looped-builder
Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
508 skills found
Scaffold complex, multi-step coding tasks into actionable implementation plans and execute them autonomously using a Claude-driven bash loop.
Search and retrieve AI-generated documentation, architecture guides, and API references for 300+ popular GitHub repositories using DeepWiki and MCP.
A rigorous TDD workflow agent that enforces test-first development, ensuring 80%+ code coverage across unit, integration, and E2E tests for features, bug fixes, and refactoring.
A decision-support tool for Claude Code users to select the optimal extension mechanism—slash commands, skills, subagents, or hooks—based on project requirements.
Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).
Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.
Perform internet searches using the Zhipu AI web search API to retrieve real-time information, news, and current data.
A structured development process for Python projects using TDD, the uv package manager, and automated testing workflows.
Explains complex concepts using master teaching frameworks like Feynman, Socratic, and Cognitive Load theory to ensure deep, clear understanding.
Development guide for creating custom nodes in FlowGram.ai workflows, supporting both auto-generated simple forms and complex custom UI components.
Manages complete plugin lifecycle for JUCE development: install, uninstall, reset, and destroy. Handles system folder deployment, cache management, and safe, version-controlled removal for audio developers.
Evaluate Deca agent prompts and behavioral consistency through automated test runners, manual LLM judgment, and structured reporting.