AI & Agents Agent Skills

Multi-mode code and skill review for controlling drift as capability surface grows.

Build or audit an evidence-driven SGLang Day-0 support program for a new LLM, VLM, MoE, hybrid-attention, or speculative-decoding model.

Artifact handoff protocol for two-pipeline architecture

Create new skills, modify and improve existing skills, and measure skill performance for Claude Code.

Meta-skill for generating new skills with proper format and structure.

Expert guidance for crafting effective prompts in Google Stitch, the AI-powered UI design tool by Google Labs.

Activate this skill whenever you need to extend, maintain, or debug the two-tier tool discovery system — even if the user doesn't…

Apply plugin knowledge base updates to an existing generated system.

Show the plugin source — name, version, and repo URL.

Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator

Add descriptions for new models from the HuggingFace router to chat-ui configuration.

Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator

Multi-agent orchestration enforcement for /team command.

Agent skill for swarm - invoke with $agent-swarm

Create and operate Markdown-native Mission workflows for multi-agent engineering collaboration in Mexus or similar CLI-agent workbenches.

7 agentic design patterns with decision tree for choosing the right pattern for each agent type

防止 AI 幻覺，確保分析程式碼或提出建議時給出以證據為基礎的回應。 Use when: 分析程式碼、提出建議、提供選項，或使用者詢問把握度／確定性時。 Not for: 撰寫 AI 指令檔本身——請用 /ai-instruction-standards；審查具體的…

AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and…

Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions.

Structured multi-provider AI debates between Claude and available advisors — use for critical decisions

Optimizes project structures and documentation to maximize AI collaboration efficiency and reduce token consumption.