Skills
97,725 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use alongside the `hardhat` skill when the project depends on `@nomicfoundation/hardhat-toolbox-mocha-ethers`. Covers the ethers helpers exposed on `network.create()`, contract interaction (`ethers.deployContract`, calling functions, `connect`), TypeChain-typed contract instances, and the chai matchers from `@nomicfoundation/hardhat-ethers-chai-matchers` (`.to.emit`, `.to.be.revertedWith*`, `.to.changeEtherBalance(s)`).
Discover product ideas, validate them, and build MVPs. Search trending tools across Product Hunt, GitHub, Indie Hackers, XiaoHongShu, V2EX, SSPAI, etc. Validate feasibility via market research and competitive analysis. Build MVPs. Send reports via email. Triggers: 'find ideas', 'search products', 'trending tools', 'product ideas', 'validate my idea', 'build MVP', 'market research', 'competitive analysis', 'indie hacker', 'send email', '找想法', '搜产品', '找灵感', '产品调研', '验证想法', '构建MVP', '发邮件', '发送报告'.
Use this skill whenever the user needs to generate, edit, or integrate AIGC images or videos with imini Open Platform — text-to-image, image editing with references, text-to-video, image-to-video, first/last frame, reference video, motion control, video editing, or multimodal generation. Two paths — (A) ad-hoc one-shot generation right now via bundled Python scripts (no codegen, no token burn for re-deriving submit/poll logic); (B) writing async integration code into the user's own project. Triggers on mentions of imini, openapi.imini.ai, or any imini model id (nano-banana, nano-banana-pro, nano-banana-2, gpt-image-2, kling-v3, kling-v3-omni, kling-v3-motion-control, seedance-2.0, seedance-2.0-fast, happyhorse-1.0).
Standards for implementing and reviewing React/TypeScript/Next.js features in codebases that use React Hook Form, Zod, React Query or Connect Query, and proto-generated API types. Use when building frontend forms, hooks/components, state flows, and type-safe UI mappings in this stack.
Use for all repository edits and their planning, including simple code, documentation, configuration, and test changes. Also use to choose the next task from a tracker, continue work, recover context, or split implementation into tasks. Review-only and publication-only requests are outside this workflow.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Implements the Schnorr identification protocol and a simplified Zero-Knowledge Password Proof (ZKPP) over the discrete logarithm problem, letting a prover authenticate by demonstrating knowledge of a secret without ever revealing it to the server. Use when designing or building password-less or password-secret-free authentication, or when a server must verify a user's credential without learning or storing the underlying secret.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Resolve a natural-language element description ("the red button in the hero", "the third card from the top") to a concrete DOM element in the current preview + source-code location. Uses Chrome DevTools MCP take_snapshot UIDs for deterministic targeting. Use when user asks to change/style/remove a specific visual element without pointing at source code.
Control interactive terminal applications like vim, git rebase -i, git add -i, git add -p, apt, rclone config, sudo, w3m, and TUI apps. Can also supervise another CLI LLM (cursor-agent, codex, etc.) - approve or reject its actions by pressing y/n at confirmation prompts. Use when you need to interact with applications that require keyboard input, show prompts, menus, or have full-screen interfaces. Also use when commands fail or hang with errors like "Input is not a terminal" or "Output is not a terminal". Better than application specific hacks such as GIT_SEQUENCE_EDITOR or bypassing interactivity through file use.
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.
Six small Capacitor plugins bundled — Camera, Filesystem, Share, Haptics, Network, Keyboard. Trigger when adding photo upload, file save/read, native share sheet, haptic feedback, network status detection, or keyboard handling to an Ionic Capacitor app.
Software development engine for coding. A production-grade skills system for web apps and mobile architecture, APIs, databases, web, mobile, AI, security, UX, SaaS, and ERP engineering. Encodes reusable engineering judgment through layered baseline and specialist skills to help generate secure, scalable, maintainable, high-performance software systems
Use when building or modifying Jigx Core SDK apps, including screens, forms, datasources, tabs, navigation, local dynamic data, media, PDFs, JavaScript functions, validation, icons, and build/deploy workflows. This skill is generic and should be used before writing Jigx app code.
Use when writing, reviewing, debugging, or documenting LanceDB pipelines in Python or TypeScript, especially code that should work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables. Helps avoid non-portable full-table materialization, choose idiomatic query/search patterns, apply LanceDB performance defaults for ingestion, indexing, filtering, and diagnostics, and resolve connections to the remote server for Enterprise-only operations such as jobs.
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
Build, review, debug, migrate, or plan Legend-State v3 applications with current docs. Use for @legendapp/state v3 beta (3.0.0-beta.48), observable, useValue, observer, Memo, $React, useObservable, computed or linked observables, observe, when, batch, fine-grained React rendering, React Native, local persistence, syncObservable, synced, syncedCrud, syncedFetch, syncedQuery, Supabase, Firebase, Keel, offline-first sync, transforms, syncState, testing, performance, and v2-to-v3 migrations.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Make websites, docs, blogs, or landing pages visible and readable to LLMs and AI agents — ChatGPT, Claude, Perplexity, Cursor, Claude Code, and other coding agents that fetch URLs. Use this for any request involving llms.txt, llms-full.txt, serving .md/Markdown versions of pages, Accept text/markdown content negotiation, Link rel="alternate" headers, Cloudflare Content-Signal in robots.txt, GEO (generative engine optimization), AI-friendly / AI-readable / LLM-discoverable sites, getting cited in ChatGPT or Perplexity answers, or fixing pages where AI tools fetch JavaScript bundles or empty React roots instead of content. Also use to push back on debunked patterns: ai.txt, AI meta tags, hidden HTML comments, AI toggle buttons, User-Agent sniffing, JSON-LD aimed at LLMs. Do NOT use for traditional Google SEO, sitemap.xml, schema.org rich snippets for search engines, WCAG/accessibility audits, or CSP/security headers.
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
Use when the user asks to build a project end-to-end, run autonomous multi-hour or multi-day development, or orchestrate multi-milestone work without human intervention. Trigger phrases include "build this whole project", "implement this end-to-end", "do this autonomously", "run a long task", "long-running agent", "build it from scratch and don't ask", "/long-task", or "$long-task". Also use for lifecycle subcommands such as `/long-task status`, `/long-task pause`, `/long-task resume`, `/long-task clear`, and `/long-task complete`.
Build industrial-grade SCADA/HMI dashboards in MATLAB following industrial-HMI conventions (ISA-101-aligned): gray-field philosophy, alarms at source, write safeguards, fixed-range trends, drill-down layout. Produces a real App Designer app (.mlapp, or plain-text .m+.xml on R2026b+) by handing serialization to the matlab-build-app skill when available, and falls back to a programmatic .m app otherwise. Use when wrapping OPC UA / Modbus / MQTT / OSI PI / PI AF monitoring scripts into a live operator app, building plant overviews, designing operator dashboards, or any time a user asks for a "SCADA dashboard", "HMI", "plant dashboard", "operator screen", or "industrial monitoring app" in MATLAB. Trigger on: SCADA, HMI, industrial dashboard, plant overview, operator screen, uigauge, uilamp, alarm banner, gray-field, ISA-101, OPC UA dashboard, setpoint, write safeguards, alarm visualization, OSIsoft PI, AVEVA PI, PI Server, PI Data Archive, PI AF, PI Asset Framework, piclient, afclient.
Provides comprehensive guidance for searching and retrieving Maven components from Maven Central Repository (https://repo1.maven.org/maven2/). This skill enables searching by groupId, artifactId, version, and other coordinates, retrieving component metadata (POM files, JARs, sources, Javadoc), querying version history, and analyzing dependencies. Use when the user needs to find, verify, or retrieve Maven dependencies, check component versions, analyze dependency trees, or work with Maven coordinates.
Bootstrap or maintain MkDocs Material docs sites with GitHub Pages, strict two-pass i18n plus default-language llms.txt, copy-to-LLM, page/nav helpers, and zh-TW translation. Use when setting up or publishing docs, adding bilingual or multilingual docs, repairing nearly empty llms.txt or i18n strict-build failures, or migrating an older mkdocs-site-bootstrap site. Consent-gated; never rewrites existing docs without approval.
Guided workflow for taking any ML codebase — including one with no experiment tracking at all, or one full of MLflow 2-era idioms — to a production-grade open-source MLflow 3 setup with dev/staging/prod environments, registry-based promotion, and served models. Walks seven phases with a developer who may have zero MLflow 3 experience — assess the codebase (scripted read-only audit), model the registry domain (per-environment model names, aliases, gates), stand up tracking per environment, restructure training code to MLflow 3 idioms, wire evaluation-gated promotion, serve and smoke-test, then run the ongoing MLOps loop. Use when asked to set up MLflow, migrate to MLflow 3, productionize model training and serving, or design a dev/staging/prod MLOps cycle. Pairs with the sibling mlflow-3 rule pack for every API decision.
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
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.