Loading...
Loading...
Found 564 Skills
Self-contained design transformer — invoke directly, do not decompose. Transforms a design reference HTML file into a Vibes app. Use when user provides a design.html, mockup, or static prototype to match exactly.
Primary tool for all code navigation and reading in supported languages (Rust, Python, TypeScript, JavaScript, Go). Use instead of Read, Grep, and Glob for finding symbols, reading function implementations, tracing callers, discovering tests, and understanding execution paths. Provides tree-sitter-backed indexing that returns exact source code — full function bodies, call sites with line numbers, test locations — without loading entire files into context. Use for: finding functions by name or pattern, reading specific implementations, answering 'what calls X', 'where does this error come from', 'how does X work', tracing from entrypoint to outcome, and any codebase exploration. Use Read only for config files, markdown, and unsupported languages.
Analyze and extract relevant patterns, best practices, and usage examples from fetched documentation for implementation guidance.
shadcn/ui component integration for Inertia Rails React (NOT Next.js): forms, dialogs, tables, toasts, dark mode, command palette, and more. Use when building UI with shadcn/ui components in an Inertia app or adapting shadcn examples from Next.js. NEVER react-hook-form/zod — wire shadcn inputs to Inertia Form via name attribute. Flash toasts require Rails flash_keys initializer config.
Implements and enforces code quality gates for TypeScript/React projects. Use when setting up Biome/ESLint/TypeScript, configuring pre-commit hooks (Husky), fixing lint errors, or running quality checks. Examples - "setup code quality", "fix lint errors", "configure Biome", "run quality checks".
Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis.
Analyzes and refines agent skills by identifying quality issues, prioritizing fixes (MUST/SHOULD/NICE), gathering user feedback, and implementing improvements. Checks for common problems like time estimates, oversized SKILL.md files, poor structure, redundant content, missing examples, and unclear workflows. Use when reviewing, improving, refactoring, or auditing existing skills. Triggers include "review skill", "improve skill", "refactor skill", "skill quality", "audit skill", "fix skill", "optimize skill", "analyze skill".
Write Python docstrings following the Google Python Style Guide, using clear sections and examples.
Analyzes errors, searches past solutions in memory, provides immediate fixes with code examples, and saves solutions for future reference. Use when user says "debug this", "fix this error", "why is this failing", or when error messages appear like TypeError, ECONNREFUSED, CORS, 404, 500, etc.
Optimize, rewrite, and evaluate prompts using the Anthropic 1P interactive prompt-engineering tutorial patterns (clear/direct instructions, role prompting, XML-tag separation, output formatting + prefilling, step-by-step “precognition”, few-shot examples, hallucination reduction, complex prompt templates, prompt chaining, and tool-use XML formats). Use for 提示词优化/Prompt优化/Prompt engineering, rewriting system+user prompts, enforcing structured outputs (XML/JSON), reducing hallucinations, building multi-step prompt templates, adding few-shot examples, or designing prompt-chaining/tool-calling scaffolds.
Learn mode for explaining code, concepts, and architecture. Use when user asks to explain how things work, understand concepts, or learn about code patterns. Provides explanations from simple to complex with examples and analogies.
Guide for Claude Agent SDK - build custom AI agents powered by Claude. Covers installation, authentication providers, tool permissions, file-based configuration, TypeScript/Python code examples, and project scaffolding templates.