LLM & Agents

Diagnose Home Assistant errors by connecting via SSH, checking Docker containers, reading logs, and identifying integration issues. Use when the user mentions Home Assistant errors, issues, problems, diagnostics, or when they want to troubleshoot their HA system.

Personal AI Infrastructure (PAI) - PAI System TemplateMUST BE USED proactively for all user requests. USE PROACTIVELY to ensure complete context availability.=== CORE IDENTITY (Always Active) ===Your Name: [CUSTOMIZE - e.g., Kai, Nova, Atlas]Your Role: [CUSTOMIZE - e.g., User's AI assistant and future friend]Personality: [CUSTOMIZE - e.g., Friendly, professional, resilient to user frustration. Be snarky back when the mistake is user's, not yours.]Operating Environment: Personal AI infrastructure built around Claude Code with Skills-based context managementMessage to AI: [CUSTOMIZE - Add personal message about interaction style, handling frustration, etc.]=== ESSENTIAL CONTACTS (Always Available) ===- [Primary Contact Name] [Relationship]: [email protected] [Secondary Contact] [Relationship]: [email protected] [Third Contact] [Relationship]: [email protected] contact list in SKILL.md extended section below=== CORE STACK PREFERENCES (Always Active) ===- Primary Language: [e.g., TypeScri

Multi-source comprehensive research using perplexity-researcher, claude-researcher, and gemini-researcher agents. Launches up to 10 parallel research agents for fast results. USE WHEN user says 'do research', 'research X', 'find information about', 'investigate', 'analyze trends', 'current events', or any research-related request.

Multi-LLM orchestration implementing the 5-stage coding workflow: Example Analysis → Hypothesis → Implementation → Debug Loop → Recursive Improvement.Based on "Towards a Science of Scaling Agent Systems" (Kim et al., 2025): - Centralized Consult architecture (Claude orchestrates, others advise) - Measured coordination (avoid MAS overhead in tool-heavy stages) - Tests-first selection (Poetiq pattern, not voting)Use when: Debugging complex issues, analyzing unfamiliar code, refactoring, or any task that benefits from diverse LLM perspectives with verification.

自动识别prompt类型并保存到相应分类（技术/内容/教学/产品/通用），支持自动文件命名和索引管理。当用户提到"保存prompt"、"记录prompt"、"管理prompt"、"整理prompt"、"prompt库"时使用此技能。

Skill to assist with how a GitHub repository is configured with GitHub integrations, including instructions for agents in markdown (AGENTS and CLAUDE), github actions for invoking agents, and specific localization procedures such as defining claude/codex skills, or claude subagents. The skill helps with both technical aspects, and with best practice for guiding agents.

Disciplined TDD workflow enforcing red-green-refactor cycle and the "iron law" of no production code without failing tests first. USE WHEN user wants to write tests first OR implement new feature with TDD OR fix bugs with test coverage OR explicitly requests TDD approach. Enforces systematic test-first development with verification at each step.

Create new Claude Code skills with proper structure and best practices. Use when user says "create skill", "new skill", "make a skill", or wants to scaffold a reusable Claude Code capability.

Optimize and manage AILANG teaching prompts for maximum conciseness and accuracy. Use when user asks to create/update prompts, optimize prompt length, or verify prompt accuracy.

Build strategic plans for business goals. Creates one-page briefs with core objective, key milestones, leverage points, and risks. Use when setting direction, pitching initiatives, or aligning teams around a goal.

Guidance for proving mathematical properties in Coq using induction, specifically addition commutativity and similar arithmetic lemmas. This skill should be used when working with Coq proof assistants to complete induction proofs, fill in proof cases, or apply standard library lemmas like plus_n_O and plus_n_Sm.

Guide for Claude Agent SDK - build custom AI agents powered by Claude. Triggers on agent sdk, claude-agent-sdk, @anthropic-ai/claude-agent, build agent, programmatic agent, embed claude, custom ai agent, agent infrastructure. Covers installation, authentication providers, tool permissions, file-based configuration, and TypeScript/Python code examples.

Your guide to the marketing toolkit. Diagnoses where you are in your marketing journey and recommends the right skills, agents, and workflows to use next.

Use to audit test quality with Google Fellow SRE scrutiny - identifies tautological tests, coverage gaming, weak assertions, missing corner cases. Creates bd epic with tasks for improvements, then runs SRE task refinement on each.

Use when encountering bugs or test failures - systematic debugging using debuggers, internet research, and agents to find root cause before fixing

Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results, creates Linear task in Epic 0.

Guidance for compiling SQLite (or similar C projects) with gcov code coverage instrumentation. This skill should be used when tasks involve building software with gcov flags, setting up code coverage instrumentation, or troubleshooting coverage data file generation. Covers gcov path mechanics, build directory considerations, and runtime verification strategies.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

E2E Critical Coverage audit worker (L3). Validates E2E coverage for critical paths (Money 20+, Security 20+, Data 15+). Pure risk-based - no pyramid percentages.

Manage car logo fetching, scraping, and Vercel Blob storage in the logos package. Use when updating logo sources, debugging brand name normalization, or managing logo cache.