LLM & Agents

Use when implementing ANY code for the Home Assistant Emby integration - enforces strict TDD with RED-GREEN-REFACTOR cycle, requiring tests to fail before implementation and pass after. No exceptions for simple code.

RGRCサイクルとBaby Steps方法論を用いたTDD。トリガー: TDD, テスト駆動開発, Red-Green-Refactor, Baby Steps, test generation, テスト生成, テスト設計, テストケース, boundary value, 境界値分析, coverage, カバレッジ, unit test

Send prompts to a remote Claude instance on a VPS for distributed AI collaboration, different model backends, or independent context.

Use when implementing Emby MediaPlayerEntity - covers all supported features, state management, playback control, media browsing, image handling, and Emby-specific API mappings for Home Assistant media player integration.

Set up Git worktrees for agent parallelization with isolated environments. Use when setting up parallel agent execution, creating isolated environments per agent, or enabling concurrent development workflows.

Systematic prompt evaluation framework with MATH, GSM8K, and Game of 24 benchmarks. Use when evaluating prompt effectiveness on standard benchmarks, comparing meta-prompting strategies quantitatively, measuring prompt quality improvements, or validating categorical prompt optimizations against ground truth datasets.

Saves Claude Code or Codex CLI conversation threads to Nowledge Mem knowledge base via HTTP API. Use when user requests to save, persist, or backup the current session or conversation thread.

CC2.0 seven-function research workflow (observe, reason, create, orchestrate, learn, verify, deploy) for categorical AI research. Use when conducting systematic research on categorical AI topics, coordinating multi-stream research workflows, applying categorical foundations to research methodology, or implementing the L5 meta-prompting research framework.

Claude Code plugin enforcing operational guidelines, terse responses, sequential execution, and no destructive operations without confirmation.

Use when working with CSS, creating components, styling elements, refactoring styles, or reviewing CSS code. Guides CSS development following Tailwind + semantic component patterns with dark mode support and test coverage.

Create meta prompts, meta agents, and meta skills that build other agentic components. Use when scaling agentic layer development, creating generators/templates, or implementing "build the system that builds the system" patterns.

LLM4S Scala functional LLM interfaces with Effect system integration. Use when building LLM applications in Scala with ZIO or Cats Effect, implementing type-safe AI pipelines with functional error handling, creating composable prompt systems in Scala, or leveraging Scala's type system for robust AI applications.

Google Cloud Vector Search 2.0 introduction and implementation guide

Opentrons Temperature Module - precise heating and cooling (4-95°C) for sample storage, enzyme reactions, and temperature-sensitive protocols with aluminum block adapters for plates, tubes, and PCR strips

Review and create technical design documents or technical blogs for the Moni Assistant project. Use this skill when:- Creating new technical design documents in docs/technical-design/- Creating technical blog posts in blog/- Reviewing existing technical designs or blogs for completeness and quality- Ensuring documents follow the project's documentation standards- Writing architecture overviews, system designs, or feature specifications

Guide creation of minimum viable agentic layer for a codebase. Use when starting agentic coding in a new project, bootstrapping essential components, or creating the minimal scaffolding for agent success.

Central authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key, Bedrock, Vertex), sessions and resumption, forking sessions, streaming vs single mode, custom tools, permissions (allowedTools, disallowedTools, permissionMode), MCP integration, system prompts (CLAUDE.md, appendSystemPrompt, outputStyle), cost tracking, todo tracking, structured outputs, hosting patterns, plugins, and SDK branding guidelines. Assists with building custom agents, configuring SDK options, and troubleshooting SDK issues. Delegates 100% to docs-management skill for official documentation.

Write prompts for orchestrator workflows with phases and aggregation. Use when designing multi-phase workflows, writing agent command prompts, or implementing result aggregation patterns.

Create and configure Claude Code marketplaces and plugins. Use when the user wants to create a marketplace, publish plugins, set up team plugin distribution, or configure marketplace.json or plugin.json files. Triggers: create marketplace, publish plugin, plugin distribution, marketplace.json, plugin.json, team plugins, share plugins

Single source of truth and librarian for ALL Cursor documentation. Manages local documentation storage, scraping, discovery, and resolution. Use when finding, locating, searching, or resolving Cursor documentation; discovering docs by keywords, category, tags, or natural language queries; scraping from llms.txt; managing index metadata (keywords, tags, aliases); or rebuilding index from filesystem. Run scripts to scrape, find, and resolve documentation. Handles doc_id resolution, keyword search, natural language queries, category/tag filtering, alias resolution, llms.txt parsing, markdown subsection extraction for internal use, hash-based drift detection, and comprehensive index maintenance.