Skill UI

Guides designers in creating Claude Code agents by defining frontmatter, triggering conditions, system prompt structure, color/tool choices, and quality best practices for autonomous workflows.

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.

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.

Automates autonomous overnight software development by wiring Git hooks, TDD, and logging so Claude can build features, refactor code, and fix bugs while guaranteeing all tests pass before committing.

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.

This skill provides a robust methodology for performing end-to-end UI testing and verification on Android emulators. Utilizing ADB commands, users can autonomously inspect UI element bounds (via uiautomator), simulate interactions (taps, swipes, input text), and capture visual/analytical screenshots. It is ideal for verifying UI changes in React Native or native Android applications, speeding up the debugging process, and generating comprehensive documentation for pull requests.

Documents how to build autonomous Claude Code loops, covering sequential pipelines, NanoClaw REPL, infinite multi-agent deployments, RFC-based DAG orchestration, and PR-driven CI cycles so teams can run persistent, quality-gated development workflows without babysitting.

Defines a continuous autonomous agent loop pattern with quality gates, evaluations, and recovery actions, orchestrating CI/PR controls, RFC breakdown, and assessment cycles to keep release branches stable.

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.

Starts a recurring autoresearch experiment loop at user-selected intervals (10 minutes to monthly), auto-schedules CronCreate jobs, records experiment metadata, and offers commands to monitor progress or stop the loop.