Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Expert guide for Glove primitives and packages such as glove-core, glove-facts, dynamic goals, form preparation, glove-react, glove-next, tools, display, models, stores, memory, voice, image, and working environments. For full agent applications, runtime orchestration, or migration from deprecated Glovebox, use the glove-foundry skill.
Go development patterns, concurrency, error handling, testing, and project structure. Use for: golang, go, goroutine, channel, context, errgroup, go test, go mod, go build, interface, generics, table-driven tests, worker pool, sync.Mutex, sync.WaitGroup, pprof, go vet, golangci-lint, go workspace, functional options, middleware, http handler.
Godot 4.x SOLID design, typed signals, command objects, undo/redo, and object pooling. Use when refactoring tightly coupled GDScript, splitting monolithic scene behavior, replacing polling with signals, representing actions for queues or history, or reducing measured spawn/free churn.
Build or review Astro animation: GSAP page transitions, ClientRouter swap hooks, persisted islands, repeated setup, and cleanup. Use for missing or duplicated motion after navigation and choosing transition:animate versus GSAP. Without ClientRouter, use gsap-vanilla. Also covers hidden-content recovery and first-load performance. Not for standalone island frameworks or isolated GSAP API questions.
This skill should be used when users need help with htmx development, including implementing AJAX interactions, understanding htmx attributes (hx-get, hx-post, hx-swap, hx-target, hx-trigger), debugging htmx behavior, building hypermedia-driven applications, or following htmx best practices. Use when users ask about htmx patterns, server-side HTML responses, or transitioning from SPA frameworks to htmx. (user)
Convert SPEC.md to spec.json, craft the implementation prompt, and execute the iteration loop via subprocess. Use when converting specs to spec.json, preparing implementation artifacts, running the iteration loop, or implementing features autonomously. Triggers: implement, spec.json, convert spec, implementation prompt, execute implementation, run implementation.
Inkblot Jira ticket writing convention. Use whenever creating, drafting, editing, or reviewing a Jira ticket on inkblottherapy.atlassian.net (POD1, POD2, or any pod) — Tasks, Stories, Bugs, Spikes, and Sub-tasks. Ensures consistent structure and discoverable acceptance criteria for QA.
IntelliJ Platform plugin development with the v2 SDK / IntelliJ Platform Gradle Plugin 2.x. Trigger for plugin code in JetBrains IDEs involving plugin.xml, org.jetbrains.intellij.platform, AnAction, PSI, extension points, Inspection/CompletionContributor, ParserDefinition, ToolWindowFactory, PersistentStateComponent, plugin verifier, Marketplace publishing, custom language support, Gradle plugin 2.x setup/migration, ConfigurationType, live templates/postfix completion, IconLoader/AllIcons, IDE theme, LSP/MCP integration, <idea-plugin>/<depends>/<applicationListeners>, dynamic plugin requirements, JCEF/JBCefBrowser/JBCefJSQuery/webview, or pluginIcon. Do not trigger for general JetBrains IDE usage, ordinary run configurations, generic Gradle/logging, or language-server discussions outside plugin-dev context.
Jimmer ORM development assistant that helps write entity mapping code and DSL queries. Use for: (1) defining or modifying Jimmer entities (interfaces annotated with @Entity); (2) writing Jimmer DSL query code; (3) configuring entity associations (@ManyToOne, @OneToMany, @ManyToMany); (4) using dynamic predicates, dynamic table joins, or implicit subqueries; (5) editing Java/Kotlin files containing Jimmer-related code.
JSDoc - documentation generator for JavaScript with type annotations. USE WHEN: user mentions "JSDoc", "JavaScript documentation", asks about "documenting JavaScript", "type hints", "jsdoc comments", "API documentation generation" DO NOT USE FOR: TypeScript - use `jsdoc-tsdoc` skill for TypeScript/TSDoc
Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation. Use when implementing features, modifying code, or when you notice yourself about to make changes without reading the existing code first.
Build tool for all new Kotlin projects. How to build, run, test, package, lint/check/verify, manage dependencies, and configure Kotlin/Java projects with Kotlin Toolchain — JetBrains' unified Kotlin CLI (formerly Amper, now the engine inside the Toolchain). TRIGGER when the repo contains `project.yaml`, `module.yaml`, or a `./kotlin` wrapper; when starting a new/greenfield Kotlin or Java project or picking its build tool ("create/start/scaffold/bootstrap a Kotlin project", "new Kotlin app/library/service", `kotlin init`); when the user asks to build/run/test/package a Kotlin project, add or remove dependencies, run lint/check/verification, or otherwise configure a Kotlin project that doesn't use Gradle/Maven; or when the user references Kotlin Toolchain or Amper. SKIP for existing Gradle/Maven Kotlin projects.
Product PRD generation tool. Combining the product storytelling methodology of 《创造》, the positioning framework of product-position, and the PRD best practices of Lenny's Newsletter, it helps you turn an idea into an actionable product requirements document. Triggers: /li-prd, "help me write a PRD", "generate a requirements document", "write a product doc", "turn this idea into a PRD", "hackathon PRD", "organize product requirements", "I'm about to start building, help me clarify the requirements". Even if the user doesn't say "PRD", this skill should trigger whenever they want to turn a product idea into an actionable document. DO NOT trigger for: content creation tasks such as content script generation, topic analysis, or data review.
Use when selecting, replacing, pinning, or auditing an Arduino, ESP32, RP2040, C++, or vendor-framework library. Compare architecture support, framework and version compatibility, API behavior, footprint, maintenance, provenance, security, and hardware assumptions before installation.
Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when the user asks for llms.txt, LLM discovery plans, visible TLDR or direct-answer blocks, source trails, entity pages, markdown alternates, AI crawler policy, topic-to-URL maps, assistant-readable public content, or LLM-friendly architecture that must preserve canonical SEO strategy without hidden bot-only facts or duplicate story bodies.
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.
Enforce low Cognitive Complexity (SonarSource) and low Cyclomatic Complexity in ALL code written or modified, in any programming language, framework, or platform. This skill MUST activate automatically whenever code is being written, generated, modified, or refactored — no explicit trigger needed. Triggers include writing any function, method, class, module, script, handler, endpoint, test, or code block. Also triggers on "low complexity", "cognitive complexity", "cyclomatic complexity", "reduce complexity", "simplify code", "too complex", "refactor for readability", "clean code", "implement", "fix bug", "add feature", "generate test", "optimize", "rewrite", "scaffold".
CRITICAL: Use for Makepad 2.0 animation system. Triggers on: makepad animation, makepad animator, Animator, AnimatorState, hover effect, makepad transition, animation state, Forward, Snap, Loop, ease function, makepad animate, timeline, snap(), default @off, animation group, 动画, 过渡, 悬停效果, 动画状态, 缓动函数
CRITICAL: Entry-level skill for Makepad 2.0 GUI development. This is the FIRST skill to load for any Makepad task — it provides design judgment anchors ABOVE the other 13 Makepad 2.0 skills. Triggers on: makepad, makepad app, makepad project, makepad design, live_design!, app_main!, script_mod!, Cx, WidgetRef, Widget, makepad-widgets, makepad architecture, makepad how to, "how should I", "should I use", "what's the best way", makepad 架构, makepad 设计, makepad 怎么做, makepad 最佳实践, 组件拆分, 状态管理, 数据流, 渲染思维
CRITICAL: Use for migrating from Makepad 1.x to 2.0. Triggers on: makepad migration, live_design to script_mod, makepad upgrade, makepad 1.x, old syntax, new syntax, makepad breaking changes, makepad 迁移, 旧语法, LiveHook to ScriptHook, apply_over to script_apply_eval, Live to Script, live_design!, angle brackets to curly braces
CRITICAL: Use for Makepad 2.0 Vector graphics widget. Triggers on: makepad vector, Vector widget, SVG path, makepad path, makepad circle, makepad gradient, makepad tween, vector animation, Gradient, RadGradient, Filter, DropShadow, Group transform, vector drawing, inline SVG, 矢量图形, SVG, 路径, 渐变, 矢量动画
Development guidelines and patterns for building React component libraries with Mantine UI, TypeScript, and modern tooling. Use this skill when creating, editing, or maintaining Mantine-based React components, implementing Styles API patterns, managing component composition, or working with TypeScript-safe component factories.
Configure, manage, and troubleshoot markdownlint in projects. Use when user wants to setup/install/configure markdownlint, add/remove/modify linting rules, fix markdown validation issues, customize .markdownlint.yaml, update ignore patterns, integrate with tools (Husky, CI), or troubleshoot markdown linting errors. Use even when user mentions markdown formatting problems, quality issues, or style consistency without explicitly saying "markdownlint".
Reference for MATLAB audiostreamer (Audio Toolbox R2025a+). Without this skill, agents consistently default to legacy audioDeviceWriter/audioDeviceReader or base MATLAB sound(), producing less capable code. Use when writing code for audio playback, recording, full-duplex device I/O, real-time audio measurements, or audio I/O processing with callbacks. Also use when debugging audiostreamer errors, dropouts, or latency issues, or migrating from audioDeviceReader, audioDeviceWriter, audioPlayerRecorder, or audioplayer/audiorecorder.
Upgrade C, C++, and Fortran MEX source files from the Separate Complex (SC) API to the Interleaved Complex (IC) API. Use when converting mxGetPr/mxGetPi to mxGetComplexDoubles, migrating MEX files to -R2018a, adding MX_HAS_INTERLEAVED_COMPLEX guards for SC/IC guarded builds, or modernizing legacy MEX code that uses mxGetData/mxSetData/mxGetImagData/mxSetImagData. Covers C (.c), C++ (.cpp, .cxx), and Fortran (.F, .f90) MEX functions. Triggers on: interleaved complex, IC MEX, mex upgrade, mex migration, separate complex, mxGetPi, mxGetPr replacement, -R2018a, complex MEX, Fortran MEX, .F MEX file, C++ MEX, .cpp MEX file, MEX performance, MEX slow complex, MEX call overhead, improve MEX performance complex.
MatrixScan AR (Barcode AR, BarcodeAr) in web/browser (TypeScript/JavaScript) projects (@scandit/web-datacapture-barcode) — scanning multiple barcodes at once with AR overlays, highlights, and annotations on tracked barcodes. Use for integration, symbology configuration, highlight and annotation providers, session handling, migration from BarcodeBatch, or troubleshooting.
Guide for making .NET MAUI apps accessible — screen reader support via SemanticProperties, heading levels, AutomationProperties visibility control, programmatic focus and announcements, and platform-specific gotchas for TalkBack, VoiceOver, and Narrator. USE FOR: "add accessibility", "screen reader support", "SemanticProperties", "AutomationProperties", "TalkBack", "VoiceOver", "Narrator", "accessible MAUI", "heading levels", "semantic description", "announce to screen reader", "accessibility audit". DO NOT USE FOR: general UI layout (use maui-collectionview or maui-shell-navigation), animations (use maui-animations), or gestures (use maui-gestures).
Add local notifications to .NET MAUI apps on Android, iOS, and Mac Catalyst. Covers notification channels, permissions, scheduling, foreground/background handling, and DI registration. Works with XAML/MVVM, C# Markup, and MauiReactor. USE FOR: "local notification", "schedule notification", "notification channel", "notification permission", "reminder notification", "alert notification", "in-app notification", "foreground notification". DO NOT USE FOR: push notifications from a server (use maui-push-notifications), permission handling only (use maui-permissions), or app lifecycle background tasks (use maui-app-lifecycle).
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.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
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.