Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Create, configure, and use Frontic blocks, listings, and pages for e-commerce data. Use when working with Frontic configuration, building product/category pages, creating data sources, or integrating the Frontic client. Covers resource decision-making, block/listing creation guidelines, and client usage patterns.
Load PROACTIVELY when task involves building a complete feature across multiple layers. Use when user says "build a feature", "add user profiles", "create a dashboard", or any request spanning database, API, UI, and tests. Orchestrates multi-agent work sequentially: schema and migrations, API endpoints, UI components, tests, and review. The runtime engine handles WRFC chains automatically via <gv> directives. Handles dependency ordering and cross-layer type sharing.
Game feel consulting based on Steve Swink's "Game Feel: A Game Designer's Guide to Virtual Sensation" (Morgan Kaufmann, 2009). Use when helping with control responsiveness, input mapping, physics tuning, avatar movement, jump mechanics, polish effects, or analyzing why controls feel "floaty", "tight", "responsive", or "sluggish". Covers the psychology of real-time control, metrics for measuring feel, and practical tuning guidance. NOT for general game design - focused specifically on the tactile sensation of controlling virtual objects.
A professional solution architect assistant offering guidance across system architecture design, technology selection, architecture review, and performance optimization. Applies to designing new system architectures, reviewing existing architectures, technology selection decisions, architecture refactoring, performance optimization, and microservice design. Combines web search to learn the latest technology trends and provides architecture recommendations based on 2025 best practices, covering modern architecture patterns such as microservices, event-driven, cloud native, and AI architecture.
Master advanced Git workflows—including rebasing, cherry-picking, bisect, worktrees, and reflog—to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
Smart Git batch-commit shortcut. Trigger words: "git 提交", "批量提交", "拆分提交", "整理提交", or when the user explicitly wants to split staged changes into multiple focused commits. Only handles commit splitting and commit message generation; branch, PR, push, merge and Issue-closing semantics follow git-workflow. After the commit completes, if the repository has skill-publish-sync or subtree-publish configuration, or is registered in this skill's config/subtree-repos.yaml (which customizes trigger timing and push commands per repository), this skill will prompt whether to publish the affected version-updated skills to ClawHub/SkillHub or push the standalone subtree repository — all such publish/push actions require explicit user confirmation.
Build and maintain local code-project wikis under .wiki or language-specific wiki roots such as .wiki-cn and .wiki-fr. Use this skill whenever the user mentions "wiki", "ingest", "refresh wiki", "update wiki", "lint wiki", "check wiki", "document the codebase", "export wiki", "bundle wiki", "archive wiki", or asks a question that can be answered from wiki pages. Also use it when the user asks how something works in the project and a wiki page could capture the answer for future reference.
Fetch, categorize, and summarize GitHub Trending projects across daily, weekly, and monthly spans. Use when a user asks for "trending projects", "latest hot repos", or a "summary of GitHub trends" to provide a structured, categorised report with full hyperlinking. Supports Markdown, HTML (Pinterest design), or both output formats, with optional Obsidian vault storage.
Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state, context management, verification, recovery, and bounded autonomous loops. Use for unreliable coding agents, cross-session drift, premature completion, harness audits, or changes to the runtime around a model, including bounded typed-decision routing. Do not use for prompt rewriting alone, model training, general application architecture, or operating an already evaluated agent in production; route those concerns to their specialist skills.
Intelligently compile the ability_runtime component, automatically determining build targets by detecting modified files. Supports compiling multiple targets together, automatic retry decisions, and intelligent error analysis. Trigger keywords: "编译", "构建", "compile", "build", "make", "make file".
Diagnose and fix failing GitHub Checks on PR work by default: fetch evidence, write ephemeral ci-fails report, apply fixes, verify locally. Run automatically — do not wait for user to ask. Never merge without authorize merge. Companion to /heyeddi fails.
Write Rust that reads like Rust — iterator pipelines over index loops, From/Into over ad-hoc converters, derives over hand-written impls, newtypes over bare primitives. Use when writing new Rust, when reviewing Rust that reads like a translation from another language, or when the user asks how to make Rust code more idiomatic or less repetitive.
Turns an unfiled idea into a confirmed mini-spec, implements the selected approach, repeats code review and black-box testing, runs the project gate, and opens a draft pull request. Use when the user runs /implement-idea or asks to build something without an existing issue.
Implement integration-ready UI code from a Figma selection or a provided nodeId using TemPad Dev MCP as the only source of design evidence (code snapshot, structure, assets, tokens, codegen config). Detect the target repo stack and conventions first, then translate TemPad Dev's Tailwind-like JSX/Vue IR into project-native code without adding new dependencies. Never guess key styles or measurements. If required evidence is missing/contradictory or assets cannot be handled under repo policy, stop or ship a safe base with explicit warnings and omissions.
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.
Futu OpenD installation assistant. Automatically downloads and installs Futu OpenD and upgrades the Python SDK. Supports Windows, MacOS and Linux. Use automatically when the user mentions installing, downloading, starting, running or configuring OpenD, a development environment, upgrading the SDK, or futu-api.
Builds, reviews, debugs, migrates, secures, tests, and implements Filament 5.x using the project's installed version and official components before custom Blade or CSS. Use for Filament resources, schemas, infolists, forms, tables, actions, widgets, relation managers, panels, tenancy, imports/exports, plugins, APIs, namespaces, Artisan commands, upgrades, and security reviews. Do not trigger for visual-only polish, layout or composition decisions, theme-preserving UI presentation work, or an isolated mention of admin panel, dashboard, or badge without another Filament signal.
Refactor module-level imports of heavy native dependencies (torch, tensorflow, jax) to function-internal lazy imports. Use when a library import triggers SIGSEGV or slow startup in environments where the native dep cannot fully initialize (e.g., CUDA driver absent, triton C-extension segfault, missing GPU). Predicts test-side effects from removed module attributes.
Provides comprehensive guidance for Lime ECharts including chart creation, configuration, data visualization, and interactive charts. Use when the user asks about Lime ECharts, needs to create charts, visualize data, or work with ECharts features.
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
Project Lombok for reducing Java boilerplate. Covers annotations for getters, setters, constructors, builders, logging, and more. Based on production patterns from castellino and gestionale-presenze projects. USE WHEN: user mentions "lombok", "@Data", "@Builder", "@Slf4j", asks about "boilerplate reduction", "getters/setters", "@RequiredArgsConstructor", "@Value" DO NOT USE FOR: Java language features - use `java` skill instead DO NOT USE FOR: MapStruct integration - use `mapstruct` skill DO NOT USE FOR: Spring annotations - use `backend-spring-boot` skill
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.
CRITICAL: Use for Makepad 2.0 performance optimization and debugging. Triggers on: makepad performance, makepad debug, makepad profiling, makepad gc, new_batch, texture_caching, render optimization, draw batching, mod.gc, garbage collection, memory, debug logging, troubleshoot, ViewOptimize, PortalList, CachedView, render tree, invisible text, text disappears, UI freezes, scroll stuttering, 性能, 调试, 优化, 垃圾回收, 渲染, 批处理, 日志
CRITICAL: Use for Makepad 2.0 theme system. Triggers on: makepad theme, theme variable, theme color, theme font, theme spacing, dark mode, light mode, theme switching, mod.themes, theme_mod, theme.color_, theme.font_, theme.space_, theme.mspace_, 主题, 颜色, 字体, 暗色模式, 亮色模式, 主题切换, 样式
Discover, configure, and connect to Arduino boards from MATLAB using the Arduino Support Package. Use this skill when the user wants to set up an Arduino board, connect to Arduino hardware, find connected boards, scan serial ports, configure Arduino libraries, or any task that requires an Arduino connection as a prerequisite (e.g., blink LED, read sensor, read digital pin, read analog pin, write pin, plot sensor data, scan I2C, use ultrasonic sensor, control servo, read temperature, read voltage, data logging from hardware). Triggers on: arduino, board setup, COM port, serial port, hardware connection, Arduino Nano, Arduino Uno, Arduino Mega, Arduino Micro, Grove, sensor setup, I2C scan, ultrasonic, servo, readDigitalPin, writeDigitalPin, readVoltage, writePWMVoltage, temperature sensor, air pressure, pin read, pin write, analog input.
.NET MAUI app icon configuration, splash screen setup, SVG to PNG conversion at build time, composed/adaptive icons, and platform-specific icon and splash screen requirements for Android, iOS, Mac Catalyst, and Windows. USE FOR: "app icon", "splash screen", "MauiIcon", "MauiSplashScreen", "adaptive icon", "change app icon", "launch screen", "SVG icon", "foreground tint", "icon resize". DO NOT USE FOR: in-app images or image loading (use maui-performance), theming or colors (use maui-theming), or custom drawing (use maui-graphics-drawing).
Guidance for localizing .NET MAUI apps: multi-language support via .resx resource files, culture resolution and runtime switching, RTL layout, platform language declarations (iOS/Mac Catalyst Info.plist, Windows Package.appxmanifest), and image localization strategies. USE FOR: "localization", "multi-language", "resx resource", "translate app", "RTL layout", "culture switching", "localize strings", "right-to-left", "language support MAUI", "Info.plist languages". DO NOT USE FOR: theming or visual styles (use maui-theming), accessibility labels (use maui-accessibility), or content from REST APIs (use maui-rest-api).
Add secure storage to .NET MAUI apps using SecureStorage.Default. Covers SetAsync, GetAsync, Remove, RemoveAll, platform setup (Android backup rules, iOS Keychain entitlements, Windows limits), common pitfalls, and a DI wrapper service for testability. USE FOR: "secure storage", "SecureStorage", "store token securely", "Keychain", "Android Keystore", "save secret", "encrypted storage", "store credentials", "sensitive data storage". DO NOT USE FOR: general file storage (use maui-file-handling), SQLite databases (use maui-sqlite-database), or authentication flows (use maui-authentication).
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/MCP SDK) or Node/TypeScript (MCP SDK). Covers tool design, output schemas, Streamable HTTP transport, authentication patterns, evaluation creation, and common debugging.
Port a Cypress test suite to CodeceptJS 4. Trigger when the project contains `cypress.config.{js,ts,mjs}`, a `cypress/` directory (`cypress/e2e/`, `cypress/support/{commands,e2e}.*`, `cypress/fixtures/`), `cypress` in `devDependencies`, or test code calling `cy.*` (`cy.visit`, `cy.get`, `cy.contains`, `cy.session`, `cy.intercept`, `cy.request`, `cy.task`, `cy.fixture`, `cy.origin`, `cy.mount`), `Cypress.Commands.add(...)`, or `Cypress.env(...)`.
This skill should be used when the user asks to adapt pretrained, foundation, language, vision, multimodal, or embedding models. PROACTIVELY activate for: (1) transfer learning, full fine-tuning, frozen backbones, adapters, LoRA, QLoRA, AdaLoRA, PEFT, (2) Hugging Face Transformers, Diffusers, Accelerate, TRL, RLHF, DPO, preference tuning, alignment, (3) dataset preparation, instruction tuning, chat templates, tokenization, packing, catastrophic forgetting, (4) RAG, vector databases, embedding optimization, reranking, (5) multimodal and edge fine-tuning. Provides: safe, efficient fine-tuning and adaptation guidance.
Design and review mobile app and mobile game product systems including refunds, promotions, subscriptions, in-app purchases, in-app ads, notifications, daily check-ins, rewards, entitlement states, retention loops, and store-compliant monetization UX. Use when building or auditing iOS/Android apps, mobile games, consumer apps, app-store monetization flows, or lifecycle engagement systems.
Phase-by-phase guidance for participating in Bitwarden's Software Initiative Funnel. Covers shepherd vs tech-lead ownership, running an epic breakdown after Scoping & Commitment handoff, sizing, cross-team dependency tracking, and escalation paths that protect team autonomy. Use when receiving an initiative epic, participating in an Architectural Assessment or PoC, preparing the Scoping & Commitment breakdown, or surfacing concerns to the shepherd or engineering leadership.
Use for production Next.js platform work involving Docker or standalone output, static export tradeoffs, self-hosting, deployment adapters, Server Actions encryption keys, shared cache coordination, OpenTelemetry instrumentation, multi-zones, multi-tenant routing, or platform capability reviews.
Design or audit notification strategy across push, email, in-app messages, SMS, lifecycle messaging, reminders, games, SaaS, mobile apps, and desktop utilities. Use when planning permission prompts, notification taxonomy, user controls, retention campaigns, quiet hours, deliverability, fatigue, event triggers, or support-safe messaging.
OkHttp 5.x HTTP client for Java/JVM 8+ and Android 5+. Use when making HTTP/HTTPS requests, building REST API clients, implementing connection pooling, response caching, request/response interceptors, certificate pinning, event monitoring, WebSocket connections, SSE consumption, or configuring TLS/cipher suites. Covers OkHttp 5.4.0 with HTTP/2, transparent GZIP, Fast Fallback (Happy Eyeballs), MockWebServer for testing, and GraalVM Native Image support.
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.