让 Agent 学会更多事

Terraform 部署实战踩坑指南，提供对常见运维陷阱（如 provisioner 时序竞争、SSH 连接冲突、DNS 记录重复、卷权限问题、数据库初始化遗漏、Caddyfile 硬编码域名等）的根因分析及可直接复制的修复方案。当用户编写 null_resource provisioner、搭建多环境配置、排查 terraform apply 后容器持续重启或不健康、使用 cloud-init 初始化实例，或遇到 terraform plan/apply 报错、provisioner 执行失败、基础设施漂移、TLS 证书错误以及 Caddy/网关配置问题时，此技能将被激活。

生成太阳轨迹图，计算实时太阳位置，分析建筑阴影投射范围与全年日照时数，并提供热舒适度评估，适用于建筑设计与场地环境分析。当用户询问太阳位置、请求绘制太阳轨迹、分析建筑阴影、计算全年日照时间、评估热舒适度或进行地形阴影分析时触发。

帮助用户编写和优化 SQL 查询，包括将自然语言转换为 SQL、提供查询优化建议以及解读 EXPLAIN 执行计划。当用户需要 SQL 相关帮助时触发，例如直接请求“自然语言转SQL”、“帮我优化这条SQL”、“解释一下这个执行计划”，或提及关键词如 NL2SQL、SQL优化、慢查询、索引建议、全表扫描、SQL调优，以及支持 SQLite 和 PostgreSQL 数据库时。

按 CVPR、ICCV、NeurIPS、ICML、ACL、ICLR 等顶级会议惯例撰写、排版与呈现科研论文的结构化指南。覆盖全流程：分章节起草、图表设计、LaTeX 排版、叙事逻辑与投稿前打磨。适用于撰写、修改或将手稿排版成 camera-ready 或预印本 PDF。

SaaS financial health advisor. Use when a user shares revenue or customer numbers, or mentions ARR, MRR, churn, LTV, CAC, NRR, or asks how their SaaS business is doing.

创建复古科技艺术风格的视觉内容，包括图像、插画与设计文档。覆盖 Synthwave、Vaporwave、Cyberpunk、复古漫画与复古未来主义美学。适用于霓虹网格风景、像素艺术、蒸汽波场景、CRT 与半调效果、配色方案与字体系统，服务于 80/90 年代科技黑色主题项目。

Create retro tech art style visual content including images, illustrations, and design documents. Covers Synthwave, Vaporwave, Cyberpunk, retro comics, and retro-futuristic aesthetics. Use for neon-grid landscapes, pixel art, vaporwave scenes, CRT and halftone effects, color palettes, and typography systems for nostalgic 80s/90s tech-noir projects.

Transforms raw meeting materials (transcripts, notes, chat logs) into structured minutes by automatically extracting agenda topics, discussion highlights, decisions, and action items with owners and deadlines. Use when a user provides a transcript, notes, or chat log and asks to create meeting minutes, summarize a meeting, extract action items, recap a discussion, or clean up a transcript.

Generates an interactive HTML user story map visualizing product requirements in an Epic → Feature → Story structure, with MoSCoW priority tagging and Release swimlane grouping. Trigger when the user mentions story mapping, backlog visualization, MoSCoW priority, release planning, or asks to organize requirements into a story map.

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 agent's capabilities with specialized knowledge, workflows, or tool integrations.

Systematically reviews code for SQL injection, XSS, SSRF, broken access control, cryptographic failures, and other common OWASP Top 10 vulnerabilities, providing vulnerable code examples and ready-to-use remediation guidance. Trigger this skill when users ask for a security review, vulnerability scan, or penetration testing assistance, or mention keywords like OWASP, SQL injection, XSS, code audit, or security checklist.

Structured guidance for composing, formatting, and presenting scientific research papers for top-tier venues (CVPR, ICCV, NeurIPS, ICML, ACL, ICLR, etc.). Covers the full workflow: section-by-section drafting, figure and table design, LaTeX typography, narrative logic, and submission-ready polishing. Use to write, revise, or format a manuscript into camera-ready or preprint PDF.

Turn any deep report/research document into a McKinsey/GS-grade interactive research website — theme-native visual grammar, editorial typesetting, four-state animated cover, signature chart library, every number drillable, persistent right-rail dashboard. Use when the user asks for an "interactive research report site / interactive report / turn a report into a website / data-visualization report". Zero-build vanilla JS; delivers a multi-file site plus a single-file version that opens over file://.

Automate browser interactions via CLI commands to navigate web pages, extract data, take screenshots, fill forms, and interact with web apps. Supports remote sessions with CAPTCHA solving and anti-bot stealth for scraping protected sites. Trigger when the user asks to browse websites, scrape data, or automate clicks on any page.

Builds weighted scoring decision matrices for technology selection, vendor evaluation, and multi-criteria option comparisons. Guides you through defining criteria, assigning weights, scoring options, and validating results with sensitivity analysis. Trigger when users ask about decision matrices, weighted scoring, comparing options, vendor selection, or build vs. buy choices.

Tools for building modern React webapps with TypeScript, Tailwind CSS and shadcn/ui. Best suited for applications with complex UI components and state management. Supports optional templates for specialized requirement.

巴菲特/格雷厄姆风格的价值投资评估技能，从护城河、管理层、财务、估值四大维度共20个细项对目标公司进行系统性评分（满分100分），并给出综合评级与投资建议。当用户需要进行价值投资分析、基本面打分、护城河或管理层评估、财务健康度检查、估值判断、安全边际计算，或使用诸如“分析一下XX的基本面”、“用巴菲特的方法评估一下这家公司值不值得投”等表述时触发。

将「投资交易策略描述」（含事件驱动、选股、组合）转成可运行的「回测代码」，输出回测结果、可视化图表和分析报告。当用户描述买卖条件、事件后收益、股票池筛选回测等量化场景时触发。

Generate beautiful interactive timeline HTML pages from JSON data, with vertical, horizontal, or dual-side layouts, collapsible details, and custom colors. Ideal for project milestones, company histories, or resumes. Triggered when a user mentions 'timeline', 'history of events', 'project milestones', 'release log', or asks to visualize a chronological sequence of data.

This skill should be used when establishing comprehensive QA testing processes for any software project. Use when creating test strategies, writing test cases following Google Testing Standards, executing test plans, tracking bugs with P0-P4 classification, calculating quality metrics, or generating progress reports. Includes autonomous execution capability via master prompts and complete documentation templates for third-party QA team handoffs. Implements OWASP security testing and achieves 90% coverage targets.