LLM & Agents

Configure Vitest 4.x with correct pool architecture, coverage settings, and multi-project setup. Use when creating or modifying vitest.config files or setting up test infrastructure.

DB管理プロンプトの作成/更新（versioning、variables、レンダリング確認、出力マーカー準拠）に使う。

Blends the user's recently sent and starred Gmail emails into a single executive recap with summaries, metadata, and follow-up prompts.

Use this skill when building MCP (Model Context Protocol) servers with TypeScript on Cloudflare Workers. This skill provides production-tested patterns for implementing tools, resources, and prompts using the official @modelcontextprotocol/sdk. It prevents 10+ common errors including export syntax issues, schema validation failures, memory leaks from unclosed transports, CORS misconfigurations, and authentication vulnerabilities. This skill should be used when developers need stateless MCP servers for API integrations, external tool exposure, or serverless edge deployments. For stateful agents with WebSockets and persistent storage, consider the Cloudflare Agents SDK instead. Supports multiple authentication methods (API keys, OAuth, Zero Trust), Cloudflare service integrations (D1, KV, R2, Vectorize), and comprehensive testing strategies. Production tested with token savings of ~70% vs manual implementation.Keywords: mcp, model context protocol, typescript mcp, cloudflare workers mcp, mcp server, mcp tools

Stream Deck integration assistant for VSCode. Create, manage, and organize Stream Deck profiles, buttons, snippets, and scripts. Helps build productivity workflows for developers using Stream Deck with Claude Code and TAC (Tactical Agentic Coding) patterns.

Prompt 工程助手，提供 AI Prompt 设计、优化与调试，涵盖系统提示词、任务提示词、结构化输出设计与最佳实践指导。

Generate comprehensive unit tests for source files with 100% coverage target. Use when writing tests for React components, utility functions, hooks, or API routes. Supports Jest and Vitest frameworks following Pandora coding standards.

Discovery-driven codebase indexer for Claude Code. Analyzes what EXISTS in a project, then documents what developers need to know. Creates CLAUDE.md + claude-docs/ with architecture-aware documentation. Supports any language (JS/TS, Python, Java, Rust, Go, etc.). Use when: user asks to "index project", "document codebase", "set up claude docs", "analyze project structure", "help me understand this codebase", or when starting work on unfamiliar project. Triggers on phrases like "index this", "create docs for claude", "document the codebase", "set up project documentation".

Generate comprehensive async pytest tests for Quart endpoints, database operations, and WebSocket connections. Activates when writing tests or ensuring code coverage.

Understanding and using StickerNest's self-improving AI system. Use when the user asks about AI self-improvement, prompt versioning, reflection loops, AI evaluation, auto-tuning prompts, or the AI judge system. Covers AIReflectionService, stores, and the improvement loop.

Guide for spec-based agent-driven development using structured requirements (EARS notation), technical design documentation, and implementation planning. Use when users want to build features using a specification-first approach, need to document requirements formally, want to generate implementation plans from specs, or when working on projects that benefit from clear requirement-to-code traceability.

Documentation for Kubernetes Agent Sandbox - a CRD-based system for managing isolated AI agent execution environments. Use for queries about Sandbox CRDs (Sandbox, SandboxTemplate, SandboxClaim, SandboxWarmPool), Python SDK (SandboxClient, SandboxRouter, ComputerUseExtension), network policies, security configurations, and implementation examples. Keywords kubernetes sandbox, agent sandbox, CRD, python sdk, agentic-sandbox-client, isolated environment, gvisor, network policy.

Collaborative idea refinement - turns rough ideas into fully-formed designs through questioning, alternative exploration, and incremental validation. Use before writing code or implementation plans.

Customer-facing documentation

Meta-skill for extracting and creating reusable Claude Code skills from past work sessions. Analyzes git history, code patterns, workflows, and documentation to identify harvestable skills, then generates comprehensive skill definitions with best practices, examples, and structured templates.

Technical documentation creation and improvement with emphasis on clarity, conciseness, and maximum communication efficiency. Use for README files, API docs, project documentation, code comments, and any written content. Prioritizes brevity over verbosity, essential information over comprehensive detail, and immediate usefulness over exhaustive coverage.

Implements Anthropic's Parallelization pattern with two modes - Sectioning (independent subtasks in parallel) and Voting (multiple approaches evaluated). Use when tasks decompose into independent units or when comparing implementation strategies. Delivers 2-10x speedup or consensus-based decisions.

Write and debug Bun tests with proper mocking, coverage, and isolation. Use when writing tests, debugging test failures, setting up test infrastructure, mocking fetch/modules, or improving test coverage.

Create, evaluate, and improve Agent skills to production quality (100/100). Use when the user wants to create a new skill, review an existing skill, score a skill against best practices, or improve a skill's quality. Also use when the user mentions skill development, skill templates, or skill optimization.

Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.