Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Iteratively improve a skill using subagent consensus and simulation testing. Use when a skill is producing bad outputs, has unclear instructions, or you want to stress-test it before shipping. Runs proposal evaluation and scenario simulation rounds with multiple agents to surface issues and build confidence.
Internal helper contract for calling the codex-companion runtime from Claude Code
Use when turning a captured human demonstration (a Trail Runner demonstration bundle: demo.yaml + actions.ndjson + per-action screenshots and view hierarchies) into a durable, independently runnable Trailblaze trail. Trigger when a prompt hands you a demonstration bundle directory and asks you to author, generate, or produce the trail for it - or to add another platform's recordings to an existing trail from a new demonstration.
Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), `user`, `workspace`, or `ws`.
Generate a complete MCP server project in Python with tools, resources, and proper configuration
Trae 项目规范化配置专家。用于快速初始化 Trae 项目配置文件、生成项目规则、用户偏好设置和 Skill 模板。当用户需要：(1) 初始化新项目的 Trae 配置 (2) 生成 .trae 目录结构 (3) 创建 USER_PREFERENCES.md 用户偏好文件 (4) 创建 project_rules.md 项目规则文件 (5) 创建新的 Skill 模板 时使用此 Skill。
为 Catpaw 项目开发、修改、补全或评审插件。用户只要提到 Catpaw 插件、监控检查、plugins 目录下的新插件、补充 agent 注册、生成 conf.d 示例、实现 Gather/Init/partials、对照现有插件仿写或重构插件时，都应使用这个 skill。
Instructs AI coding agents to invoke CodeGuard MCP Server security rules before writing or reviewing code.
Creates multi-step input chains for conversation flows using the telegram-bot DSL. Use when building simple multi-step dialogs without wizard state persistence, or when inputChain is preferred over @WizardHandler.
Generate tool-specific configuration files (Cursor rules, Copilot instructions, Windsurf rules) from the .context/ documentation. Use when setting up a project for a specific AI coding tool.