Explorar skills

学者问道：为人文社科学者构建可调用的思想分析工具。 输入学者名/研究领域，自动多语言采集著作、二手文献、传记与学术争论， 提炼出可在你的研究中调用的"分析镜片"——而不是聊天机器人。 默认输出第三人称分析模式，对话/角色扮演作为 opt-in。 触发词：「学者问道」「问道于XX」「蒸馏学者」「构建XX的分析镜片」 「XX的研究方法」「XX视角」「scholar-wendao」「XX-perspective」「为XX建一个 skill」。 模糊触发：「我研究XX，需要某种分析框架」「有没有一种学者视角能帮我看待这个材料」。

Visual design review of an HTML file or URL using Playwright MCP. Opens the page in a real browser, captures desktop / tablet / mobile screenshots, audits typography, contrast, rhythm, spacing, hierarchy, color, and alignment, and proposes concrete fixes. With user consent — applies them in place. Trigger when the user says "review this design", "how does this look", "what's wrong with the layout"

Fetch a public Polymarket wallet's activity, positions, and order-book context, then summarize behavior, exposure, and market focus from a JSON snapshot. Use when analyzing a public wallet or bot without generating copy-trade instructions or reverse-engineered parameter packs.

Gridea Pro 博客主题开发专家。支持 Jinja2 (Pongo2)、Go Templates、EJS 三种模板引擎。提供主题脚手架生成、语法验证、渲染测试、避坑指南和完整的模板变量参考。当用户要求创建 Gridea 主题、修改 Gridea 主题、修复主题渲染问题、学习 Gridea 主题开发、从 EJS/Hugo 迁移主题时触发。触发关键词：Gridea 主题、博客主题、theme 开发、模板语法、主题配置、theme config。

Use when 需要多文件代码实现并要求异源模型（Claude + Codex）交叉审查，或架构方案需要对抗性质询验证。适用于大型编码任务的端到端协作，不适用于单文件小修改或纯数据处理。

Analyze the contents of a video. Use whenever the user provides a YouTube/Vimeo/TikTok/X/Instagram URL (including Reels) or local video file (.mp4/.mov/.mkv/.webm) and asks a question about what's in it — what was said, what was shown, who appears, when something happens, etc. Pulls the transcript from platform captions when available, otherwise transcribes locally with whisper.cpp, and extracts f

Interactive Brokers options & stock trading assistant. Provides real-time portfolio Greeks, option chain analysis, McMillan/Overby strategy recommendations, P&L statistics, Wheel strategy tracking, earnings warnings, risk simulation, and a complete toolkit for options traders. Use this skill whenever the user asks about specific options trades, position risk, buy/sell recommendations, IV environme

每日热搜 + SEO 关键词评分工具。抓取微博/百度实时热搜榜，对指定关键词做搜索热度评分， 辅助公众号/内容创作选题。 触发词：热搜 / 今日热点 / 热词 / 选题参考 / SEO评分 / 关键词热度 / 热搜雷达

Use when the user wants to autonomously search for the best AI/engineering approach across competing candidates (prompts, models, retrieval strategies, architectures, algorithms) — give it a goal + candidate arms + success threshold, it runs the experiment to a defensible ship-or-kill verdict. Autonomously handles sourcing real production data, scoring arms in parallel, diagnosing per-row, sprint-

AI governance learning, news briefings, topic explainers, and interactive quizzing. Use this skill whenever the user asks about AI regulation, AI policy, AI law, AI compliance, or AI governance — including the EU AI Act, US executive orders, NIST AI RMF, ISO/IEC 42001, state-level AI laws (Colorado AI Act, California CPPA rules, NYC LL 144), regulator guidance, enforcement actions, court rulings o

Multi-perspective code review council: advisors analyze, reviewers cross-examine, chairman synthesizes verdict. USE for: architecture decisions, security audits, tradeoff analysis, "what am I missing" questions, pre-merge deep reviews, iterative re-reviews after fixes. DO NOT USE for: simple code generation, syntax fixes, single-file refactors, or factual lookups. TRIGGERS: 'hydra', 'hydra this',

Analyzes occupancy, utilization, and presence data from any source (Wi-Fi device counts, badge swipes, sensor headcounts, camera counts, manual surveys, room reservations) to surface trends, peaks, day-of-week patterns, anomalies, and prioritized recommendations. Use when the user shares headcount, foot-traffic, badge, Wi-Fi, occupancy, utilization, or facility usage data and asks to analyze, summ