Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Query ChatGPT/Codex reset announcements and the remaining quota and spare Full resets of multiple Pro accounts; reuse Google sign-in to verify and restore web accounts one by one, converting to Beijing time. Distinguish Tibo's official announcements, unannounced platform silent resets, banked resets and account-level periodic resets. Use when the user asks "when does it reset", "when will the quota be restored", "what time is the next everyone reset", "has the banked reset arrived", "what did Tibo say", "usage limit when reset", or says "the quota suddenly went back to 100%", "it seems to/certainly has reset again", or asks "are all the accounts used up", "which one is still full". Must cross-verify using live product status, independent user measurements and announcements; it is forbidden to deny a reset that has already happened just because Tibo Radar has no new entry, and Pacific Time must be converted to Beijing time on the spot.
Build communication features with Twilio: SMS messaging, voice calls, WhatsApp Business API, and user verification (2FA). Covers the full spectrum from simple notifications to complex IVR systems and multi-channel authentication. Critical focus on compliance, rate limits, and error handling. Use when: twilio, send SMS, text message, voice call, phone verification.
Handle rate limits, retries, and failures when building on Twilio at scale. Covers 429 exponential backoff with jitter, per-number throughput limits, StatusCallback resilience, thin-receiver pattern, and fallback chains. Use this skill whenever sending messages or making calls at volume, or when building production-grade Twilio integrations.
Scans the A-share market to find listed companies with strong fundamentals but undervalued market capitalizations. Use this skill when users ask about undervalued stocks, value-investing screens, cheap A-share stocks, companies with low PE or PB, fundamentally strong but undervalued companies, or request a valuation screening.
Select and create the perfect AI voice for your content using ElevenLabs, Qwen3-TTS, and other platforms—matching voice characteristics to brand personality and audience. Use when: Choosing an AI voice for video narration; Creating a consistent brand voice across content; Cloning a voice for scalable production; Comparing voice synthesis platforms; Designing voice characteristics by description
Plan new YouTube videos with optimized titles, thumbnails, and hooks. Use when planning a video, writing or reviewing opening hooks, generating title and thumbnail concepts, or creating a production-ready video plan backed by research.
Zod v4 schema validation for TypeScript. Covers primitives, string formats, objects, arrays, unions, coercion, transforms, refinements, parsing, type inference, error customization, JSON Schema, file validation, and metadata. Use when writing schemas, validating input, parsing data, inferring types, or converting schemas with Zod.
Automate Alibaba Cloud Yunxiao DevOps tasks — create and run pipelines, manage code repositories and merge requests, track work items and sprints, create test cases, manage artifacts, and drive application release workflows across 8 Yunxiao products. Triggers: "Yunxiao", "DevOps", "pipeline", "code repository", "merge request", "work item", "sprint", "test case", "application delivery", "artifact repository", "Codeup", "Flow", "Projex", "AppStack", "Packages", "Testhub"
Comprehensive animation reference from iOS 13 through iOS 26. Use when implementing SwiftUI animations, understanding VectorArithmetic, using the @Animatable macro, zoom transitions, UIKit/AppKit animation bridging, choosing between spring and timing curve animations, or debugging animation behavior
Expert knowledge for Azure DNS development, including troubleshooting, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns. Use when automating DNS zones or records, configuring Private DNS or Resolvers, planning DNS migrations, enabling DNSSEC, and other Azure DNS development tasks. Not for Azure Traffic Manager (use azure-traffic-manager), Azure Load Balancer (use azure-load-balancer), Azure Application Gateway (use azure-application-gateway), or Azure Front Door (use azure-front-door).
Export the current Blender scene as a GLB and generate a ready-to-use Three.js HTML viewer with orbit controls, lighting, and auto-rotation. Trigger when asked to export for web, create a Three.js viewer, make a 3D model interactive for a website, or export from Blender for the web.
INTERNAL sub-agent for blind 7-dim rubric scoring. **NOT a user-facing skill — do NOT invoke from main conversation.** Called via Task tool by cheat-score / cheat-predict / cheat-bump to get a context-isolated score on a script. Receives ONLY script_path + rubric_notes_path; refuses any other input. Outputs strict JSON: 9 dimensions × {score 0-5, confidence enum, one-line reason}. **Hard refuses to Read** .cheat-state.json, predictions/*, retro 段, or anything that could leak post-publish data. This is channel B in the 3-channel calibration model (A=main, B=blind sub, C=cross-model).
Load this skill whenever the project contains text, UI components, icons, form controls, data visualisations, or focus indicators — in short, almost every project. Under no circumstances hard-code colour values without verifying contrast ratios. Absolutely always ensure text meets 4.5:1, large text meets 3:1, and non-text UI elements meet 3:1 against adjacent colours. Test in light mode, dark mode, and forced-colors (high contrast) mode.
Build scalable customer support systems including help centers, chatbots, ticketing systems, and self-service knowledge bases. Use when designing support infrastructure, reducing support load, improving customer satisfaction, or scaling support without linear hiring.
Enforces pubspec/lock discipline — caret ranges in pubspec.yaml with a committed pubspec.lock as the only pin, a separately-recorded SDK version string, a version-pinned very_good_analysis include (whose missing file fails default analyze, or silently drops the ruleset where warnings are non-fatal), transitive-tree auditing before adding a package, a dependency gate that refuses network/telemetry/crash/ads/heavy-transitive deps by policy, and vendoring any bus-factor-1 native plugin behind an interface into third_party/. Use when running dart pub add/get/upgrade/outdated/deps, editing pubspec.yaml or pubspec.lock, bumping the Flutter/Dart SDK, choosing or rejecting a new dependency, removing a package, or auditing what a dependency drags in.
Estimates a person's age from one selfie with Didit's standalone Age Estimation API (POST /v3/age-estimation/), which also runs a passive liveness check in the same call. Use when implementing an age gate, checking whether someone looks over 18 or 21, detecting underage users, or adding low-friction age assurance. Returns the estimated age, a liveness score and an Approved/Declined status against configurable age and liveness thresholds. Also covers the AGE_ESTIMATION workflow feature, where borderline ages fall back to ID verification and per-country age limits apply.
DingTalk AI Notes. Use when querying or editing note summaries, full transcripts, keywords, tags, minutes templates and default templates, action items, recordings, uploads, built-in mind maps, speaker insights, ASR hotword/recognition-term settings, or sharing permissions. For creating standalone .amind mind-map files and reading or writing their themes, use the mind reference in dingtalk-misc; for writing documents, use dingtalk-doc; for creating to-dos, use dingtalk-todo; for schedules, use dingtalk-calendar. Command prefix: dws minutes.
Use when asked to create an explainer, walkthrough, or board-work video, worked-example lesson, or mini-lesson for a math problem (including geometry, algebra, functions, and motion/行程 problems) from a screenshot or text, with Chinese voice-over. Deliver a browser preview (HTML) first; export MP4 only if requested. Choose from five visual templates: hand-drawn canvas animation with bilingual zh+en subtitles, or one of four board styles (chalkboard, geometry lab, whiteboard, or graph-paper notebook, with auto-rotating 3D figures). Choose a TTS engine: 智谱 GLM-TTS, 豆包 Doubao, MiniMax, or free edge-tts / macOS say
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use improve-animations or review-animations instead.
Interpret the expectation gap, event implications, and intraday risk points behind gap-up and gap-down openings. Use to assess direction after the opening auction, evaluate the credibility of a gap, and distinguish a strong open from sentiment exhaustion.
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration, CLI tools, benchmarks, or table-driven testing.
Design and optimize self-reinforcing growth systems using the Reforge methodology—shift from linear funnels to compounding loops where outputs become inputs for sustainable, defensible growth. Use when: **Analyze your current growth model** and identify if you have a loop or funnel; **Design a growth loop** for a new product or feature; **Diagnose why growth isn't compounding** despite acquisition efforts; **Identify the right loop type** for your business model; **Optimize loop velocity** to acc...
Expert patterns for HubSpot CRM integration, including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs. Use when: hubspot, hubspot api, hubspot crm, hubspot integration, contacts api.
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
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.