Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Decide when repeating a full prompt is a useful accuracy hack for non-reasoning or lightweight LLM tasks, and when the real fix is better prompt structure, retrieval, or a stronger model. Use when the user has long-context retrieval, options-first multiple choice, or position-sensitive prompts on models like Haiku, Flash, or mini variants — even if they ask in domain language like the model missed the instruction at the end, forgot the question after a long context block, or keeps failing inventory/index lookups. Do not use as a universal prompt-engineering default for reasoning-heavy, tool-heavy, or RAG architecture problems.
Ruby performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring Ruby code to ensure optimal performance patterns. Triggers on tasks involving object allocation, collection processing, ActiveRecord queries, string handling, concurrency, or Ruby runtime configuration.
SEO, AEO (Answer Engine Optimization), and GEO strategy for search engines and AI visibility. Use when working on "SEO audit," "technical SEO," "on-page SEO," "AI search optimization," "AEO," "GEO," "AI visibility," "optimize for ChatGPT," "optimize for Perplexity," "AI Overviews," "answer engine optimization," "generative engine optimization," "AI citations," "featured snippets," "meta tags," "schema markup," "search ranking," "content optimization," "E-E-A-T," "structured data," "search console," "SEO health check," "why am I not ranking," "AI search readiness," "backlink strategy," "link building," "domain authority," "programmatic SEO," "SEO at scale," "template-based SEO," "AEO monitoring," "AI search monitoring," "JSON-LD," "rich snippets," "schema.org," "SERP analysis," "search intent," "site architecture," "information architecture," "URL structure," "internal linking," or "navigation." For keyword research, see keyword-research-and-clustering.
A core tool dedicated to summarizing, optimizing, and iterating on existing Skills at the end of a conversation based on user feedback and conversation content. It continuously evolves the Skills library by learning from the conversation’s “essence,” such as successful solutions, lessons from failures, and specific coding conventions.
A comprehensive guide to implementing Syncfusion Angular Input components, including Uploader, NumericTextBox, TextBox, Signature, CheckBox, OTP Input, RangeSlider, TextArea, ColorPicker, MaskedTextBox, and Rating. This guide is intended for building Angular applications with file upload UIs supporting async and chunked uploads, drag-and-drop functionality, numeric inputs with validation and formatting, text inputs with floating labels and custom adornments, digital signature capture with undo, redo, and export capabilities, checkbox multi-select and indeterminate states, seamless form integration, accessibility compliance, one-time password (OTP) inputs, programmatic row adjustments, slider tick customization and styling, visual color selection with HSV picker and palette support, masked text input for structured data entry, and interactive star rating components
Creates Vue 3 components, builds vanilla JS composables, configures Vite projects, and sets up routing and state management using JavaScript only — no TypeScript. Generates JSDoc-typed code with @typedef, @param, and @returns annotations for full type coverage without a TS compiler. Use when building Vue 3 applications with JavaScript only (no TypeScript), when projects require JSDoc-based type hints, when migrating from Vue 2 Options API to Composition API in JS, or when teams prefer vanilla JavaScript, .mjs modules, or need quick prototypes without TypeScript setup.
“Learn then Build” — help developers understand AWS Well-Architected best practices for their specific workload, then produce actionable visual artifacts (architecture diagrams with WA annotations, decision trees, improvement roadmaps) they can commit and use. Adapts explanations for beginners and generates artifacts faster for experienced builders. Use when the user wants to understand WA for their project, create architecture diagrams with pillar health overlays, get guided decision flows for architectural choices, or generate a visual improvement roadmap
A professional tool that generates viral WeChat Official Account headlines based on popularity data or scores user-provided headlines across multiple dimensions. Use when users want to generate WeChat Official Account headlines, find viral content, analyze popular trends, get creative inspiration, or learn from viral content patterns. Trigger words: WeChat Official Account headline, viral headline, headline generation, headline scoring, viral WeChat Official Account content.
Detects and bolds prohibited Xiaohongshu terms in copy, files, or web pages, and provides replacement suggestions and a version of the copy with only the prohibited terms replaced. Use when users need to look up Xiaohongshu prohibited terms, check Xiaohongshu post copy for sensitive terms, or get safe replacements and revised copy. If the API returns insufficient credits (code=3210), automatically open Alipay to top up and continue the search.
Create and query Alibaba Cloud alert rules via CLI. Supports CMS 1.0 cloud resource monitoring (ECS, RDS, SLB, etc.) and CMS 2.0 advanced monitoring (Prometheus, APM, UModel). Intent routing automatically selects the correct workflow based on alert type. Use this skill when users mention: create alert, setup monitoring, configure alarm, ECS/RDS/SLB alert, Prometheus alert, PromQL, K8s monitoring, APM alert, UModel alert, list alerts, query rules, 告警规则, 创建告警, 监控报警, Prometheus告警, 应用监控, 查看告警.
Use when setting up, verifying, or troubleshooting a custom Auth0 login domain (e.g. login.example.com). Covers CNAME setup, verification, TLS policy, Multiple Custom Domains, and Management API errors — even if the user just says "use my own domain for Auth0 login"
Texture authoring in Blender 5.2 - smart-material layers (edge wear, cavity grime, dust, rust, roughness breakup) from curvature/AO masks, z-fight-safe decal and sticker placement, trim sheets, tiling + vertex-color blends, texture painting, baking the look to game texture sets. Use when a material needs wear, dirt, a decal, trims or hand painting, not just wiring.
Guides cooking through culinary principles, food science, and flavor architecture rather than rote recipe steps. Covers technique teaching (knife skills, sauces, searing, braising), food science (Maillard reaction, emulsions, brining), flavor troubleshooting (salt/acid/fat/heat balance), menu planning, ingredient substitutions, plating, and cultural cuisine exploration. Use when users mention cooking, recipes, chef, cuisine, flavor, technique, plating, food science, seasoning, or culinary questions.
Use when ANY command fails with 'command not found', when installing CLI tools (ripgrep, fd, jq, yq, bat, etc.), auditing project environments, or batch-updating tools. Triggers on: command not found, install tool, missing binary, environment audit, update tools, which, apt install, brew install.
Reformat source code in this project using its own code-style settings — through the IntelliJ IDE when it's running, otherwise via the project's own formatter (Spotless / google-java-format / palantir-java-format) as a fallback. Use this whenever the user asks to format, reformat, tidy, "prettify", fix indentation, or optimize imports on Java/Kotlin/XML/etc. files — whether it's a single named file, a selected block or line range, a group of named files, or all uncommitted (git-changed) files. This skill is also normally invoked after any editing of files — apply it to the files you just created or changed once the edits are done, so the result stays consistent with the project's code style.
Use when structuring or refactoring Convex codebases with Domain-Driven Design boundaries, repository abstractions, adapters for external APIs, and transaction-safe workflows. Also use for naming—ubiquitous language, bounded context, short locals inside clear parent scope (avoid verbose identifiers)
Analyzes coupling between modules using the three-dimensional model (strength, distance, volatility) from "Balancing Coupling in Software Design". Use when asking "are these modules too coupled?", "show me dependencies", "analyze integration quality", "which modules should I decouple?", "coupling report", or evaluating architectural health. Do NOT use for domain boundary analysis (use domain-analysis) or component sizing (use component-identification-sizing).
Comprehensive data quality assessment against business rules, schema constraints, and freshness expectations. Activate when validating data pipeline outputs before production use, auditing a dataset against defined business rules, or producing a quality scorecard for a data asset.
Build agents specialized in conducting thorough research, gathering information from multiple sources, and synthesizing findings. Covers research planning, source evaluation, and report generation. Use when automating market research, competitive analysis, literature reviews, or intelligence gathering.
Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners. Use when setting up or migrating GitHub Actions workflows to Depot runners, choosing runner sizes (CPU/RAM), configuring runs-on labels, setting up ARM, Windows, or macOS runners, troubleshooting runner issues, configuring egress filtering, using Depot Cache with GitHub Actions, or running Dagger/Dependabot on Depot runners. Also use for depot-ubuntu, depot-windows, or depot-macos runner labels, or questions about faster/cheaper GitHub Actions runners, `depot jobs`, job analytics, or CPU and memory metrics.
Generate an ABAP Unit test class for a CDS entity using the CDS Test Double Framework — replicates SAP Joule's "CDS Unit Test Generation" capability. Use when asked to "generate CDS unit tests", "test this CDS view", "create CDSTDF tests", or "write unit tests for ZI_SALESORDER"
Creates comprehensive GitHub Actions CI/CD workflows for linting, testing, building, and deploying. Includes caching strategies, matrix builds, artifact handling, and failure diagnostics. Use for "GitHub Actions", "CI pipeline", "workflow automation", or "continuous integration".
Invoke for ANY Telegram bot code — `gramio`/`@gramio/*` imports, `new Bot()`, `bot.command`/`bot.callbackQuery`/`bot.on`/`bot.updates.on`, scenes/FSM, inline & reply keyboards, message entities, file uploads, sessions, plugins, webhooks vs long-polling, Telegram Stars, Mini Apps (TMA), broadcasting, Docker. Type-safe TypeScript framework (Node.js/Bun/Deno) with full Bot API coverage. Also covers migrations from Telegraf/grammY/puregram/node-telegram-bot-api. When delegating to a subagent, pass relevant reference files (callback-data, scenes, formatting, context, middleware-routing, ux-patterns) inline — this skill does not auto-load in subagent sessions.
Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (missing origin check), Service Worker abuse (intercept requests from same-origin script), CSS Injection/Exfiltration (attribute selectors → token char-by-char via OOB), client-side template injection, dangerouslySetInnerHTML. Grounded in named public research: Gareth Heyes / PortSwigger DOM-clobbering + DOM-Invader, Michał Bentkowski DOMPurify clobbering bypasses, jQuery htmlPrefilter XSS (CVE-2020-11022 / CVE-2020-11023), d0nut CSS-exfil research. Use when hunting DOM-XSS, client-side auth bypass, or token exfiltration without server-side interaction
Hunt Host Header Injection — password reset poisoning → ATO, web cache poisoning via unkeyed Host/X-Forwarded-Host, routing-based SSRF (Host picks upstream → cloud metadata/internal services), path-override SSRF/ACL-bypass (X-Original-URL/X-Rewrite-URL), OAuth redirect_uri/issuer poisoning, and absolute-URL link poisoning in emails. High to Critical when it reaches ATO or mass cache poisoning. Built on public Host-header research (PortSwigger 'Practical web cache poisoning' + James Kettle, and the classic password-reset-poisoning class). Use on any forgot-password flow, CDN/reverse-proxy-fronted app, OAuth/OIDC endpoint, or absolute-URL-in-email feature
Hunt Local File Inclusion (LFI), Remote File Inclusion (RFI), and Path Traversal — /etc/passwd read, log poisoning → RCE, PHP filter-chain RCE (no upload needed), php:// / data:// / zip:// / phar:// wrappers, RFI via allow_url_include, directory traversal read/write/delete. Covers OOB/blind LFI confirmation and false-positive discipline. Use when hunting file-include or path-traversal bugs on any target
Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains (lodash/merge/assign), Express trust proxy misconfiguration, child_process/eval injection, template engine SSTI (EJS/Pug/Handlebars), path traversal in file servers, require() injection, environment variable exfil via /proc/self/environ. Use when target runs Node.js/Express/Fastify/NestJS/Koa.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Use when the user wants architecture improvement candidates surfaced before choosing one. Triggers on: improve the architecture, find deepening opportunities, where should we refactor.
Generates Jest unit and integration tests in JavaScript or TypeScript. Covers mocking, snapshots, async testing, and React component testing. Use when user mentions "Jest", "describe/it/expect", "jest.mock", "toMatchSnapshot". Triggers on: "Jest", "expect().toBe()", "jest.mock", "snapshot test", "JS test", "React test".
Quantifies market sentiment, risk appetite, and trading crowding to help determine whether the current market is euphoric, balanced, cautious, or fearful. Suitable for position sizing, timing decisions, and sentiment reviews
Use this skill whenever a lawyer or mediator needs help analyzing a dispute for mediation purposes. This includes: reviewing case materials (pleadings, contracts, correspondence, evidence) to identify issues in dispute, summarizing each party's position and interests, conducting legal analysis of the key issues, proposing mediation strategies or settlement directions, and preparing for mediation sessions. Trigger this skill when the user mentions 'mediation', 'dispute analysis', 'settlement', 'dispute resolution', 'identify issues in dispute', 'party positions', 'mediation brief', 'case analysis for mediation', 'ADR', 'mediation preparation', 'caucus strategy', 'settlement options', or any request to analyze a conflict between two or more parties with the goal of finding resolution. Also trigger when the user uploads case files and asks for a structured breakdown of who wants what, what the core disagreements are, or how the case might settle. Even if the user doesn't explicitly say 'mediation', trigger when the context involves analyzing opposing positions in a dispute with a resolution-oriented (rather than litigation-oriented) goal.
Build React animations with Motion (Framer Motion) - gestures (drag, hover, tap), scroll effects, spring physics, layout animations, SVG. Bundle: 2.3 KB (mini) to 34 KB (full). Use when: drag-and-drop, scroll animations, modals, carousels, parallax. Troubleshoot: AnimatePresence exit, list performance, Tailwind conflicts, Next.js "use client".
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.