Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when you see memory warnings, 'retain cycle', app crashes from memory pressure, or when asking 'why is my app using so much memory', 'how do I find memory leaks', 'my deinit is never called', 'Instruments shows memory growth', 'app crashes after 10 minutes' — systematic memory leak detection and fixes for iOS/macOS
Expert knowledge for Azure Event Hubs development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when working with Kafka clients, Flink/Spark, geo-replication, Entra ID/RBAC authentication, Event Hubs Capture/Avro, or other Azure Event Hubs development tasks. Not for Azure Service Bus (use azure-service-bus), Azure Event Grid (use azure-event-grid), Azure Notification Hubs (use azure-notification-hubs), or Azure Web PubSub (use azure-web-pubsub).
Dodo Payments plugin for Better Auth (@dodopayments/better-auth) covering customer sync on signup, authenticated checkout, customer portal, usage ingestion, and verified webhooks. Use when an app uses Better Auth and needs the dodopayments, dodopaymentsClient, checkout, portal, usage, or webhooks plugins; for other auth stacks use framework-adapters.
A workflow for handling chapter screenshots and illustrations while writing a book. Use to identify the screenshots needed for a chapter, provide step-by-step Claude Code prompts, define screenshot filenames and figure-number mappings, fill in image locations in local Markdown, clean author notes from the reader-facing text, and sync chapters and images to the correct places in Feishu documents. Trigger when the user mentions "book screenshots", "chapter illustrations", "figure-number mapping", "put it in the original text", "upload to Feishu documents", or "use the workflow from earlier".
Orchestrates multiple business ventures using Hormozi portfolio frameworks, prioritizing which to focus on and routing to specialized skills. Triggers when a user manages multiple products or businesses, asks "which business should I focus on," needs cross-venture resource allocation, or wants a portfolio-level health check.
Keep a Changelog format. Covers structure, change types, versioning. Use when creating or updating CHANGELOG.md files following the Keep a Changelog specification, or applying semver-compatible changelog conventions. Keywords: CHANGELOG.md, semver, Keep a Changelog.
Expert-level CI/CD with GitHub Actions, Jenkins, deployment pipelines, and automation. Use when the user mentions CI/CD, GitHub Actions, Jenkins, GitLab CI, deployment, or automation, or when the task involves CI/CD Fundamentals, Pipeline Design, Workflow Basics, or Docker Build and Push
Reviewer role. Opens rendered HTML, inspects every slide visually, fixes problems in custom.css or slides.html and rebuilds through build-html.sh. Use whenever the user says "review", "QA", "check slides", "inspect", "audit", "proofread", or wants feedback on a rendered deck.
Multi-tenant organization and team management for Convex with @djpanda/convex-tenants and @djpanda/convex-authz. Use when (1) setting up or integrating multi-tenant SaaS with Convex, (2) working with organizations, teams, members, or invitations, (3) configuring authz permissions for tenants, (4) using TenantsProvider, OrganizationSwitcher, or related React components, or (5) the user mentions convex-tenants, @djpanda/convex-tenants, or multi-tenant Convex
Make an AI avatar of yourself that looks and sounds like you. A HeyGen digital twin trained on a couple of minutes of your own footage says lines you never recorded, in your own ElevenLabs voice, lip-synced from the audio, on the engine whose mouth moves most like yours. Covers picking and joining takes, training, consent, making the voice, rendering the same line on Avatar V, IV and III, and judging them mouth to mouth against your real footage before anything else is made. Use when someone wants a digital twin, an AI avatar or talking head of themselves or a consenting person, a HeyGen avatar from their YouTube videos or recordings, their avatar to speak in their own cloned voice, a lip-synced talking video from a photo and audio, or says their avatar looks wrong, over-acts or its mouth isn't theirs.
CSS animations, transitions, keyframes, and modern motion APIs. Use when adding animations, transitions, scroll-driven effects, or view transitions. Use for css-animation, transition, keyframes, view-transitions, scroll-animation, transform, motion-preference, animation-timeline.
Long-lived connection listener for DingTalk personal IM, OA approvals, VoIP call invitations, to-dos, calendars, interactive cards, contacts, and meeting-notes events. Use when the user asks to listen for messages/@mentions, messages from a person or group, or all messages; read/recall/reaction events; group member joins or leaves; approval task creation/completion/transfer; approval instance initiation, CC, termination, or completion; VoIP call invitations; to-do creation/update/deletion; schedule creation, added participants, modification, or cancellation; friend requests or successful additions; meeting-notes creation or summary generation; interactive card callbacks; app event discovery; event Schema queries; or real-time consumption. Command prefix: dws event.
Provides comprehensive guidance for the Electron EGG framework, including project structure, main/renderer processes, IPC, window management, and desktop app development. Use when the user asks about Electron EGG, needs to create Electron applications with EGG, or work with Electron EGG patterns.
Official fal.ai agent skills for AI image, video, and 3D generation. A genmedia CLI core plus model routing, prompting, and recipe skills, production skills (character design, cinematography, commercial, marketing, storytelling, UGC), and verticals such as website redesign and 2D game assets. Requires a fal.ai API key.
Find the published business contacts of companies with Firecrawl, whether the user names them or describes them by type and place: press and media, sales, partnerships and support inboxes, shared business phone numbers and official contact forms, taken from the companies' own websites. Use when the user asks how to contact a company or wants published business emails, phone numbers or press, sales, support or partnership contacts, since contact pages change and an address must come from the page, not memory. Not for named people's details (use firecrawl-lead-research) or finding people to reach out to (use firecrawl-lead-gen).
Create narration from project subtitles or AI analysis output, then author SSML-style voice scripts with phoneme, break, and ttnumber markup for FrameVideo voiceovers. Use when the user wants subtitles linked to voice generation, automatic narration from transcript/content, pronunciation fixes, pause insertion, or text normalization before TTS.
Re-audit a website and compare scores against a previous GEO audit baseline to track improvement over time. Use when the user asks to re-audit, check progress, track GEO score changes, monitor improvements, or compare before and after optimization.
Create, view, manage, approve, and merge GitLab merge requests. Use when working with MRs: creating from branches/issues, reviewing, approving, adding comments, resolving discussion threads, checking out locally, viewing diffs, rebasing, merging, or managing state. Triggers on merge request, MR, pull request, PR, review, approve, merge, resolve thread.
Create and composite HeyGen digital-human videos in the content workspace. Use whenever the user asks for a 数字人, 数字人5, HeyGen, AI 口播人物, 数字人小窗, 圆形头像口播, full-screen digital human, or asks to make a video that uses the existing avatar. Enforce Creator-plan CLI OAuth, the configured Digital Twin, local IndexTTS2 narration, Avatar III for an unspecified digital human but Avatar V whenever the named preset 数字人5 is requested, adaptive face measurement plus the approved human-reviewed visual-centering offset in the headroom_08 circular bottom-left layout unless full-screen is explicitly requested, subtitle-safe placement, credit-aware master reuse, final QC/archive routing, and mandatory pairing with `heygen-avatar-motion` before any motion prompt or paid generation.
Builds reactive real-time backends on the iii engine. Use when building event-driven apps where state changes automatically trigger side effects, clients receive live updates via streams or websockets, or you need a real-time database layer with pub/sub and CRUD endpoints.
Ink terminal renderer for json-render: turns JSON specs (including AI-generated ones) into interactive terminal UIs with standard components, data binding, visibility rules, actions and dynamic props. Use for building terminal UIs from JSON or component catalogs.
Detect UX antipatterns (smells) in interface descriptions using the uxuiprinciples smell taxonomy. Returns structured findings with matched symptoms, severity, and step-by-step remediation recipes. API key optional — full remediation recipes require uxuiprinciples.com API Access.
Create, run, poll, and inspect results for Jinkō CMA-ES calibrations via the jinko-sdk: attach data tables and/or an advanced output set as fitness-function sources, set CMA-ES options and parameter priors, launch and monitor the run, and read performance/results payloads. Use whenever the user needs the SDK mechanics of building or driving a Calibration object. Do not use this skill for calibration business rules (defaults, diagnostics, deliverable rules). Do not use this skill for advanced output set / scoring design authoring — use jinko-output-set. Do not use this skill for data-table creation or validForFitnessFunction checks — use jinko-data-table. Do not use this skill for model or protocol authoring — use jinko-model / jinko-protocol. Do not use this skill for calibration-plan orchestration or iteration workflow.
Create, inspect, validate, and incrementally edit Jinkō output sets via the jinko-sdk: simple output sets (measure designs) that list scalar measures derived from model outputs, and advanced output sets (scoring designs) that define constraints, scalars, and weighted objectives for scoring virtual populations. Validate scoring expressions and read diagnostics before attaching an output set elsewhere. Do not use this skill for attaching a simple or advanced output set to a trial and running it; use jinko-trial for that. Do not use this skill for data-table creation or fitness-function metadata; use jinko-data-table for that. Do not use this skill for calibration setup or CMA-ES options.
Design or edit multi-arm Jinkō protocol designs via the jinko-sdk. Use this skill whenever the user wants to compare doses, schedules, administration routes, treatment activation flags, or combinations of treatments by overriding model component values per arm. Protocol designs assign values to model-defined inputs; dosing functions, schedule parameterization, treatment activation logic, and administration-mode logic belong in the model. Use jinko-model when those functions or inputs do not exist yet. Use jinko-trial for running trials.
Create, update, inspect, sanity-check, and retrieve Jinkō TrialVisualization project items for completed or running trials. Use this skill whenever the user wants a trial visualization, trial viz, time-series plot setup, scalar result plots, scatter plots, contribution analysis, survival analysis, data overlays, or to fetch the current visualization JSON. The SDK exposes a typed TrialVisualization API: creation helpers plus a per-section subservice for every plot type.
Create, generate, inspect, or work with Jinkō virtual populations (vpops) and vpop designs via the jinko-sdk. Use this skill whenever the user wants to upload a vpop from CSV or pandas DataFrame, create a vpop generator from marginal distributions, generate a vpop from a vpop design, inspect vpop content/statistics, or edit an existing vpop design. Vpops generated or uploaded as Vpop project items are not editable; edit the vpop design instead and regenerate.
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.