raphaelmansuy

Drive the macOS desktop in the background via computer_use and cua-driver — launch apps, capture SOM indices, click/type/key without stealing focus.

Use JSON validation and JSON Pointer lookup tools for exact payload inspection.

Use calculator tools for exact arithmetic and unit conversion.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native EdgeCrab tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

Query Base (Ethereum L2) blockchain data with USD pricing — wallet balances, token info, transaction details, gas analysis, contract inspection, whale detection, and live network stats. Uses Base RPC + CoinGecko. No API key required.

Query Solana blockchain data with USD pricing — wallet balances, token portfolios with values, transaction details, NFTs, whale detection, and live network stats. Uses Solana RPC + CoinGecko. No API key required.

Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files.

Implement Agent-to-Agent (A2A) protocol for inter-agent communication. Use for agent discovery, agent cards, task delegation, and multi-agent orchestration. Triggers on "A2A protocol", "agent-to-agent", "agent discovery", "agent card", "multi-agent", "agent delegation", "agent communication", or when implementing spec/api/017-a2a-protocol.md.

Implement CI/CD pipelines for AI agent deployment with evaluation gates. Use for GitHub Actions workflows, GitOps with ArgoCD, container image building, and automated testing. Triggers on "CI/CD", "pipeline", "GitHub Actions", "GitOps", "ArgoCD", "deployment automation", "continuous deployment", or when implementing safe agent release workflows.

Implement agent evaluation and safety gates using MLflow 3.x. Use for creating LLM-as-Judge scorers, evaluation datasets, quality gates, tracing, and continuous evaluation. Triggers on "evaluate agent", "MLflow scorer", "LLM judge", "safety evaluation", "quality gate", "agent testing", "hallucination detection", or when implementing spec/010-agent-evaluation.md requirements.

Build CLI tools using Go with Cobra and Viper. Use for implementing agentctl commands, interactive prompts, configuration management, and output formatting. Triggers on "CLI", "agentctl", "command line", "cobra", "terminal application", "interactive prompt", or when implementing spec/009-developer-experience.md CLI section.

Build the AgentStack API Gateway in Go with Fiber/Chi. Use for creating REST API endpoints, HTTP handlers, middleware, request validation, and API routing. Triggers on "build API", "create endpoint", "HTTP handler", "REST API", "API gateway", "Fiber handler", "Chi router", or when implementing spec/004-api-design.md endpoints.

Deploy serverless workloads with Knative Serving for scale-to-zero and autoscaling. Use for creating Knative Services, configuring autoscaling, traffic splitting, and revisions. Triggers on "knative service", "scale-to-zero", "serverless deployment", "ksvc", "knative autoscaling", "traffic splitting", or when deploying agents as serverless workloads.

Generate production-ready Kubernetes manifests for AgentStack. Use for creating Deployments, Services, ConfigMaps, Secrets, RBAC, and other K8s resources. Triggers on "create deployment", "k8s manifest", "kubernetes yaml", "pod spec", "service definition", "configmap", "RBAC", or when deploying components to Kubernetes.

Implement multi-tenant PostgreSQL database layer with row-level security. Use for database schema design, tenant isolation, migrations, connection pooling, and data access patterns. Triggers on "database schema", "PostgreSQL", "multi-tenant", "row-level security", "RLS", "database migration", "sqlc", or when implementing the data layer for AgentStack.

Integrate CopilotKit AI components into Next.js frontend for building agentic UIs. Enables context-aware AI agents that can read app state and trigger tools/actions. Supports custom adapters for self-hosted LLMs and multiple provider integrations.

Validate documentation traceability between code annotations (@implements), feature registry, business rules, and use cases. Detect ID collisions, undocumented features, broken cross-references, and namespace violations.

Service management for E2E testing in EdgeQuake. Start, stop, and monitor PostgreSQL, backend API, and frontend services. Includes health checks and logging utilities for interactive testing workflows.

Unified development workflow for EdgeQuake using Makefile commands. Use when starting services, running tests, or managing the full development stack (database, backend, frontend). Provides simplified alternatives to raw cargo/npm commands.

Validate PDF to Markdown conversion quality using multi-dimensional metrics. Assess table accuracy, style preservation (bold/italic/headings), robustness, and performance with standardized F1-scoring methodology.

Capture EdgeQuake WebUI routes with Playwright and write artifacts immediately (screenshots + per-page request JSON + capture index). Use when adding/updating Playwright E2E capture specs or when asked to automate UI screenshot collection.

Automatically generate comprehensive documentation for Rust and TypeScript codebases by analyzing code structure, patterns, and relationships. Supports trait-based patterns, async operations, React components, and Next.js applications.

Analyze exactly one captured UI page (from ux_ui_map screenshots + request JSON) and immediately write/update ux_ui_map/pages/{page}.md in neutral descriptive language. Use when asked to analyze screenshots, rewrite corresponding analysis immediately, or avoid memory/context saturation.

Write and generate Packt publisher manuscripts as pixel-perfect DOCX using edgemint. Use this skill when the user is authoring a Packt book chapter, applying Packt house styles, generating or reviewing a Packt-style Word document, or converting Markdown to a Packt-compliant manuscript. Knows every Packt paragraph style, character style, callout, list level, and code block variant. Triggers on: "Packt chapter", "Packt style", "publisher manuscript", "Packt template", "write a chapter for Packt", "generate Packt DOCX".

Generate style-faithful DOCX documents from Markdown using the edgemint CLI. Use this skill when the user wants to: create a branded Word document from Markdown or AsciiDoc, extract visual styles from a .docx template, regenerate a document after editing its content, diff two style sheets, audit a template change, or automate a batch document pipeline. Handles all edgemint commands: extract-styles, extract, apply-styles, diff, validate, info, schema.

Write and generate Packt publisher manuscripts as pixel-perfect DOCX using edgemint. Use this skill when the user is authoring a Packt book chapter, applying Packt house styles, generating or reviewing a Packt-style Word document, or converting Markdown to a Packt-compliant manuscript. Knows every Packt paragraph style, character style, callout, list level, and code block variant. Triggers on: "Packt chapter", "Packt style", "publisher manuscript", "Packt template", "write a chapter for Packt", "generate Packt DOCX".

Generate style-faithful DOCX documents from Markdown using the edgemint CLI. Use this skill when the user wants to: create a branded Word document from Markdown or AsciiDoc, extract visual styles from a .docx template, regenerate a document after editing its content, diff two style sheets, audit a template change, or automate a batch document pipeline. Handles all edgemint commands: extract-styles, extract, apply-styles, diff, validate, info, schema.

Master SOTA data prep for Kaggle comps: automated EDA (Sweetviz), cleaning (Pyjanitor), and feature selection (Polars + XGBoost) for medium datasets (100MB–5GB) in Colab.

Use this skill to create new Agent Skills for GitHub Copilot. It guides you through the process of setting up the directory structure and the SKILL.md file.

Guide for using and supporting the AGENTS.md standard in VS Code. Use this when asked about AGENTS.md, custom instructions, or repo-level AI agent configuration.

Use this skill for systematic problem-solving through structured, iterative thinking. Break down complex problems, iterate on understanding, catch edge cases, and validate solutions comprehensively.

Extract structured content from any PDF for AI agents, RAG pipelines, and Copilot Skills. Use this skill whenever the user wants to read, analyze, or reason about a PDF document; needs to feed document content to an LLM; mentions PDF extraction, parsing, or conversion; wants tables, headings, or bounding boxes from a PDF; is building a RAG pipeline; or asks an agent to process a document. Install with: pip install edgeparse

Use this skill whenever the user wants to extract structured content from PDF files — reading or extracting text, tables, headings, images, and bounding boxes from PDFs, or converting PDFs to Markdown, JSON, HTML, or plain text. EdgeParse is a zero-dependency Rust-native tool (no JVM, no GPU, no OCR models required). Use this skill when the user has a .pdf file and wants to parse it, extract its text or tables, convert it to Markdown or JSON, get bounding boxes for content elements, process multiple PDFs in batch, or pipe PDF content to an LLM pipeline.

Build fast, SEO-optimized static sites with Docusaurus v3.9.2 using Markdown/MDX, SEO metadata, and plugins. Helps with setup, docs, SEO optimization, plugin integration, and GitHub Pages deployment.