Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user or project explicitly adopts hexagonal (ports and adapters) architecture—a README, CLAUDE.md, or ADR that says so is the opt-in. Once a project has opted in, load this for every code change in it, not only architecture work—a new feature, a transport or SDK swap, a bug fix, or a small business-rule change to a function that still calls an SDK directly; load it alongside tdd, never instead of it, and follow its Before You Write Code section before editing. Implements TypeScript ports, driving/driven adapters, dependency inversion, and domain isolation. Do NOT infer hexagonal architecture from a generic adapter, interface, test seam, or isolation request in a project that has not opted in.
Hookdeck Event Gateway — webhook infrastructure that replaces your queue. Use when receiving webhooks and need guaranteed delivery, automatic retries, replay, rate limiting, filtering, or observability. Eliminates the need for your own message queue for webhook processing.
Asset preprocessing for HyperFrames compositions—text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or Whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.
Analyze customer motivations using Jobs-to-be-Done and Forces of Progress. Use when asked about jobs-to-be-done, why customers switch products, what job a product is hired for, or when analyzing the forces that drive or resist product adoption.
Use this skill whenever a question should be answered from documents stored in a LlamaCloud Index v2 knowledge base — retrieving passages, locating indexed files, or searching indexed content through the LlamaParse Platform REST API with curl. Teaches agentic retrieval — navigating an index like a file system instead of one-shot RAG.
Lovrabet runtime CLI — an AI operations suite for business scenarios. Use the lovrabet command to manage app catalogs, business roles and permissions, user-level external accounts, Service Tree business commands, API documentation discovery, dataset queries, Instant API data operations, Custom SQL/Backend Function, Personal Backend Function, file uploads, OCR text and structured-field extraction for ticket-related business documents, approval tasks and processing, scheduled tasks, Skill, knowledge bases, and runtime app-config key status checks. Triggers: 云图, lovrabet, lovrabet-cli, business roles, role members, page permissions, menu permissions, dataset permissions, user-account bind, provider external account binding, DingTalk userId binding, service tree, business service tree, api-doc, dataset, data filter, file upload, file query-url, ocr recognize, OCR recognition, ticket text extraction, ticket field extraction, invoice recognition, receipt recognition, credential recognition, attachment upload, personal-bff, approval, approvals, pending tasks, approve, reject, transfer, schedule, scheduled tasks, cron, kb, skill, sql exec, bff exec, app-config, accessKey, compress, jq.
Provider-independent motion graphics direction for AI agents producing title sequences, lower thirds, explainer graphics, product UI overlays, social ads, kinetic typography, diagrams, data callouts, brand films, and video post. Use when planning, prompting, storyboarding, specifying, implementing, reviewing, or QAing motion graphics across live footage, generated video, UI capture, data visualization, brand systems, typography, accessibility, claim integrity, runtime handoff, and iteration.
Use when the user provides a reference image and asks for reverse image prompting, scene decomposition, structural keyword extraction, composition/color/material analysis, or Chinese prompts that can generate images directly; explicitly asks to calibrate this Skill by generating a return image; or explicitly asks to inspect or update the “南鸢图片反推 Skill” itself. A normal invocation delivers only a structural breakdown, reference color palette, and copyable prompt; it is not for skipping analysis to generate an image directly, ordinary image editing, or general prompt writing without a reference image.
Dense description covering Server-Side Template Injection across Jinja2, Twig, Freemarker, Velocity, Pebble, Smarty, Mako, Handlebars, ERB, Thymeleaf, EJS, Pug. Engine fingerprinting, filter bypass, blind exploitation, WAF evasion, SSTI-to-RCE chains. Tools: tplmap. CWE-1336. MITRE T1190. Use when testing template rendering endpoints or exploiting template injection for code execution.
Use this skill when the user asks to “create a scene,” “add a new scene,” “make a menu scene,” “create a game over screen,” “add a level,” “set up scene transitions,” “create a pause screen,” “add a preloader,” “create a HUD overlay,” or needs any Phaser 4 scene created, structured, or connected to other scenes.
Master the art of podcast interviewing using NPR training methodology and Tim Ferriss's preparation techniques to draw compelling stories and insights from any guest. Use when: preparing for a podcast interview; designing questions that elicit stories, not soundbites; struggling to get guests to open up authentically; planning a new interview-format podcast; improving your interviewing technique
Create remarkable products and experiences that spread through word of mouth using Seth Godin's Purple Cow methodology Use when: **Launching a new product** and need it to stand out in a crowded market; **Differentiating your brand** from competitors who all look the same; **Escaping commodity status** where you compete only on price; **Planning a marketing strategy** with limited advertising budget; **Finding your remarkable angle** when "good enough" isn't working
Senior Python developer expertise for writing clean, efficient, and well-documented code. Use when: writing Python code, optimizing Python scripts, reviewing Python code for best practices, debugging Python issues, implementing type hints, or when user mentions Python, PEP 8, or needs help with Python data structures and algorithms.
Research how production Rails apps solve architectural problems using the Real World Rails repository. Use when the user wants to know how other apps handle something, find patterns, or compare approaches. Triggers on "rails patterns", "how do other apps", "real world rails", "research how apps do".
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered sources. Skip one file, one function, a single needle, or a one-page PDF conversion. Triggers: long context, context rot, large codebase, many files, all files, big document, multi-document, PDF, aggregate, summarize everything, codebase-wide, multi-hop, recursive, sub-agents, map-reduce.
Sets up and starts the AI Tutor project locally (environment file, dependencies, database, migrations, and dev server). Use when standing up the AI Tutor for the first time on a new machine or after a fresh clone. This is sample-project specific; adapt it when you install the AI Layer into your own project.
Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest.
Ghi và kiểm provenance (nguồn + sha256 checksum) cho skill — dùng khi 'cài skill từ ngoài', 'skill này từ đâu', 'audit nguồn skill', 'checksum skill', 'supply-chain skill', phát hiện skill bị sửa lén; bổ trợ orca-sec-scans. Chạy fdk/tools/skill-provenance.py. /skill-provenance
Implement and audit web accessibility with WCAG, semantic HTML, keyboard navigation, focus, accessible names, contrast, zoom, and assistive technologies. Use for components, pages, forms, dashboards, and compliance reviews; automation does not replace manual testing.
Worked qupai-system (曲牌体) opera scripts, act by act. Guan Hanqing's three surviving zaju (窦娥冤／救风尘／金线池 — twelve acts, 126 tunes, one mode and one rhyme per act, sung/spoken ratios); Tang Xianzu's 牡丹亭 (55 scenes, ~420 tunes, 集唐 closing quatrains, the 圆驾 south-north composite suite); Kong Shangren's 桃花扇 (44 scenes plus four unnumbered, the 副末 frame line, upper/lower halves, a fan's seven transformations, his sixteen 凡例); 长生殿 (Wang Jilie's fifty-scene staging table); Wei Minglun's 巴山秀才 (1983 Sichuan 高腔, 43 tunes, nine 帮腔 passages). Every case states its edition and collation status, then structure, tunes, stage conventions and transferable devices. Method is in sw-chinese-opera-qupai; this skill holds the worked scripts. Use when you want a real example of how a 传奇 or 杂剧 is assembled, need actual scene counts and tune counts to imitate, are judging where a famous script breaks prosody, or need models for 副末开场, 集唐下场诗, 南北合套 or 帮腔 (曲牌体全本／牡丹亭／桃花扇／窦娥冤／救风尘／长生殿／巴山秀才／唱段表／结构表).
Implements Syncfusion .NET MAUI DataForm (SfDataForm). Use when creating data entry forms, edit forms, login forms, registration forms, or contact forms in MAUI. Covers form creation, data validation, editor customization, layout management, data binding, grouping, localization, built-in editors, custom editors, and validation modes.
Implements Syncfusion .NET MAUI DateTime Range Selector (SfDateTimeRangeSelector) for interactive date/time range selection with chart integration. Use when working with range selectors, date range pickers, time range selection, chart range filtering, or interactive range controls. Covers range selection UI, filtering chart data by date range, and selecting time periods.
Implement and customize Syncfusion® .NET MAUI Funnel Charts (SfFunnelChart). Use when implementing funnel charts, sales funnel visualization, conversion funnel analysis, process stage visualization, or marketing funnel tracking. Covers funnel chart implementation, customization, data labels, legends, tooltips, segment spacing, and orientation.
Sets up and validates Syncfusion .NET MAUI licensing, including license key registration, generation, and error resolution. Use when encountering trial license warnings ("This application was built using a trial version"), licensing errors, license key registration, unlock key vs license key confusion, build server or CI/CD licensing, NuGet package licensing requirements, platform mismatch errors, or version mismatch errors.
Implements Syncfusion® .NET MAUI Linear ProgressBar (SfLinearProgressBar) control. Use when working with progress bars, progress indicators, loading indicators, determinate/indeterminate progress, or buffer progress visualization. Covers progress tracking, multi-segment progress, animated progress, and gradient progress bars.
Implements Syncfusion .NET MAUI Range Slider (SfRangeSlider) for selecting numeric range values with dual thumbs. Use this for range selection controls, dual-value sliders, price range selectors, date range filters, or scenarios requiring minimum-maximum value selection with interactive thumbs.
Implements Syncfusion .NET MAUI Scheduler (SfScheduler). Use when creating scheduling applications, calendar views, appointment management, event planning, or resource scheduling in .NET MAUI. Covers scheduler views, appointment management, recurring events, timeline views, hierarchical resources, ICS import/export, quick info template, floating action button, adaptive UI, agenda layout mode, and month agenda view.
Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
Manage Tencent Cloud CLS alarm policies, notice groups, shields and alarm execution logs. Use when the user asks to: list / create / modify / delete CLS alarms, enable or disable alarms, manage notice recipients (SMS / email / webhook), mute alarms during deploys, or view which alarms fired and when. For searching the underlying log content, use the companion `tencentcloud-cls` skill.
Emulated Vercel REST API for local development and testing. Use when the user needs to interact with Vercel API endpoints locally, test Vercel integrations, emulate projects/deployments/domains, set up Vercel OAuth flows, manage environment variables, create API keys, configure protection bypass, emulate Vercel Blob storage, or test without hitting the real Vercel API. Triggers include "Vercel API", "emulate Vercel", "mock Vercel", "test Vercel OAuth", "Vercel integration", "Vercel Blob", "local Vercel", or any task requiring a local Vercel API
When the user provides a WeChat Official Account article link (URL containing mp.weixin.qq.com), this skill must be used to read the article. Do not use web_fetch, web_search, or any other method as a substitute. This skill uses a dedicated script to reliably retrieve and return structured results, including the title, publication time, author, and body.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
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.