Skills
100,696 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use this skill whenever you need to verify that a web UI actually works the way it's supposed to — clicking through flows, asserting state, catching console errors, taking screenshots across multiple viewports for visual review. Triggers on phrases like "驗證網頁", "verify the site", "Playwright tests", "visual regression", "RWD verification", "screenshot comparison", "responsive check", "console error check", "看看手機版有沒有壞", "視覺驗證", "Playwright 測試", "截圖比對", "RWD 驗證", "驗 sidebar", "看 console 有沒有錯", or any post-change moment where the user wants to know "did I break anything?". This is the runtime-behaviour verifier — use `web-content-audit` instead if the question is about file/data consistency rather than rendered behaviour.
Configure fastlane + GitHub Actions for iOS projects to automatically build and upload to TestFlight on pushes to the main branch. Reference implementation: the Cathier project. Triggers: "testflight", "fastlane", "auto build", "CI TestFlight", "/wjs-publishing-testflight".
WordPress CI/CD and release engineering review guidance. Use when reviewing GitHub Actions, deployment pipelines, Composer/npm build steps, plugin/theme packaging, release automation, secrets handling, SVN deploy flows for WordPress.org, staged rollouts, rollback plans, or when user mentions CI, CD, release pipeline, GitHub Actions, deployment workflow, build artifact, plugin zip, or release engineering. Helps review build reproducibility, packaging correctness, secret boundaries, deployment safety, rollback readiness, and WordPress-specific release pitfalls.
WordPress WP-CLI and operations review guidance. Use when reviewing WP-CLI commands, search-replace plans, multisite operations, cron or cache maintenance, deployment scripts, operational runbooks, CLI automation, or when user mentions "WP-CLI", "search-replace", "multisite ops", "wp cron", "wp db", "deployment script", "maintenance task", "CLI command", or "ops review". Helps review command safety, environment targeting, multisite scope, automation reliability, and operational blast radius in WordPress codebases and runbooks.
Writes and edits prose for people in a plain, conversational, short house style with no em dashes. Use when the user says "write this up", or when drafting or revising documentation, READMEs, explanations, blog posts, or other human-facing prose. Not for prompts written for agents; use writing-system-prompts or composing-agent-prompts.
Drafts technical design docs that are directionally correct, not perfect, deciding one-way doors, deferring two-way doors, and naming unknowns. Use when the user says "write a design doc", or when asked to write, draft, or author a design doc, RFC, tech spec, or architecture proposal. Not for reviewing a design; use reviewing-design-docs.
X/Twitter public sentiment research for recent market, company, product, or community discourse. Use when the brief asks what people are saying on X, Twitter sentiment, CT sentiment, public opinion, expert posts, or social reaction around a stock, sector, company, product, or market event.
Break down and lay out user-provided articles, notes, tutorials, SOPs, checklists, web content or local documents into 3:4 multi-page Xiaohongshu image-text HTML. By default generates a complete self-contained HTML with more than 6 pages at 1080×1440 each that can be screenshotted page by page; supports 62 brand design styles and, before starting, offers the user matching style candidates and 6/7/8/9-page options to choose from. For requests such as "make Xiaohongshu image-text", "turn content into Xiaohongshu cards", "generate multi-page Xiaohongshu HTML", "make 3:4 knowledge cards", "lay out an article into a Xiaohongshu image set", "make tutorial image-text", "make screenshottable HTML".
Integrate OpenAI Agents SDK with You.com MCP server - Hosted and Streamable HTTP support for Python and TypeScript. - MANDATORY TRIGGERS: OpenAI Agents SDK, OpenAI agents, openai-agents, @openai/agents, integrating OpenAI with MCP - Use when: developer mentions OpenAI Agents SDK, needs MCP integration with OpenAI agents
Zeng Guofan's thinking framework and self-management philosophy. Distilled from in-depth research across 30+ sources, including 《曾国藩家书》《挺经》《冰鉴》、《清史稿·曾国藩传》, 唐浩明's 《曾国藩》 trilogy, and 张宏杰's 《曾国藩传》, into 5 core mental models, 7 life heuristics and a complete expression DNA. Purpose: as a thinking advisor, analyze self-management, leadership, breaking through adversity and interpersonal relationships from Zeng Guofan's perspective. Use when the user mentions 「用曾国藩的视角」「曾国藩会怎么看」「曾国藩模式」「zengguofan perspective」. Also applies to: self-discipline struggles, team management, surviving adversity, clumsy effort vs clever methods, talent identification. Even if the user only says 「怎么坚持下去」「怎么带团队」「笨办法」「结硬寨打呆仗」「自我管理」 it can trigger. Do not trigger when the user only asks general questions such as 「这个决策靠谱吗」「帮我想想」— activate only when it concerns Zeng Guofan's core methodology such as self-cultivation, leadership training, breaking through adversity, or winning through clumsiness.
ZenTao bug management - query bug lists, view bug details, create bugs, update bug status, resolve bugs, and close bugs. Triggered when the user says: "查询 bug", "有哪些 bug", "bug 列表", "查看 bug", "创建缺陷", "报告 bug", "登记 bug", "缺陷", "bug 数量", "待处理 bug", "bug 状态", "禅道 bug".
Route Zephyr entries from any document to their proper bake logs, with deduplication, reverse chronological ordering, and move or copy semantics. Use when asked to route Zephyr entries, move entries out of a log to where they belong, or clean up a document holding mixed entries.
Usage guidelines for the Zerone CLI toolkit. Covers four main functions: API interface code generation (zerone api), font icon management (zerone font_grabber), frontend project scaffolding (create-zerone), and work log generation (zerone log). Use this skill for the following scenarios: generating API modules, generating interface code, updating interfaces, pnpm api, adding backend interface modules, iconfont font icons, updating icons, pnpm font, using icon icons, creating frontend projects, pnpm create zerone, scaffolding initialization, daily work reports, weekly reports, monthly reports, zerone log — and even when the user merely mentions keywords such as "接口", "图标", "新建项目", or "日报周报".
Use when you need to create images or image prompts with AI — personal brand images, logos, campaign key visuals, daily post images, editorial, infographics, web mockups, quote graphics. Reads brand identity from context, then writes prompts, generates images, or exports prompts for MidJourney, DALL-E, Imagen, Leonardo. Has a mode that takes reference images and returns a copy-pasteable master prompt. Activates when the user mentions "thiet ke anh", "lam logo", "ve banner", "prompt MidJourney", "tao key visual", "lam anh giong anh nay", "gen anh AI", "doi mau thuong hieu tren anh". Not for — writing briefs for designers, use skill 42-brief-hinh-anh; asset workflows for a whole campaign, use skill 41-campaign-asset-list; AI avatar videos, use skill 24-ai-avatar-production; interactive UI wireframes, use web-prototype; animation, use motion-frames.
Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, and CLS prevention. Use when user says "image optimization", "alt text", "image SEO", "image size", or "image audit".
Comprehensive academic textbook chapter writing system for medical/scientific content. Use when the user wants to: (1) Write a full textbook chapter (5,000-15,000 words) on any medical/scientific topic, (2) Generate a detailed table of contents with section word counts, (3) Research topics via PubMed MCP and compile 20-30 references, (4) Write section-by-section with proper citations in Vancouver format, (5) Create publishable academic content with Eric Topol-inspired voice and authentic human prose, (6) Get approval at TOC stage before writing begins, (7) Export well-structured chapters for textbook publication.
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, Microsoft, and Apple Ads. Analyzes competitor ad copy, creative strategy, keyword targeting, estimated spend, and identifies competitive gaps and opportunities. Use when user says competitor ads, ad spy, competitive analysis, competitor PPC, or ad intelligence.
Brand DNA extractor for paid advertising. Scans a website URL to extract visual identity, tone of voice, color palette, typography, and imagery style. Outputs brand-profile.json to the current directory. Run before /ads create or /ads generate for brand-consistent creative. Triggers on: brand DNA, brand profile, extract brand, brand identity, brand colors, what is the brand voice, analyze brand, brand style guide.
A/B test design and experiment planning for paid advertising. Structured hypothesis framework, statistical significance calculator, test duration estimator, sample size calculator, and platform-specific experiment setup guides (Meta Experiments, Google Experiments, LinkedIn A/B). Use when user says A/B test, split test, experiment design, test hypothesis, statistical significance, sample size, or test duration.
Butler Afu — turns an Obsidian inbox into a living Wiki, then into this week's todo cards and weekly calendar: Inbox -> Wiki -> Todo Card -> Calendar as one line. Local-first, Markdown is the single source of truth, inbox originals are never rewritten, and all import/scheduling/discard/compile operations are logged and reversible. Trigger words include but are not limited to: organize my Obsidian inbox, remind me every day to process my Obsidian inbox, inbox zero, compile this batch of material into a Wiki, generate this week's todos from notes, schedule todo cards into the weekly calendar, Afu help me sort out my vault. It should also trigger even if the user only says "my Obsidian has piled up a bunch of unprocessed stuff". Do not use for: ordinary todo management not involving an Obsidian/Markdown vault (use a general todo tool); rewriting, polishing or summarizing note originals (Afu only organizes location and does not touch the original text); non-Markdown knowledge bases such as Notion.
Evaluate, test, and track an AG2 Agent offline. Build a Suite of tasks, run the agent with run_agent, and grade answers with prebuilt scorers (final_answer_matches, tool_called, no_tool_errors, token_budget) or a custom @scorer — including the agent_judge LLM judge. Read the RunResult scorecard (pass_rate, score_stats, value_counts), gate it in CI with deterministic TestConfig cassettes, persist to store_dir and diff runs to catch regressions, and grade existing traces with evaluate_traces. Use when the user wants to evaluate, test, grade, or benchmark an agent, build a CI or regression gate, or score correctness, tool use, cost, or quality. To compare builds head-to-head or on a leaderboard, see ag2-eval-comparison.
Build a multi-agent AG2 network — load this whenever two or more `Agent`s need to interact. The network is the standard multi-agent pattern in `ag2`. Covers `Hub.open`, `LocalLink`, `HubClient.register`, `Passport`, `Resume`, channel lifecycle (PENDING → ACTIVE → CLOSING → CLOSED), the two 2-party channel adapters (`consulting` for strict 1Q1R and `conversation` for free-form), the `Envelope` wire format, audience routing, `wait_for_channel_event`, WAL replay via `hub.read_wal`, and the five channel-close routes. Entry point — routes to `ag2-network-discussion` (N-party round-robin), `ag2-network-workflow` (declarative orchestration / GroupChat migration), `ag2-network-governance` (rules / expectations / audit), or `ag2-network-tools-and-views` (custom handlers / peer discovery) for deeper needs.
Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting .NET (C#) applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.
Design websites and applications that AI agents can consume, navigate, and interact with. Use when building any site, app, or product that agents will use as an end-user — not just crawl or index. Covers semantic structure, accessibility-as-agent-interface, machine-readable data, API-first patterns, and the emerging protocols (llms.txt, MCP, NLWeb, A2UI) that make sites agent-ready. Triggers on: agent-friendly, agent-readable, agent-accessible, AX, agent experience, agentic web, dual-interface, machine-readable, llms.txt, MCP integration, NLWeb, accessibility tree, ARIA for agents, structured data, JSON-LD, Schema.org, API-first design, build for agents, agent-ready.
Provides AI agents with a single-file HTML componentization spec and template system based on the minimalist modern aesthetic of shadcn/ui. Always use this skill when the user asks to "generate an HTML page/web page", "front-end visualization dashboard/board", "interview/analysis/test report", "comparison matrix/option comparison", "turn review results into a visualization page", "code review report / turn a diff into a visual review page", "don't output a markdown wall/text wall", "turn analysis results into an interactive single-file web page", and similar scenarios. Zero build, zero npm, strictly no external CDN (no blank screen risk when offline), pure native HTML/CSS/SVG, supports dark mode and instant open on double-click.
Read-only MongoDB CLI. Use when exploring databases, collections, schemas, or indexes, querying documents (find, get by id, count, sample, distinct, aggregate), checking database or collection statistics, or managing MongoDB connections and credentials — including identity-provider login (MONGODB-OIDC, workforce/workload identity federation, SSO).
Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.
Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing). Actions: transcribe, analyze, extract, caption, detect, segment, generate from media. Keywords: Gemini API, audio transcription, image captioning, OCR, object detection, video analysis, PDF extraction, text-to-image, multimodal, speech recognition, visual Q&A, scene detection, YouTube transcription, table extraction, form processing, image generation, Imagen. Use when: transcribing audio/video, analyzing images/screenshots, extracting data from PDFs, processing YouTube videos, generating images from text, implementing multimodal AI features.
Perform security inspection and monitoring for Alibaba Cloud WAF (Web Application Firewall), covering CNAME-based domain access, hybrid cloud access, and cloud product access assets. Supports querying Web attacks, CC attacks, Bot attacks, API security events, traffic analysis (QPS/bandwidth), HTTP status code anomalies (4xx/5xx period-over-period), protection status, certificate expiry, and instance asset inventory. Use this Skill when users need WAF security inspection, protection status checks, attack event queries, traffic anomaly investigation, or to confirm whether WAF products are provisioned. Triggers: "WAF inspection", "WAF security check", "Web attack query", "traffic anomaly", "certificate check"
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.