Loading...
Loading...
Found 8,097 Skills
Readable primary-flow–first code structuring with minimal boundaries, atomic composition, and contract-driven unit tests
Strict Home Assistant Integration Code Review. Used for comprehensive checks before submitting PRs, including Quality Scale rule validation, code style, Config Flow, test coverage, and documentation. Triggered when users say "Review my HA integration", "Check if my code complies with HA specifications", or "Help me review the code ready for submission".
Create Claude skills from book content (markdown files). Transforms long-form book knowledge into structured, context-efficient skill packages with granular reference files, workflows, and use-case guidelines. Use this skill when: - Converting a book (markdown) into a reusable Claude skill - Creating knowledge bases from technical books, guides, or documentation - Building skills that need progressive disclosure of large content - Structuring book knowledge for efficient context loading
Conversational guidance for building software with AI agents, covering workflows, tool selection, prompt strategies, parallel agent management, and best practices based on real-world high-volume agentic development experience. Use this skill when users ask about setting up agentic workflows, choosing models, optimizing prompts, managing parallel agents, or improving agent output quality.
Create new Agent Skills for Claude Code. Use when user wants to create a skill, add a new capability, document a CLI workflow, or asks how skills work.
Integrate oh-my-ag with MCP for ulw-style multi-agent workflows. Covers install, setup, bridge mode, and verification steps.
Git-centric implementation workflow. Enforces clean checkout, creates a properly named branch, tracks progress in a WIP markdown file, and commits continuously so git logs serve as the primary monitoring channel. Use when starting instructed, offer for any plan-based implementation task.
Iterative debugging workflow with confidence scoring and strategic log injection. Five phases: investigate, inject logs, propose fix, verify, cleanup. Use when: debugging unexpected behavior, silent errors, intermittent failures, or issues requiring runtime data. Triggers on "debug", "fix bug", "investigate", "trace issue", "add debug logs", "cleanup debug logs".
Generate git commit messages and help with git workflows
Create interactive Sankey diagrams for flow visualization from CSV, DataFrame, or dict data. Supports node/link styling and HTML/PNG/SVG export.
Edit, analyze, and create Node-RED flows by working with flows.json files, understanding node types, and applying Node-RED best practices. Use when the user mentions Node-RED, flows.json, flow development, or needs to modify Node-RED configurations.
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.