Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Implement and configure the Syncfusion Blazor TreeMap component (SfTreeMap) for hierarchical data visualization. Use this when working with treemaps, area-proportional visualizations, or heat-map-like block displays. This skill covers TreeMap setup, layout configuration, data binding, color mapping, drill-down navigation, and accessibility features.
Integrate Vercel Blob for file uploads and CDN-delivered assets in Next.js. Supports client-side uploads with presigned URLs and multipart transfers for large files. Use when implementing file uploads (images, PDFs, videos) or troubleshooting missing tokens, size limits, client upload failures, token expiration errors, or browser compatibility issues. Prevents 16 documented errors.
Guides the creation of agile epics with comprehensive definitions covering business value, success criteria, and breakdown into user stories. Use when the user wants to create an agile epic, define a large body of work, break down features into user stories, or document strategic initiatives. Trigger for requests such as “Create an agile epic”; “Write an epic”; “I need to create an epic”; “Define an epic”; or “Epic definition”. Part of Plinth Toolkit
I2C and SPI bus driver skill for Linux client drivers. Use when writing i2c_driver or spi_driver, register access over bus, DMA SPI transfers, or ACPI/DT client binding. Activates on queries about i2c_client, spi_driver, regmap I2C, SPI transfer, or Linux I2C SPI subsystem.
Build stateful Durable Objects for real-time apps, WebSocket servers, coordination, and persistent state. Prevents 20 documented errors. Use when: implementing chat rooms, multiplayer games, rate limiting, session management, WebSocket hibernation, or troubleshooting class export, migration, WebSocket state loss, boolean binding, RPC streams, or binding errors.
Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations. Use this skill when writing, reviewing, or debugging codemods, AST transformations, or automated refactoring tools. Triggers on tasks involving codemod, ast-grep, JSSG, code transformation, or automated migration.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.
Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so many TypeError issues that look the same?", "merge these duplicates", "stop splitting this error into new issues", or wants to clean up fingerprint sprawl. Decides between a one-shot merge of existing issues and a durable grouping rule that keeps future events from creating new fingerprints. Does NOT group conceptually similar bugs across different runtimes, SDKs, or call sites.
Use when the user asks to “create a hook,” “add a PreToolUse/PostToolUse/Stop hook,” “validate tool use,” “implement prompt-based hooks,” “use ${CLAUDE_PLUGIN_ROOT},” “set up event-driven automation,” “block dangerous commands,” or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks, focusing on the advanced prompt-based hooks API
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Migrates Honcho Python SDK code from v1.6.0 to v2.1.1. Use when upgrading the honcho package, fixing breaking changes after an upgrade, or when errors mention AsyncHoncho, observations, the Representation class, the .core property, or get_config methods.
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
Find focused, runnable Deepgram recipes for a specific feature and language. Use whenever someone wants a minimal working code snippet for one feature (transcribing a URL, diarization, smart formatting, connecting a voice agent, etc.) rather than a full starter app. Recipes are under 50 lines, read DEEPGRAM_API_KEY from the environment, and include a runnable example_test. Covers Python, JavaScript, Go, .NET, Java, Rust, and the Deepgram CLI
Implement, review, and refactor SwiftUI features using the iOS 26+ Liquid Glass API. Use when adopting Liquid Glass in new UI, converting existing surfaces to glass, reviewing glass usage for correctness, or fixing common Liquid Glass pitfalls (custom blur stacks, scroll views, button shapes, bottom bars, pre-enclosed symbols).
Implement Syncfusion Blazor Smith Chart for RF circuit analysis and transmission line impedance matching. Use this when visualizing impedance/admittance data, reflection coefficients, S-parameters, or antenna tuning in Blazor applications. This skill covers circular grid representations and RF network parameter analysis.
Bare-metal startup skill for reset-to-main bring-up. Use when writing startup code, vector tables, .data/.bss initialization, stack setup, or crt0 for Cortex-M/RISC-V. Activates on queries about reset vectors, VTOR, startup.s, bss initialization, or bare-metal entry points.
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
NocoBase 2 only; never use in a NocoBase 3 project. INTERNAL CONTINUATION ONLY. Never select this skill from a raw user UI request. Use it only after nocobase-portal-manage has already resolved exactly one enabled Portal and confirmed portalType=no-code, or has proved the runtime has capabilities.multiPortal === false. Portal count or `isDefault` marker alone never enables this skill. It authors NocoBase Modern UI pages, blocks, menu items, fields, actions, layouts, reactions, and AI employee placements through backend flow-surfaces via nb api. Unresolved UI requests go to nocobase-portal-manage first; a sole AI Portal is handed off automatically for source-code implementation. Hand off AI employee lifecycle work to nocobase-ai-employee and explicit DSL, YAML, git, or cli push workflows to nocobase-dsl-reconciler. It does not handle ACL, data modeling, workflow orchestration, browser reproduction, page error postmortems, Portal lifecycle, AI Portal source-code UI, or non-Modern page navigation
Migration guide from @openrouter/sdk to @openrouter/agent for callModel, tool(), stop conditions, and agent features. This skill should be used when code imports callModel, tool(), or stop conditions from @openrouter/sdk and needs to migrate to @openrouter/agent.
Use when building React 18+ applications in .jsx or .tsx files, Next.js App Router projects, or create-react-app setups. Creates components, implements custom hooks, debugs rendering issues, migrates class components to functional, and implements state management. Invoke for Server Components, Suspense boundaries, useActionState forms, performance optimization, or React 19 features.
A Chinese-language tool for creating feature specifications, converting natural-language feature descriptions into structured specification documents. Supports automatic branch name generation, Git branch creation, specification file initialization, and quality validation. Trigger phrases include: “speckit规范,” “功能规范,” “创建规范,” “功能描述转换,” and “speckit-specify.” Use this skill when users need to turn feature ideas into structured specifications.
Model and review safe TypeScript with strictness, narrowing, generics, modules, declarations, runtime validation, and public APIs. Use for tsconfig, types, compilation errors, libraries, or TS/JS contracts; don't confuse static types with external data validation
Embedded bootloader skill for firmware update and app handoff. Use when writing a custom bootloader, jumping to application code, relocating VTOR, or implementing DFU/USB firmware update on Cortex-M. Activates on queries about bootloader jump, vector table relocation, application entry point, STM32 DFU, or dual-bank flash.
Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.
Implement feature flags in Next.js or SvelteKit code with the Flags SDK (`flags` npm package). Use when installing or configuring the SDK, declaring flags with `flag()`, wiring a provider adapter (`@flags-sdk/vercel`, Statsig, LaunchDarkly, PostHog, GrowthBook, Global Config, OpenFeature, and others), using `identify`, `dedupe`, or `evaluate`, keeping pages static with precompute, setting up Flags Explorer, or encrypting flag values. For planning a flag, Vercel Flags rollouts and experiments, the `vercel flags` CLI, or other frameworks, use the `vercel-flags` skill.
GPU memory model skill for SIMT execution and memory hierarchy. Use when analyzing warp divergence, memory coalescing, shared memory bank conflicts, cache behavior, atomics, or occupancy tradeoffs. Activates on queries about SIMT, warp coalescing, bank conflicts, wavefront, GPU occupancy, or memory-bound kernels.
Kernel concurrency skill for Linux locking and synchronization. Use when choosing spinlocks vs mutexes, using RCU, seqlocks, completions, or applying memory barriers in kernel code. Activates on queries about kernel spinlock, mutex, RCU, seqlock, memory barrier, or PREEMPT_RT locking
Expert guidance on ParadeDB text and vector search, hybrid search (BM25 + semantic), filters, facets, joins, and aggregations in Postgres. Use when writing ParadeDB queries, creating ParadeDB indexes, indexing vectors, configuring tokenizers, or implementing Elasticsearch-quality search in Postgres.
Full Sentry SDK setup for Apple platforms (iOS, macOS, tvOS, watchOS, visionOS). Use when asked to “add Sentry to iOS,” “add Sentry to Swift,” “install sentry-cocoa,” or configure error monitoring, tracing, profiling, session replay, or logging for Apple applications. Supports SwiftUI and UIKit.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. Trigger when the user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. Do not trigger for Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work unrelated to Agent Script, or when the primary input is a production session or trace ID rather than an agent artifact.
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.