Skill UI

This powerful router analyzes complex document types (scanned, medical, table-heavy, etc.) and determines the optimal conversion pipeline (tools, flags, cleanup) to extract data into various formats like Markdown, JSON, or DOCX. It goes beyond simple text extraction by prioritizing the preservation of document structure, relational data, and high fidelity, ensuring the generated output is accurate for downstream machine processing.

This skill enables authorized reverse engineering of custom binary protocols, Protobuf/gRPC schemas, and WebSocket frames using PCAP data. It helps recover undocumented wire protocols, decode structured traffic, and reconstruct state machines for security analysis and debugging purposes.

Review supervisor, swarm, planner-worker and parallel agent workflows as distributed state machines: task ownership, shared state, branch joins, retries, cancellation, context handoffs, budgets, deadlocks and human escalation before rollout.

This skill provides best practices for state management and persistence in Makepad applications based on Robrix and Moly codebases. It covers AppState structure, serde serialization, theme switching, and passing state through widget trees using Scope. Includes production patterns for global registry, navigation, state machines, and local persistence to ensure robust application data handling.

This skill provides a robust system for tracking all code modifications using structured JSON records and enforcing a defined state machine (e.g., planned -> deployed). It is critical for AI coding workflows, ensuring that if a session expires or is abandoned, the next session receives the full context, progress summary, and blockers to resume seamlessly. Ideal for complex, multi-stage development projects and onboarding new codebases.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes like Node.js, Bun, and Deno, enabling text analysis, image classification, speech recognition, and multimodal AI applications without a Python backend.

This skill guides the systematic triage of project issues and external pull requests (PRs). It moves development items through a defined state machine using roles (e.g., bug, enhancement) and states (e.g., ready-for-agent, wontfix). The process involves context gathering, cross-codebase verification, deep questioning (grilling), and generating comprehensive, agent-ready briefs or marking them for human implementation.

Official M2MCent wrapper for injecting x402 paywalls into Node.js/Express APIs or Model Context Protocol (MCP) servers. Enables machine-to-machine monetization by requiring USDC micropayments on Base L2. Includes middleware for Express routes and handles settlement automatically.