技能列表

Integrate REVEL, CADD, PolyPhen scores to predict variant pathogenicity

AI-driven visual/UI design generation with Impeccable design system. Generates 3 distinct design variations from a prompt with built-in scenario materials, design system references (typography, color, spatial, motion, interaction, responsive, UX writing), and anti-AI-slop quality gates. Supports variation actions: Vary strong/subtle, Distill, Change style, Remix colors, Shuffle layout, Polish, Critique, Extract tokens, See other views. Exports to HTML or React. Triggers on: "design options for X

Query and annotate gene variants from ClinVar and dbSNP databases. \n\

Build DCF models and run comparable analysis for company valuation. Use when modeling cash flows, benchmarking peers, projecting growth, or pitching.

Validate emails, URLs, phones, dates, and custom patterns. Use when sanitizing input, verifying form fields, checking formats, or enforcing rules.

Generate UUIDs, short IDs, and nano IDs. Use when creating database keys, minting session tokens, generating unique filenames, or producing batch IDs.

生成 UUID（通用唯一标识符）。使用场景：(1) 需要为数据库记录、API、文件生成唯一 ID，(2) 批量生成多个 UUID，(3) 需要无连字符的紧凑格式，(4) 验证字符串是否为有效 UUID格式。

Sends user-authorized transactional email via uSpeedo API with ACCESSKEY credentials (env preferred). Before SendEmail, calls GetSenderList to resolve SendEmail (default first enabled sender; user may override). Requires explicit confirmation of sender, recipients, subject, and content before sending.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when the user wants to discover, track, sync, or query news, RSS, social, financial, or other external sources through agent-data-cli and any configured source workspace such as agent-data-hub.

定义需要征求用户同意才能执行的操作规则。当任务涉及修改系统配置、安装/变更组件、执行可能影响系统运行的操作时，必须参考此skill确认是否需要先获得用户同意。特别适用于：系统管理任务、配置变更、skill安装/修改、定时任务管理、数据清理、网络配置、版本更新等场景。

A universal MCP-compatible tool/skill that empowers ANY AI Agent to natively call the local Anthropic Claude Code CLI. Ideal for code refactoring, large scale code generation, terminal execution, bash shell commands, running tests, local environment modification, and bypassing token limits.