LLM & Agents

A workflow that enforces genuine test-driven development: tests first, behavior-focused, with strong edge-case coverage.

Detects and refactors code duplication using PMD CPD. Use when identifying code clones, addressing DRY violations, or refactoring duplicate code across repositories.

When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting local LLM server connections.

Identify and fix Magento 2 module compatibility issues with Hyvä Themes. Covers block plugin bypasses, RequireJS/Knockout replacements, ViewModels, and Alpine.js integration for modules that work in admin but fail on Hyvä frontend.

how to approach tests, types and coverage

Generate YouTube Live stream content, consciousness responses, and engagement prompts. Use when creating stream announcements, chat responses, moderation messages, community engagement prompts, or emergency protocol responses.

Bulk backlog scanner that analyzes the entire finans codebase vs CLAUDE.md, identifies ALL gaps, and generates a comprehensive, prioritized, numbered task backlog. Uses broad→narrow pattern.

Professional skill creation with research-driven workflow and automated validation. USE WHEN: Creating new skills, validating existing skills, deciding between Skills vs Subagents, migrating documents to skills, or running individual validation tools. PRIMARY TRIGGERS: "create skill" = Full creation (12 steps with research + execution planning) "validate skill" = Validation workflow (steps 3-8) "Skills vs Subagents" = Decision workflow (step 0) "convert doc to skill" = Migration workflow "estimate tokens" = Token optimization "security scan" = Security audit WORKFLOW COMPLIANCE: Structured workflows with validation checkpoints. Research phase (Step 1c-1d) ensures skills based on proven approaches. DIFFERENTIATOR: Research-driven creation. Web search (3-5 queries) before building. Multi-proposal generation. 9 automation scripts. Quality 9.0+/10. REUSED: Anthropic's init_skill.py and package_skill.py (production-tested).

查询计量经济学RAG知识库。当用户输入以"rag："开头时，LLM会使用Python查询Bruce Hansen计量经济学教材的RAG数据库，返回相关文档内容。

This skill should be used when describing patterns or anti-patterns for detection by LLM agents across any domain (code analysis, business processes, security audits, UX design, data quality, medical diagnosis, etc.). Uses narrative storytelling structure ("The Promise" → "The Betrayal" → "The Consequences" → "The Source") to achieve 70% faster pattern identification compared to checklist or formal specification approaches. Triggers when creating pattern descriptions for any systematic analysis, detection tasks, or when delegating pattern-finding to sub-agents.

Write maximally terse agent prompts from scratch. Use when creating new agent specs, command prompts, or instruction sets. Teaches structure-first composition with compression-by-default patterns.

Comprehensive guide for creating by-example tutorials - code-first learning path with 75-90 heavily annotated examples achieving 95% language coverage. Covers five-part example structure, annotation density standards (1-2.25 comments per code line PER EXAMPLE), self-containment rules, and multiple code blocks for comparisons. Essential for creating by-example tutorials for programming languages on educational platforms

Creates complete Claude Code plugins with proper structure, configuration, and best practices. Handles plugin.json metadata, slash commands, agent configurations, event hooks, and MCP server integration. Use when building Claude Code plugins, extending Claude Code capabilities, creating custom commands or agents for Claude Code, or setting up plugin project structure.

Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.

Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project

Expert in storage agreements for storage lockers and ancillary storage space in commercial buildings (typically month-to-month, simplified terms). Use when tenant needs additional storage beyond leased premises, reviewing storage locker terms, negotiating storage rates and use restrictions, analyzing month-to-month vs fixed-term storage, evaluating storage-only agreements, or comparing storage agreements to full lease terms. Key terms include storage locker, ancillary storage space, month-to-month, storage-only use, no business operations, simplified rent structure, minimal services, as-is condition, short notice termination

AI Agent development specialist for Novel-Engine multi-agent system.

Save and retrieve memories or embeddings via the repo helpers or API. Use when working with embedding config or memory storage.

Creates a frontend controller action in Magento 2 for the storefront. Use when building custom frontend pages, AJAX endpoints, form submission handlers, or API-like endpoints for JavaScript.

Scans and refactors deprecated Magento 2 controller patterns to modern HTTP verb interfaces. Use when modernizing controllers that extend deprecated Action base class or need PHP 8.3+ compatibility.