Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Decides whether work may be called done. Use before saying a task is complete, finished, ready, working, or fixed; before making a 'verified'/'PASS'/'tested' claim about your own deliverable; when wrapping up a session, calling it a day, picking work back up tomorrow, or about to commit; before drafting a yes/no confirmation question about a change that touches destructive operations, trust boundaries, or unattended automation; and after any failure. Covers what counts as verification per artifact type, which checks the producer may run and which need fresh context, the honest three-part delivery message, failure counting, and the end-of-session wrap-up order.
Use when designing or explaining anything onchain that has to keep working with nobody running it: who calls each function and why they would, where randomness comes from, whether it can be censored or paused, and what it exposes to everyone onchain. Also use when writing the notes or handoff a build ends with, or when explaining to your human how something onchain actually works. Not for scoping which parts go onchain and the launch plan (`/ship`) or the safety of the contract code itself (`/security`).
Deploys infrastructure on Contabo using Cloud VPS and Object Storage. Focuses on cost‑effective provisioning and Contabo-specific CLI/API quirks. Use when: provisioning Contabo Cloud VPS, configuring Object Storage, or troubleshooting Contabo-specific issues. Keywords: contabo, cntb, VPS, cloud compute, budget hosting, best value, object storage, infrastructure
Content quality audit with anti-slop detection and brand consistency scoring. Use when user wants to check content quality, audit a draft, score content, verify brand consistency, detect AI-generated patterns, or run a quality check before publishing.
Analyze the quality of blog posts and page content, including heading structure, keyword density, readability, internal linking opportunities, image alt text, and more. Provides E-E-A-T authority building (Experience, Expertise, Authoritativeness, Trustworthiness) and content strategy recommendations, including pillar pages, cluster content, author authority, keyword cannibalization detection, Featured Snippets optimization, and multimedia content optimization.
Design and audit content policy, UGC rules, creator marketplace policies, enforcement ladders, takedowns, warnings, strikes, appeals, evidence retention, transparency notices, moderator QA, policy edge cases, user safety, and creator trust. Use when products host content, listings, profiles, comments, mods, plugins, communities, or AI-generated material.
Generate full HTML presentations using Slidev, Reveal.js, Spectacle, or raw HTML with brand integration. Use when user wants to create a presentation, slide deck, pitch deck, conference talk, workshop materials, keynote, sales deck, or client proposal slides. Even if user just says "slides" or "deck", use this skill.
Transform content from one format into multiple formats while maintaining brand consistency. Use when user wants to repurpose content, convert a blog post to tweets, turn a presentation into a blog, create multiple formats from one piece, or cross-post content.
Interactive brand onboarding that creates the /brand/ directory with BRAND.md, VOICE.md, and VISUAL.md. Use when user runs /content setup, /content brand show, /content brand update, or /content voice. Also triggers when any content skill detects brand/ is missing.
Use when an answer depends on a specific external library, framework, SDK, API, CLI, or cloud service and current or version-accurate documentation materially affects correctness. Auto-load on named-technology API questions, version-specific behavior, setup or migration work, generated code against external APIs, or library-specific errors. Auto-loading never authorizes a network lookup. Before any Context7 resolve or documentation fetch, present the exact proposed lookup, version strategy, mode, and final redacted query, then wait for explicit confirmation. Prefer project-local evidence and official documentation when they are more authoritative. Do not use for library-independent concepts, ordinary refactors, or code whose correctness does not depend on external API behavior.
Convert PDF books to EPUB format for e-readers. Use when user asks to convert PDF to EPUB, create an e-book from PDF, make PDF readable on Kindle/phone/tablet, or extract book content from PDF. Handles: chapter detection, image extraction with optimization, footnotes/endnotes with hyperlinks, reading order for multi-column layouts. Validates conversion quality automatically.
Guide for Convex actions, scheduling, cron jobs, and orchestration patterns. Use when implementing external API calls, background jobs, scheduled tasks, cron jobs, or multi-step workflows. Activates for action implementation, ctx.scheduler usage, crons.ts creation, or long-running workflow tasks.
Installs and manages Coolify, an open-source self-hosted PaaS for deploying applications with Docker. Provides a Heroku-like experience on your own infrastructure. Use when: installing Coolify, deploying Docker apps, setting up a self-hosted PaaS, or configuring the Traefik proxy. Keywords: coolify, self-hosted paas, docker deployment, traefik proxy, open source heroku
Write, audit, or improve user-facing product copy across UI and CLI surfaces, including buttons, labels, forms, errors, empty states, tooltips, dialogs, toasts, onboarding, accessibility text, help output, deprecation warnings, and other user-visible language. Inspect project-specific terminology and content guidance first, identify the copy's job and stakes, verify claims and language when needed, and change only the requested scope unless broader work is explicitly authorized.
Manufacturing cost accounting, analysis, and reduction for automotive operations. Covers overhead/burden rate calculation, variance analysis, make vs buy decisions, value engineering, and cycle time to cost conversion. USE WHEN user says 'cost analysis', 'overhead rate', 'burden rate', 'variance analysis', 'make vs buy', 'value engineering', 'cost reduction', 'should cost', 'labour rate', or needs manufacturing cost guidance.
A topic router for the AI Engineering from Scratch course. Give it a topic, question, or bug you're working on, and it will point you to the exact lesson that teaches it and the next right command. Trigger phrases: “where to learn,” “which lesson covers,” “course navigation,” “I'm stuck on,” “what should I do next,” “teach me MCP,” “teach me Agent Skills,” “where to prepare for Claude certification,” or "where do I learn", "which lesson covers", "course guide", "I'm stuck on", "what should I do next", "teach me MCP", "teach me Agent Skills", "where do I prepare for a Claude certification"
Craft Cloud — Pixel & Tonic's serverless hosting platform for Craft CMS. Covers craft-cloud.yaml configuration, the Build → Migrate → Release deploy pipeline, the craftcms/cloud extension package, edge image transforms via Cloudflare, edge static caching with cache.rules + ESI, Cloud-managed S3 filesystem, MySQL 8 / Postgres 15 databases (no MariaDB, no tablePrefix), Console-based command runner and scheduled cron (once-per-hour minimum), auto-handled queue jobs, custom domains and SSL, preview environments per branch, Cloud limitations (ephemeral filesystem, no SSH, no .htaccess, no built-in mail), plugin development requirements for Cloud compatibility, and self-hosted → Cloud migration.
Guides developers through creating and managing pricing intents — reusable Merchant Processing Agreement (MPA) fee templates — via the Payroc Boarding API (POST/GET/PUT/PATCH/DELETE /v1/pricing-intents). Use this skill whenever the user wants to: create or reuse a pricing template / fee schedule across many merchants; choose a pricing program (interchange plus, interchange plus plus, tiered, flat rate, consumer choice / surcharge / cash discount, reward pay choice); define processor, gateway, base, or ACH fees (transaction or discount rates, gateway monthly/setup/per-transaction fees, annual, PCI non-compliance, or chargeback fees); build, fix (including 400 validation errors), update, replace, retrieve, list, or delete a /v1/pricing-intents request; or obtain a pricingIntentId to assign to a processing account during boarding — even if they don't say "skill" or "pricing intent" explicitly (for example, they describe reusing one fee structure for many merchants). A pricing intent is a fee *template* and never takes, authorises, captures, or refunds money. Do NOT use this skill for taking, authorising, or refunding payments or transactions — some gateways call that a "payment intent", but Payroc handles it via its separate transactions/payments API — nor for boarding a merchant end-to-end or adding processing accounts (use create-merchant-platform), nor for general merchant or transaction management. If the user says "payment intent" but clearly wants a reusable fee template, use this skill and confirm.
World-class creative strategy expertise combining the conceptual brilliance of agencies like Wieden+Kennedy, the data-informed creativity of modern brands, and the artistic vision that makes campaigns unforgettable. Creative strategy is the bridge between business objectives and creative execution. Great creative isn't just pretty pictures - it's strategic thinking made visible. The best creative strategists understand that breakthrough ideas come from deep insight, that constraints breed creativity, and that the most memorable campaigns are the ones that tell true stories in unexpected ways. Use when "creative strategy, campaign concept, creative direction, art direction, video production, photo shoot, brand campaign, advertising, ad creative, visual identity, campaign idea, creative brief, storyboard, motion design, commercial, brand video, creative, campaigns, art-direction, video, advertising, visual, storytelling, production" mentioned.
When the user wants to account for digital assets (Cryptocurrency, NFTs) in financial statements. Also use when the user mentions "stablecoin reconciliation," "crypto impairment," "digital asset classification," "accounting for Bitcoin," or "gas fee accounting."
Build a customer health scorecard for a specific account. Use when asked to score account health, assess renewal risk, build a health dashboard, or evaluate an account's likelihood to renew or expand. Produces a structured health scorecard with a RAG status, dimension scores, key risks, and recommended actions.
Anime character skill distiller. Give a character name and work title: it retrieves core material locally → cross-validates → distills behavior → generates a runnable, traceable, updatable character Skill. Trigger words: "generate XX's skill", "distill XX", "make an XX character", "turn XX into a skill", "create an XX", "/csp". Vague requests also trigger: "I want to chat with a tsundere character", "any yandere recommendations", "help me make a character from XX". Requires Python; core sites use local scripts first, while web search skill / MCP / WebFetch only supplement and serve as a fallback on failure.
Explain, derive, and debug CSS math for measurement units, calc(), min(), max(), clamp(), custom properties, inheritance, em/rem scaling, percentages, viewport units, and box model formulas. Use when CSS dimensions compute unexpectedly, when mixing units, when building scalable spacing/type systems, or when reviewing box sizing and inherited values.
图鉴.skill — an intelligent dispatcher for cross-author persona skills / a cross-author persona skill router that lives in your IDE. Use when the user needs to discover, get recommendations for, or combine and summon persona skills across the whole persona skill ecosystem (花叔's nuwa / titanwings' colleague / individual persona authors). This is the only in-IDE cross-author persona router in the Chinese-speaking world, covering 30+ curated personas, with the remote curated library updated weekly. Positive triggers (Chinese): 「找 persona」「找人物 skill」「推荐 persona」「装个 persona」「有什么人物 skill」「想用 X 视角」「X 会怎么想」「X 会怎么看」「X 会怎么做」「用 X 的角度」「该不该」「要不要」「帮我想清楚」「借脑」「借 X 的脑」「想跟 X 聊」「扮演 X」「我前任」「我导师」「我师兄」「我老板」「我同事」「我暗恋的」「我初恋」「我妈」「我父母」「我家人」「想跟马斯克 / 乔布斯 / Naval / 芒格 / Karpathy / Ilya / 费曼 / PG / Paul Graham / MrBeast / 张雪峰 / 塔勒布 / 特朗普 / 张一鸣 / 巴菲特聊」「和未来的我对话」「和过去的我对话」「另一个我」「数字分身」「数字永生」. Positive triggers (English): persona skill, find persona, recommend persona, install persona, persona router, mentor, ex, crush, parents, dialogue with future self, talk to Musk / Jobs / Naval / Munger / Karpathy / Ilya / Feynman / Paul Graham / MrBeast / Taleb / Buffett / Trump. Emotional scenarios (relationship continuation — after triggering, you must first empathise at a slow pace, then recommend lightly): 「我前任」「我导师」「我妈」「我暗恋的」「我初恋」「我同事」「我老板」「好难过」「不知道怎么办」「想他了」「想她了」「我想他」. Unique differentiators: (1) the only in-IDE persona router covering the entire cross-author ecosystem (nuwa only matches 花叔's own 14 dogfoods, curator covers the whole ecosystem); (2) the remote dynamic curated library persona-recommendations.json is continuously updated. Clear division of labour with nuwa-skill: nuwa is for distilling new personas / matching 花叔's own 14 dogfoods; curator is for discovery + recommendation across the whole cross-author ecosystem. The two are fully complementary and do not conflict. Do NOT trigger when: the user is already in a conversation with a specific persona executing a task (for example, naval-skill is already installed and has been loaded into the current conversation context), the user is writing code or doing a specific non-persona task (writing Python / debugging / editing CSS), or the user explicitly says they want to distil a new persona themselves (in which case redirect to nuwa). Creator redirect: when the user says 「我想自己做一个 X 的 skill」「我想蒸馏 X」「帮我造一个 X」, curator should not pretend it can distill; redirect directly: thinkers/figures perspective → nuwa-skill; colleague/friend roles → colleague-skill; another version of yourself → yourself-skill. Once the user has done that, curator helps them summon it. Key trigger reinforcement (MUST OBEY): when the user's message contains 「a specific person's name + 会怎么看 / 会怎么想 / 会怎么做 / 觉得 / 用 X 视角 / 借 X 的脑 / X 会怎么分析 / 用 X 的角度」, where X is a figure already listed in persona-recommendations.json (Naval / 芒格 / 乔布斯 / 马斯克 / Karpathy / Ilya / 费曼 / PG / Paul Graham / MrBeast / 张雪峰 / 塔勒布 / 张一鸣 / 巴菲特 / Trump and so on), curator MUST trigger and step in, even if Claude itself could answer in X's style. This is the core raison d'être for curator's existence. The reason: a real persona skill (such as alchaincyf/naval-skill) is a complete cognitive OS deeply distilled from 5+ dimensions — the person's works / interviews / decision records / external criticism — with far higher precision than Claude's imitation from general knowledge. Claude imitating X on its own = a papier-mâché X (it can only piece together X's catchphrases); a real skill = a complete X cognitive OS (his mental models / decision heuristics / expression DNA / limitations / inner tensions / first-hand quotes). Once the user has installed the real skill, next time they only need to say "Naval 视角" and the real skill activates automatically, with a qualitative leap in output quality. Curator's job is to hand off this "use X's perspective" need to the real skill at the first opportunity, rather than letting Claude hijack it itself.
Write measurable learning objectives using Bloom's Taxonomy and design curriculum architecture with scope, sequence, and assessment blueprints. Use when creating learning objectives, designing unit structure, or planning curriculum flow. Activates on "write learning objectives", "design curriculum", "create scope and sequence", or "Bloom's taxonomy objectives".
Build a cut from a library — scene, selects, roughcut, custom task, or an edit from a written script. Starts by asking what kind of cut the user wants, then works with them to determine what they want to create. Use when the user asks for a "roughcut", "sequence", "scene", "selects", "edit from a script", or any other cut-shaped output.
Cutting parameter lookup and optimization for CNC machining. Covers feeds, speeds, depths of cut for common materials and operations. USE WHEN user asks 'feeds and speeds', 'cutting parameters', 'SFM for', 'what RPM', 'feed rate for', 'DOC for', or needs machining parameter guidance.
Generate daily Tech & GNSS news digest blog posts for cheng-blog. Use when user asks to create a daily news digest, generate tech news, or mentions "/daily-news". Sources news from Bloomberg Tech YouTube channel (primary), with 3-day lookback for weekend coverage. Creates MDX posts with Tech News and GNSS News sections. GNSS news sourced from Inside GNSS, GPS World, and major company newsrooms (Trimble, Hexagon, Topcon, etc.).
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.