Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
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).
Analyze and optimize metadata for Next.js projects, including title, description, Open Graph and Twitter Cards. Automatically detects App Router or Pages Router, and offers length suggestions, keyword optimization and best-practice guidance. Supports bilingual Chinese/English SEO analysis.
Decomposes complex, multi-day tasks into optimized milestones (ultraplan). Broad parallel exploration grounds a draft milestone DAG, then independent adversarial critics attack the draft in rounds until no blocking findings remain. Triggers when the user says "plan milestones", "break this into milestones", "ultraplan", or when long-run harness needs milestone generation.
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.
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling `connect()`), configuring connection pools, troubleshooting connection errors (ECONNREFUSED, timeouts, pool exhaustion), optimizing performance issues related to connections. This includes scenarios like building serverless functions with MongoDB, creating API endpoints that use MongoDB, optimizing high-traffic MongoDB applications, creating long-running tasks and concurrency, or debugging connection-related failures.
Recognize and apply the monoid abstraction (binary associative operation + neutral element) in Clojure/ClojureScript code. Use whenever the user is combining, aggregating, merging, or reducing data — metrics and counters, event logs, config objects, or any `reduce`/`fold`/`merge-with` over a collection — even if they don't use the word "monoid". Also use when reviewing code that special-cases empty lists/collections, when discussing Map-Reduce or parallel aggregation (including `pmap`-based reduction), or when designing a generic `combine`/`merge`/`empty` API instead of ad hoc merge logic. Trigger this for "how do I merge these two X" or "what's a clean way to aggregate Y" style questions, not just explicit monoid/algebra questions. For TypeScript idioms, route to the `typescript` skill instead.
Use when building applications, bots, SDKs, or integrations against the Morpho lending protocol — deposits, borrows, repays, withdrawals, vault v1/v2 integrations, V1→V2 migration flows, risk monitors, portfolio dashboards. Steers toward `@morpho-org/morpho-sdk` (`MorphoClient`) for user-facing transactions and flags uncovered flows (curator ops, market creation, liquidations, flashloans, rewards) that need lower-level SDKs. Invoke whenever a user mentions Morpho, MetaMorpho, Morpho Blue, or any on-chain integration touching these contracts — even if they don't name morpho-sdk explicitly.
Design NATS subject hierarchies for messaging patterns (pub/sub, request/reply, streaming). Apply naming conventions, segmentation strategies, and wildcard patterns to create scalable subject architectures. Use when designing NATS messaging systems, choosing account-vs-subject namespace boundaries for multi-tenant communication, designing export/import subjects, or auditing existing subject hierarchies. Do not use for: (1) NATS server or account provisioning, (2) cluster setup, (3) client library implementation or connection code, (4) debugging connectivity or performance issues, (5) choosing between NATS and other messaging systems.
Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.
Capture exceptions and promise failures with `neverthrow` instead of hand-written `try/catch` in TypeScript and JavaScript code. Use when wrapping synchronous functions that may throw, promise-returning functions that may throw before returning, existing `PromiseLike` values that may reject, or third-party APIs such as parsers, database clients, HTTP clients, file-system helpers, serializers, and SDK calls. Prefer `Result.fromThrowable` for synchronous throwers, `ResultAsync.fromThrowable` for promise-returning functions that may throw or reject, and `ResultAsync.fromPromise` when you already have a `PromiseLike` value in hand. Only keep `try/catch` when the language construct, cleanup requirement, or framework boundary truly requires it.
Guide for creating Nushell plugins in Rust using nu_plugin and nu_protocol crates. Use when users want to build custom Nushell commands, extend Nushell with new functionality, create data transformations, or integrate external tools/APIs into Nushell. Covers project setup, command implementation, streaming data, custom values, and testing.
Nuxt GEO (Generative Engine Optimization) guidelines for getting cited by ChatGPT, Perplexity, Claude, Google AI Overviews, and Gemini. Covers AI crawler access (llms.txt, GPTBot/ClaudeBot/PerplexityBot allowlisting), content extractability for RAG retrieval, entity clarity via JSON-LD, and the evidence-backed +40% visibility levers (statistics, citations, quotations) from the GEO arxiv paper. Triggers on tasks involving GEO, AEO, AI search, LLM visibility, llms.txt, AI crawlers, ChatGPT citations, Perplexity, AI Overviews, generative engines, or AI mentions.
Odoo OWL frontend engineering guidance covering components, templates, reactivity, hooks, props, plugins, registries, debugging, assets, and OWL 1/2/3 migration. Use when working with Odoo frontend components, @odoo/owl, static/src JavaScript/XML templates, signals, proxy, props, t-on, t-ref, t-model, registries, plugins, or OWL migrations.
Receive and verify Okta Event Hooks. Use when setting up Okta event hook handlers, implementing the one-time verification challenge, authenticating requests with the Authorization header secret, or handling identity events like user.lifecycle.create, user.session.start, user.account.lock, or group.user_membership.add.
Use when the user wants to iteratively improve an artifact under a hard correctness bound while minimizing a measured cost — refactoring a code module to cut complexity while its test suite stays green, OR speeding up a SQL query while it returns the same rows. Each iteration applies one focused change, checks a correctness gate that must pass, measures a metric that must drop, and keeps the change only if both hold, else reverts; loops to a plateau or budget. Not for adding features, fixing bugs, or any change that is allowed to alter behaviour or results.
Review and optimize application data access that uses Entity Framework Core (EF Core). Use for EF Core performance and correctness reviews of services, repositories, imports, and background jobs: slow or memory-heavy queries, excessive round-trips, hidden SaveChanges, premature materialization, dynamic query construction, result-graph tracking, bulk writes, DbContext lifetime or overlapping operations, search semantics, paging, raw SQL, and model/index coverage. Use whether or not EF Core owns the schema. For EF Core, not Dapper or raw ADO.NET.
Design and audit partner integration ecosystems, APIs, app directories, OAuth flows, webhooks, SDKs, partner onboarding, certification, co-marketing, revenue share, support boundaries, abuse controls, and ecosystem health. Use when a product depends on third-party integrations, platform partners, developer apps, marketplace listings, or strategic distribution channels.
Build multimodal AI apps with Pixeltable. One application file (app.py) declares TableModel tables and FastAPIRouter routes. Create tables with pxt schema update. Start HTTP with pxt service update. Insert a row or POST to try the app. Use computed columns instead of LangChain, pandas-as-store, or a separate vector DB. Use when building RAG or tool-calling agents, processing images/video/audio/documents, or serving an API. Do NOT use for general Python or direct PostgreSQL administration.
Plans a Phase 1 Jira ticket or GitHub issue snapshot into staged, validated Phase 2 task-plan artifacts with deterministic branch names. Use when an orchestrator or user asks to decompose docs/<KEY>.md, plan Jira tasks, plan GitHub issue tasks, or re-plan a work item after critique. Does not fetch work items, create subtasks or child issues, implement tasks, or mutate the work-item platform.
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
Use when breaking a large, complex, messy, or hard-to-review pull request into multiple smaller PRs; planning stacked PRs; extracting independent changes from a branch; splitting mixed refactor and behavior changes; managing drift after review feedback; rebasing follow-up PRs as earlier PRs change; or preserving original branch intent while shipping incrementally.
Systematic problem-solving techniques for stuck-ness. Techniques: simplification cascade (complexity spirals), collision-zone thinking (innovation blocks), meta-pattern recognition (recurring issues), inversion exercise (assumption constraints), scale game (uncertainty). Actions: simplify, analyze, recognize patterns, invert assumptions, scale thinking. Keywords: problem solving, complexity spiral, innovation block, stuck, simplification, meta-pattern, assumption inversion, scale uncertainty, breakthrough thinking, root cause, systematic analysis, Microsoft Amplifier, debugging approach, creative solution. Use when: complexity spiraling, hitting innovation blocks, seeing recurring patterns, constrained by assumptions, uncertain about scale, generally stuck on problems.
Multi-phase iterative project analysis with Mermaid diagrams. Generates architecture reports, design reports, method analysis reports. Use when analyzing codebases, understanding project structure, reviewing architecture, exploring design patterns, or documenting system components. Triggers on "analyze project", "architecture report", "design analysis", "code structure", "system overview".
Comprehensive project planning and documentation generator for software projects. Creates structured requirements documents, system design documents, and task breakdown plans with implementation tracking. Use when starting a new project, defining specifications, creating technical designs, or breaking down complex systems into implementable tasks. Supports user story format, acceptance criteria, component design, API specifications, and hierarchical task decomposition with requirement traceability.
Use when building or reviewing service, job, or CLI runtime behavior in Python — designing startup validation, shutdown sequences, observability, and structured logging. Also use when startup crashes from late config, shutdown leaves orphaned processes, terminal states are implicit, or logs lack structure.
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and human approval. Use for: Python integration, AI apps, agent development, RAG pipelines, automation. Triggers: python sdk, inferencesh, pip install, python api, python client, async inference, python agent, tool builder python, programmatic ai, python integration, sdk python
[Hyper] Analyze vague or relayed non-developer stakeholder requests (client, executive, PM, sales/support) by mapping them to codebase impact, presenting interpretation candidates with risks, then implementing only after confirmation. Use for stakeholder-message analysis, not browser QA testing, CI/build failures, or already-clear technical tasks.
Use when implementing animations, transitions, or motion effects in React apps. Invoke this skill whenever someone asks about animation, transition, motion, framer motion, react spring, GSAP, entrance/exit effects, scroll animation, parallax, gesture, drag, card flip, screen shake, health bar, damage numbers, loading states, page transitions, hover effects, or any element that should move, fade, scale, or respond to interaction — even if they don't use the word "animation".
Write and refactor React components to be small, composable, and customizable, doing one thing well. Improve rendering performance, maintainability, and reusability by leveraging compound components, prop spreading, and utility class merging. Apply these patterns when authoring new components or breaking down large monolithic ones.
React Native mobile development. Core components, navigation (React Navigation), platform-specific code, native modules, performance optimization, and debugging. USE WHEN: user mentions "React Native", "react-native", "mobile app with React", "cross-platform mobile", "RN", "react-native-cli" DO NOT USE FOR: Expo-specific features - use `expo`; Flutter - use `flutter`; web React - use `react` skills
React Native ecosystem — navigation, state, data fetching, Reanimated, storage, TypeScript patterns, accessibility, and deep linking. Use when building production React Native apps with React Navigation, Zustand, TanStack Query, or Reanimated v3.
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.