Explorar skills

社交关系距离计算器：输入两个公开社交主页 URL（X 和/或 LinkedIn）， 自动找出双方之间所有真实可达的 2 跳和 3 跳连通路径（基于双向互动证据， 不靠图论臆想），输出一份 evidence-grounded 的中英双语 HTML 报告。 核心承诺：找不到真路径就如实说"无连通"，绝不编造。 Use this skill whenever the user wants to figure out how to reach someone, whether two people are connected, who their mutual contacts are, what their social distance is, who could broker an introduction, or how their social graphs overlap — even

Silently watches your work. When you repeat manual tasks 3+ times, suggests a project to automate it. Also /vibe-spark for personalized project ideas based on your context.

Delegate coding tasks to OpenAI Codex CLI. Supports presets (turbo/balanced/quality/max) or custom model+effort selection. Use when user wants to leverage GPT-5.5/Codex models for code analysis, refactoring, security audits, or complex transformations. Also covers MCP server management and advanced CLI features.

Context-aware Figma design refinement with AIDesigner integration. Reads designs/ for project identity, classifies modifications into Level A (property) and Level B (structural), applies via Figma MCP with optional AIDesigner-powered improvements, and verifies with 3-layer screenshot validation + Before/After comparison. Use after requirements_designer Phase 5 to polish UI designs. Triggers: "figm

Analyze one or more projects by identifying the top 5 user personas across the full spectrum from technical to non-technical, surfacing gaps each persona hits, and synthesizing what to build next — including breakthrough moves that elevate the project to a new level. Use this skill whenever the user asks "what should I build next", "what do my users want", "what's missing from this project", "who

领导问"这是AI写的？"——这个问题每个打工人都怕。 45条中文AI痕迹规则，改完原文格式一字不动，只换掉那股机器味。 粘贴进来就能改，不用配置不用学。

Generate interactive, image-rich HTML travel itinerary pages with distance verification, real landmark photos, countdown timers, and mobile-first design. Trigger when user asks to plan a trip, create a travel itinerary, or make a trip page/website.

Interact with the Claw Agent Protocol (CAP), a lightweight MCP server providing canonical, real-time access to personal data for AI agents. Use when working with user personal data across Gmail, Calendar, Notion, Slack, tasks, contacts, or any CAP-connected data source. Enables structured querying, data organization, and task-oriented views of user information.

Wiki.js 文档中心管理助手。通过 GraphQL API 管理公司 AI 应用文档中心。 支持项目文档的自动维护、读取、搜索和组织。每个项目拥有独立的文档空间（基于路径前缀）。 使用场景： - 创建/更新/删除项目文档 - 搜索和读取文档内容 - 同步代码库文档（README、CHANGELOG等）到 Wiki.js - 管理项目文档结构和导航 - 查看文档修改历史 触发关键词：wiki、文档中心、项目文档、wikijs、文档同步

Use when reviewing an AI-generated implementation plan before execution, when handed a plan to approve, or when checking if a plan is ready to act on

Use when converting local documents with docling-skill into agent-ready source.* sidecar outputs, especially PDF, DOCX, PPTX, XLS, XLSX, CSV, HTML, TXT, Markdown, or common image inputs that need manifest-gated Markdown, structured Docling JSON, image sidecars, OCR remediation, or local document pre-ingestion for downstream knowledge-base workflows.

Use when building with any AI SDK or API — Anthropic, OpenAI, or Google. Fetches current documentation in real time before answering, so stale training data doesn't cause bugs. Trigger on: model selection, tool use, function calling, streaming, prompt caching, batch processing, SDK setup, or any AI API integration, planning, debugging, or code review.