Skill UI

This skill unlocks advanced multi-step code generation and architectural refactoring capabilities using autonomous agents. It supports parallel agent workflows, complex multi-file migrations, and multi-codebase orchestration by autonomously calling tools (Read, Write, Bash) in controlled, checkpointed cycles, drastically improving large-scale development efficiency.

A powerful AI tool designed for complex, coordinated programming tasks. It enables developers to generate, refactor, and scaffold entire features across multiple files (e.g., schema, API routes, service layers, tests) while maintaining consistency with existing codebase patterns. It supports agent mode for autonomous, multi-step changes and allows systematic migration and review of all affected files via detailed diffs.

Enables Claude to orchestrate Sugar's autonomous development workflows by creating tasks, checking system status, reviewing pending work, and triggering autonomous execution via recognized commands.

This skill automates the entire software development process overnight. By leveraging mandatory Git hooks, it strictly enforces Test-Driven Development (TDD). Use this when complex features need building, large codebases need refactoring, or bugs need fixing autonomously, guaranteeing that every commit passes rigorous testing cycles and meets high production-ready standards.

This skill performs deep, line-by-line scanning of an entire codebase to understand its architecture, patterns, and dependencies. It systematically identifies critical issues across security vulnerabilities (SQL injection, secrets), performance bottlenecks (N+1 queries, caching), architectural flaws, and code quality gaps. It then automatically refactors and fixes all identified issues, transforming the code into professional, production-grade, enterprise-level quality.

This skill simulates an autonomous, overnight development cycle by leveraging Git hooks to enforce Test-Driven Development (TDD). It ensures that all code changes, whether building new features, refactoring, or fixing bugs, are rigorously tested and meet high quality standards before commitment. Use this when high code reliability and comprehensive testing are critical requirements.

This skill provides detailed guidance on authoring effective `specs.md` files for autonomous development workflows. It teaches users how to clearly define sprint goals, establish explicit scope boundaries (In/Out of Scope), and configure rigorous testing requirements (QA, UI Testing). This ensures that agentic development remains focused and prevents scope creep.

A powerful agentic workflow for complex software development. Cascade Write mode acts as an autonomous coding agent, allowing users to build features, refactor code across multiple files, run terminal commands, and debug errors—all from a single natural language prompt. Ideal for full-stack development, complex system building, and large-scale code refactoring.

PyLabRobot is a vendor-agnostic, pure Python SDK designed for autonomous and automated laboratory workflows. It provides a unified interface to control a wide array of laboratory equipment, including liquid handling robots (Hamilton, Opentrons, Tecan), plate readers, pumps, shakers, and incubators. Ideal for developing complex, multi-device, reproducible protocols and simulating experiments before physical execution.

A comprehensive guide covering patterns and architectures for automating code execution using LLMs. It spans simple sequential pipelines (e.g., daily dev scripts) to advanced, RFC-driven multi-agent Directed Acyclic Graph (DAG) orchestration. Ideal for building CI/CD style continuous development pipelines, managing complex state, and automating quality gates without human intervention.

Autonomous frontend builders follow a Stitch-driven baton loop to read prompts, generate and integrate pages, refresh documentation, and hand off the next task for continuous site evolution.

Autoresearch Agent runs an autonomous optimization loop that edits a target file, invokes a provided evaluation command, keeps metric-improving commits, drops failures, and repeats indefinitely so engineers can optimize speed, bundle size, prompts, or other measurable goals overnight.