroying personal debt permanently. Maps every dollar you owe into a single battlefield view, builds a payoff strategy calibrated to your psychology and math, tracks every payment against the plan, negotiates better terms with creditors, repairs your credit score along the way, and does not stop until the balance reads zero. For anyone drowning in credit cards, student loans, medical bills, or any combination of obligations that feel impossible to escape. They are not impossible. They are math. And math can be beaten.

Browse and search recurring patterns discovered across analyses. Patterns

>

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in Apache Pekko, Akka, Spark, ZIO/Cats Effect, and reactive architectures.

This skill enables estimation in the domain of logic (mathematics). It represents advanced-level expertise and is designed for production use in research, industry, and educational contexts.

>-

This file provides context and instructions for AI coding agents working on CIFTT.

Coordination-class Eidolon. Turns user intent into a governed multi-agent run. Use when the user asks the team (not a single Eidolon) to do something, or when a mission spans multiple capability classes. Runs the four-phase OPUS cycle (Open → Plan → Unfold → Seal). Does not reason, plan work, explore, build, or write prose — composes and routes the roster.

<!-- SYNC NOTE: AGENTS.md and CLAUDE.md must be kept identical. Edit AGENTS.md first, then copy to CLAUDE.md -->

Multi-agent visualization platform for monitoring OpenCode plugin events:

This file applies to `packages/shared`.

These instructions apply to everything under this directory tree.

This file provides guidance for agentic coding agents working with the XKids Learning Center codebase.

This document serves as the architectural blueprint and execution plan for building an open-source, asynchronous evolutionary code-generation pipeline inspired by DeepMind's AlphaEvolve. The system pr

You perform a comprehensive security audit of the codebase. You are the first agent in the pipeline — your findings drive everything that follows.

Core application code lives in `src/`. The backend API is in `src/server`, with `api/` for FastAPI routes, `modules/` for pipeline stages such as parsing, alignment, narration, and rendering, `models/

Learn how to execute agents and handle results.

When a command is invoked, follow the chain defined in its frontmatter:

Quick reference for visualizing data on Mapbox maps.

The `kalistat` CLI queries ISTAT and Eurostat statistical data through the Kalistat API. This skill teaches you to drive it correctly without guessing flags or inventing dataset codes.

Radzen Blazor Components is a free, open-source library of 90+ Blazor components including DataGrid, Scheduler, Chart, Form, Dialog, and Notification. The library provides its own design system with m

Transform lengthy academic papers into concise, structured 250-word abstracts.

Draw ROB2 risk-of-bias plots, including a Traffic Light Plot and a Summary Bar Plot. Input is a CSV file with ROB2 assessments for each study; output are two PNG plot files.

A practical guide to choosing, pairing, and implementing typefaces for the web. Typography serves communication — the best typography is invisible, immersing readers in content rather than calling att

Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.

Use when the user wants to download a paper PDF from a DOI (or title, resolved to a DOI first) via legal open-access sources. Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, and Semantic Scholar in order.

AMAZON ALEXA \u2014 Voz Inteligente com Claude workflow skill. Use this skill when the user needs Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home) and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

AMAZON ALEXA \u2014 Voz Inteligente com Claude workflow skill. Use this skill when the user needs Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home) and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

ANALYTICS-PRODUCT \u2014 Decida com Dados workflow skill. Use this skill when the user needs Analytics de produto \u2014 PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

ANALYTICS-PRODUCT \u2014 Decida com Dados workflow skill. Use this skill when the user needs Analytics de produto \u2014 PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

>-

'Mine transcripts and artifacts into reusable learnings, decisions, and patterns.'

'Load relevant .agents knowledge into the current session context.'

'Show current work, recent validation, flywheel health, and next action.'

Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

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.

Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly Express) and fine-grained customization (graph objects). Outputs interactive HTML or static images (PNG, PDF, SVG).

Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.

Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.

Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

Comprehensive Cloudflare account management for deploying Workers, KV Storage, R2, Pages, DNS, and Routes. Use when deploying cloudflare services, managing worker containers, configuring KV/R2 storage, or setting up DNS/routing. Requires CLOUDFLARE_API_KEY in .env and Bun runtime with dependencies installed.

Production-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environments, processing large volumes of PDFs, or requiring robust error handling and validation.

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Uploads promo videos and content to Cloudflare R2 or AWS S3. Use when the user wants to host promo content for social media or distribution.