Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when generating Kubernetes CustomResourceDefinitions from a typed schema source (zod / TypeBox / Valibot / json-schema). Covers the Structural Schema dialect's restrictions, the /status subresource trap, the metadata-prohibition rule, and plural inflection — the four pitfalls that bite on first attempt.
A communication and interpersonal advice consultant inspired by Tsai Kang-yung’s public content. Handles three scenarios: tactful refusals, difficult customer-service replies, and supporting students through their stories. First clarify the relationship and boundaries, then draft a warm but clear reply that makes no unwarranted promises and is ready to send. Also triggered by “Please have Tsai Kang-yung review this email,” “Help me refuse tactfully,” “I don’t know how to reply to a student’s letter,” or “Customer service is getting emotional.”
Teach Claude ANY topic - code libraries, APIs, concepts, tools, methodologies, or domains. Researches via web and docs, then retains knowledge as a permanent skill. Use when user says "/learn <topic>", "learn about X", "teach yourself Y", "become an expert on Z". Examples - "/learn stripe" for payments, "/learn GTD" for productivity, "/learn israeli-tax-law" for domain knowledge.
Generate measurable learning outcomes aligned with Bloom's taxonomy and CEFR proficiency levels for educational content. Use when educators need to define what students will achieve, create learning objectives for curriculum planning, or ensure objectives are specific and testable rather than vague.
Use when designing, refactoring, or reviewing web interfaces that should feel calm, precise, functional, and visually restrained. Applies minimalist UI principles inspired by Ludwig Mies van der Rohe, Louis Sullivan, Massimo Vignelli, Dieter Rams, and Jony Ive, with emphasis on strong typography, structured layouts, semantic HTML, restrained motion, and removal of visual noise.
Guides life and health insurance—life (term, whole, universal, variable overview), health (individual, group, Medicare/Medicaid overview), disability and LTC, underwriting, policy provisions, claims and benefits administration, reinsurance, distribution, and metrics (lapse, persistency, loss ratio, MLR). Regulatory overview (state DOI, NAIC, ACA, HIPAA privacy—not legal advice). Use for life insurance, health insurance, term life, group health, underwriting life, Medicare, Medicaid, ACA, medical loss ratio, MLR, disability insurance, long-term care, LTC, persistency, reinsurance life—not P&C (property-casualty-insurance), pensions (pension-retirement-funds), actuarial modeling (actuary), actuarial engagements (actuarial-consulting), legal interpretation (commercial-counsel), or GRC without insurance context (compliance-engineer).
Takes pasted LinkedIn job posts or hiring descriptions and converts them into a structured buyer pain map with inferred pains, capability gaps, buy-vs-build signal, account priority scores, and suggested outreach angles. Use when asked to analyze hiring posts, decode job descriptions for buyer intent, build a pain map from job listings, extract GTM signals from hiring activity, or prioritize accounts based on hiring data. Trigger when a user says "analyze these job posts", "what pain does this hiring signal", "build a pain map from these listings", "decode this job description", or "score these accounts from their hiring".
Take an enriched Extruct table and a hypothesis set, then segment companies by hypothesis fit and assign tiers based on data richness and signal strength. Outputs a tiered, segmented list ready for email generation. Triggers on: "segment", "tier", "segment companies", "tier companies", "prioritize list", "segment and tier", "tiering", "which companies first".
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative
When the user wants to optimize load building, create efficient truck loads, or maximize trailer utilization. Also use when the user mentions "load planning," "truck loading," "cargo optimization," "shipment consolidation," "cube utilization," or "weight distribution." For pallet loading, see pallet-loading. For container loading, see container-loading-optimization.
Logo design principles and AI image generation best practices for creating logos. Covers logo types, prompting techniques, scalability rules, and iteration workflows. Use for: brand identity, startup logos, app icons, favicons, logo concepts. Triggers: logo design, create logo, brand logo, logo generation, ai logo, logo maker, icon design, brand mark, logo concept, startup logo, app icon logo
When the user wants to optimize production or order lot sizes over multiple periods, solve multi-period inventory planning problems, or determine when and how much to order/produce with time-varying demand. Also use when the user mentions "lot sizing," "lot-for-lot," "fixed order quantity," "POQ" (periodic order quantity), "part-period balancing," "Silver-Meal heuristic," "Wagner-Whitin algorithm," "least unit cost," "lot sizing with capacity constraints," or "multi-item lot sizing." For single-period problems, see newsvendor-problem. For time-varying lot sizing, see dynamic-lot-sizing.
Guidance for hardening macOS endpoints managed by Microsoft Intune — automated device enrollment via Apple Business Manager (ABM), platform single sign-on (PSSO) with Entra ID, FileVault disk encryption escrow, security configuration profiles (Gatekeeper, XProtect, system extensions allowlist, firewall, login window, Privacy Preferences Policy Control / PPPC), Microsoft Defender for Endpoint on macOS, app management (VPP / managed apps / shell scripts via Intune), patching strategy (managed software updates / DDM), Conditional Access compliance signal, and cross-platform identity model. WHEN: Mac Intune baseline, macOS hardening Intune, FileVault escrow, ABM Apple Business Manager, Platform SSO macOS, PSSO Entra, MDE on Mac, Gatekeeper Intune, system extensions Intune, PPPC Intune, macOS compliance Conditional Access. DO NOT USE for general Intune device management end-to-end (use intune-device-mgmt), MDE config alone (use defender-for-endpoint), or iOS device management.
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Create or modify GitHub Actions workflows for CI, automation, or PR management. Use when asked to create, scaffold, add, extend, or fix a workflow (.yml file under .github/workflows/), including existing pull-request policy and comment automation.
Generate a 5/10/15s vertical UGC video where your character holds, wears, and shows a product. Provide a character_sheet_url (R2-hosted) and the product image (product_image_url — any https URL — OR product_image_base64; re-hosted to R2 automatically). Two modes: script for a lip-synced talking-head product review (2-4 words/sec), OR scene_action for a silent demo / b-roll. Set subject (e.g. "a young woman") to lock the person's gender/appearance so a gendered product can't drift it. framing: "close_up" (chest-up, default) or "full_body" (head-to-toe, for turn-arounds / showing the whole outfit). Both the person and the exact product are locked from the reference images.
When the user needs marketing or product ideas grounded in behavioral principles and proven experiments. Use when the user mentions 'marketing ideas,' 'product ideas,' 'awareness experiments,' 'conversion experiments,' 'growth experiments,' 'PLG tactics,' 'top of funnel,' 'trial to paid,' or 'self-serve SaaS strategies.' This skill provides a 5-layer mental model, 30 foundational marketing principles, and tested experiments for awareness and conversion.
Integrate markstream-vue2 into a Vue 2 Vue CLI or Webpack 4 app. Use when Codex needs Webpack 4-friendly setup, CDN worker fallbacks for Mermaid or KaTeX, `dist/index.css` imports, Vue 2 composition-api shims, or code block choices limited to `stream-diffs` or plain `<pre>`.
Unified skill for all MATLAB and Simulink report generation tasks. Covers report generation, PDF report, document generation, mlreportgen, Report Generator, template, TitlePage, Chapter, multipage HTML, HTMLPage, html-multipage, custom reporter, customizeReporter, template hole, page header, page border, company style package, branded reporters, buildTemplates, Simulink report, model documentation, slreportgen, block diagram report, model report, subsystem documentation, SystemDiagramFinder, SystemIO, ExecutionOrder, LookupTable, template style, page footer, TemplateSrc, report package, table variants, multiple HTML pages, PDF report generation, Word report, DOM API, FormalTable, BaseTable, Figure, FormalImage, Section.
Use when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner — including opening the app, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models. Programmatic access to Classification Learner and Regression Learner apps via AppController.
MatrixScan Count (BarcodeCount) in React Native projects — scandit-react-native-datacapture-barcode package. Multi-barcode counting workflows (scan-and-count, counting against an expected capture list, status overlays) with BarcodeCountView. For Capacitor use matrixscan-count-capacitor. Use for integration, settings and symbology configuration, result handling, UI customization, or troubleshooting counting workflows.
Guide for creating custom .NET MAUI handlers, customizing existing handlers with property mappers, and implementing platform-specific native views. Covers PrependToMapping/ModifyMapping/AppendToMapping, PropertyMapper, CommandMapper, partial handler classes, and handler registration. USE FOR: "custom handler", "PropertyMapper", "AppendToMapping", "PrependToMapping", "ModifyMapping", "CommandMapper", "platform-specific rendering", "native view", "handler registration", "custom control renderer". DO NOT USE FOR: platform API calls without custom controls (use maui-platform-invoke), data binding (use maui-data-binding), or gesture handling (use maui-gestures).
Guidance for calling platform-specific native APIs from .NET MAUI apps. Covers partial classes, conditional compilation, multi-targeting configuration, and dependency injection patterns for cross-platform code that needs Android, iOS, Mac Catalyst, or Windows functionality. USE FOR: "platform-specific code", "conditional compilation", "partial class", "#if ANDROID", "#if IOS", "multi-targeting", "native API call", "platform invoke", "platform-specific DI", "DeviceInfo.Platform". DO NOT USE FOR: custom control handlers (use maui-custom-handlers), permission requests (use maui-permissions), or dependency injection patterns (use maui-dependency-injection).
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Search, install, configure, update, and remove MCP servers across coding agents (Claude Code, Cursor, VS Code, Claude Desktop, Gemini CLI, Codex, Goose, Zed, Devin CLI/Desktop, and more). Supports multi-agent installation via npx add-mcp, the official MCP registry, and direct config editing.
Converts a markdown PR writeup or code review (one with ```diff fenced blocks and severity-tagged GFM callouts [!BLOCKER]/[!MAJOR]/[!MINOR]/[!NIT] callouts) into a single-file 2-column HTML review — unified-diff on the left, severity-tagged annotation cards on the right, top jump-nav listing every finding, mandatory named reviewer footer. Triggers when the markdown-html-orchestrator classifies an input as REVIEW, or when invoked directly via /cs-md-review. Refuses without explicit --reviewer (a code review must name a human), refuses if no diff hunks present (route to md-document instead), and refuses to encode severity in color only (every badge ships color + icon + aria-label per WCAG 1.4.1). Use after orchestrator routing.
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
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.