TDD workflow for migrations - orchestrate agents, zero main context growth

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Use this skill when a task needs AI-assisted web research via a real browser. Uses Chrome CDP (Chrome DevTools Protocol) as the primary automation method, with browser-use as fallback. Supports...

Systematically reduces AI detection rate and adds human touch through three-pass proofreading (content, style, details). Use when proofreading articles, reducing AI flavor, when content feels...

Implement static code analysis with linters, formatters, and security scanners to catch bugs early. Use when enforcing code standards, detecting security vulnerabilities, or automating code review.

Ultimate Bug Scanner - Pre-commit static analysis for AI coding workflows. 18 detection categories, 8 languages, 4-layer analysis engine. The AI agent's quality gate.

Build production AI agents with Pydantic AI: type-safe tools, structured output, embeddings, MCP, 30+ model providers, evals, graphs, and observability.

Generate or edit images using Google Gemini API via nanobanana. Triggers: "nanobanana", "generate image", "create image", "edit image", "AI drawing", "图片生成", "AI绘图", "图片编辑", "生成图片".

Help users evaluate emerging technologies. Use when someone is assessing new tools, making build vs buy decisions, evaluating AI vendors, or deciding on technical architecture.

Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination

Reference guide for Agentica multi-agent infrastructure APIs

Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code...

Run Claude Code (Anthropic) from this host via the `claude` CLI (Agent SDK) in headless mode (`-p`) for codebase analysis, refactors, test fixing, and structured output. Use when the user asks to...

Run Claude Code (Anthropic) from this host via the `claude` CLI (Agent SDK) in headless mode (`-p`) for codebase analysis, refactors, test fixing, and structured output. Use when the user asks to...

A skill for reviewing code, providing feedback, and ensuring code quality and best practices.

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.

Elevate projects to production quality using proven patterns. Use when starting a project, reviewing architecture, auditing code, or when user mentions "elevate-code", "production ready",...

Intelligent code review dispatcher - automatically selects best reviewer based on context and preferences

Coding Agent Account Manager - Sub-100ms account switching for AI coding CLIs with fixed-cost subscriptions. Vault profiles, isolated profiles for parallel sessions, smart rotation with health...

Enables Claude to use Google AI Studio for testing prompts, exploring models, and prototyping AI applications