Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Build Google Chat bots and webhooks with Cards v2, interactive forms, and Cloudflare Workers. Covers Spaces/Members/Reactions APIs, bearer token verification, and dialog patterns. Use when: creating Chat bots, workflow automation, interactive forms. Troubleshoot: bearer token 401, rate limit 429, card schema validation, webhook failures.
Make HTTPS requests from canisters to external web APIs. Covers replicated, non-replicated and flexible outcalls, transform functions for consensus, both cycle pricing versions (legacy and pay-as-you-go via ic0.cost_http_request_v2), response size limits, and idempotency patterns. Use when a canister needs to call an external API, fetch data from the web, make HTTP requests, choose a pricing_version, or use flexible_http_request. Do NOT use for EVM/Ethereum calls — use evm-rpc instead.
LLVM passes skill for writing compiler optimizations. Use when writing FunctionPass or ModulePass, registering PassPlugins, running with opt, using analysis utilities, or testing with llvm-lit. Activates on queries about LLVM pass, PassPlugin, opt -passes, DominatorTree, llvm-lit, or New Pass Manager.
Use Lucide icons correctly across any framework or environment. Lucide is a tree-shakeable SVG icon library with 1000+ icons. Use this skill when working with Lucide icons in React, Vue, Svelte, Solid, Preact, Angular, Astro, React Native, Vanilla JS, or static/server-side environments. Triggers include installing lucide icons, importing lucide components, customizing icon appearance, using dynamic icons, or using Lucide lab custom icons.
Resource optimization skill for constrained embedded targets. Use when reducing flash/RAM usage, analyzing stack depth, reading linker map files, or tuning size vs speed on MCUs. Activates on queries about firmware size optimization, linker map, stack usage, -Os, flash RAM budget, or bloat analysis.
Full Sentry SDK setup for Go. Use when asked to "add Sentry to Go", "install sentry-go", "setup Sentry in Go", or configure error monitoring, tracing, logging, metrics, or crons for Go applications. Supports net/http, Gin, Echo, Fiber, FastHTTP, Iris, and Negroni.
Integrate Redis-compatible Vercel KV for caching, session management, and rate limiting in Next.js. Powered by Upstash with strong consistency and TTL support. Use when implementing cache strategies, rate limiters, or troubleshooting environment variables, serialization errors, rate limit issues, scanIterator hangs, or Next.js cache stale reads.
How to write JSDoc (/** */) and inline (//) comments in the Astro codebase, for contributors reading the source — not end users. Use whenever writing or editing comments in .ts/.js source, including comments added incidentally while fixing bugs or building features. Does not cover the @docs-generated config/error reference.
Generates, formats, and validates technical documentation — including docstrings, OpenAPI/Swagger specs, JSDoc annotations, doc portals, and user guides. Use when adding docstrings to functions or classes, creating API documentation, building documentation sites, or writing tutorials and user guides. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, getting started guides.
Creates step-by-step decomposition plans and migration roadmaps for breaking apart monolithic applications. Use when asking “what order should I extract services?”, “plan my migration,” “create a decomposition roadmap,” “prioritize what to split,” “monolith to microservices strategy,” or tracking decomposition progress. Do NOT use for domain analysis (use domain-analysis) or component sizing (use component-identification-sizing)
Cross-file consistency audit of docs, templates, manifests (package.json, plugin.json, .mcp.json), installer scripts, and instruction files (CLAUDE.md, AGENTS.md, SKILL.md): flags drift, and content restated in several places instead of referenced from one; skips credential files. Use for "check consistency", "in sync", "find inconsistencies", "verify everything is updated", "single source of truth", "restated in multiple places". Offer proactively—asking first—after any README, SKILL.md, CLAUDE.md, AGENTS.md, template, plugin.json, changelog, or installer change, or on "docs", "sync", "feature added", "I just updated". `review-intentional` re-surfaces suppressed findings.
FiveM development best practices for any framework (vRP, QBCore, Qbox, ESX). Covers performance, security, client/server communication, cache (cacheaside + client-side cache §2.1.1), cerberus (load balance, SafeEvent, SetCooldown), view-cache audit (audit-passes.md §2.4), client-callable endpoint exposure & server auth (§5.1), input validation (§5.3), quality gates for implementation/refactor (quality-gates.md), asset discovery, framework auto-detection, and dynamic documentation fetching. Use when the user works with FiveM, Lua scripts, natives, resources, fxmanifest, optimization, /fxmind audit, or general server development without a specific framework context.
Use when the user asks to manage Make platform resources with makecli — create/deploy apps, promote beta to production, check build/deploy progress or app URLs, read build/deployment logs, entities, relations, records, inspect resources, switch backend context, log in to Make, or run makecli CLI commands. Also triggered by requests like \"部署\", \"发布到 production\", \"promote\", \"部署进度\", \"构建状态\", \"构建日志\", \"部署日志\", \"apply\", \"查看应用\", \"创建记录\", \"登录 Make\", \"切换环境\", or \"/makecli\". Does not own DSL schema design (use makedsl), frontend UI (makeui), auth (make-app-auth), Service/API code (make-app-service), runtime packaging (make-app-runtime), OCR integration (make-integration), or canvas-table behavior.
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).
Build CLI scripts alongside MCP servers for terminal environments. File I/O, batch processing, caching, richer output formats. Templates for TypeScript scripts and SCRIPTS.md. Use when: MCP companion scripts, batch processing, saving results to files, CLI API wrappers. Troubleshoot: context too large, no file access, batch input.
Pattern for using useSearchParams hook with Suspense boundary in Next.js. Covers the required combination of 'use client' directive and Suspense wrapper when accessing URL query parameters in client components. Use when building search interfaces, filters, pagination, or any feature that needs to read/manipulate URL query parameters client-side.
NUMA programming skill for multi-socket memory locality. Use when detecting NUMA topology, binding processes with numactl, using libnuma API, building NUMA-aware data structures, or measuring remote access penalties. Activates on queries about numactl, libnuma, NUMA topology, mbind, lstopo, or remote memory access.
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays, uploadAndPoll issues.
Implement "Sign In with OpenRouter" using OAuth PKCE — framework-agnostic, no SDK or client registration required. Use when the user wants to add OpenRouter login, authentication, sign-in buttons, OAuth, or AI model inference API keys for browser-based apps. No client registration, no backend, no secrets required.
Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4). Use whenever writing or editing Remotion code — scaffolding a video project, animating with interpolate/spring over useCurrentFrame(), sequencing scenes and transitions, captions/subtitles, audio, GIFs/Lottie/3D, charts, visual effects, dynamic duration via calculateMetadata, or rendering. Consult before reaching for a Remotion API, since its components and props evolve (e.g. @remotion/media).
Extracts structured data from LLM responses using JSON schemas, Zod validation, and function calling for reliable parsing. Use when users request "structured output", "JSON extraction", "parse LLM response", "function calling", or "typed responses".
Implement the Syncfusion Angular Maps component for geographical data visualization. Use when users need to display maps, visualize geographical data with markers and bubbles, integrate map providers like Bing or OpenStreetMap, render GeoJSON shapes, or create choropleth maps with color-coded regions. Supports interactive features like zooming, panning, layers, legends, tooltips, color mapping, and accessibility
Tailwind CSS code refactoring patterns for v4 migration and anti-pattern cleanup. Use this skill when refactoring Tailwind utility classes, migrating from v3 to v4, cleaning up deprecated utilities, consolidating verbose class patterns, or removing code smells—all without changing the visual output. Triggers on tasks involving Tailwind CSS cleanup, v4 migration, class refactoring, @apply removal, or utility modernization.
Provides comprehensive guidance for Vue 2.x development including Options API, components, directives, lifecycle hooks, computed properties, watchers, Vuex state management, and Vue Router. Use when the user asks about Vue 2, needs to create Vue 2 components, implement reactive data binding, handle component communication, or work with Vue 2 ecosystem tools.
Expert in AppleScript and JavaScript for Automation (JXA) for macOS system scripting. Specializes in secure script execution, application automation, and system integration. HIGH-RISK skill due to shell command execution and system-wide control capabilities.
Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.
Architect scalable backend systems, database schemas, APIs, and cloud infrastructure for robust server-side applications. Use when you need microservice vs monolith decisions, database indexing strategies, API versioning, event-driven architecture, ETL pipelines, WebSocket streaming, data modeling, query optimization, or cloud-native service design with high reliability and sub-20ms query performance.
Write, explain, and debug Metal GPU code, including shaders (vertex, fragment, compute), render pipelines, compute pipelines, buffer/texture management, and Metal 4 APIs. Use this skill whenever the user mentions Metal, GPU programming, shaders, MSL (Metal Shading Language), render passes, compute kernels, MTLDevice, MTLCommandBuffer, MTLRenderPipelineState, or any Apple GPU/graphics programming topic. Also trigger when the user wants to do parallel computation on Apple devices, write GPU-accelerated code, or work with Metal Performance Shaders, MetalFX, MetalKit, or Compositor Services. Covers iOS, macOS, iPadOS, tvOS, and visionOS.
Use when code must be checked, not assumed: trace connections (callers, imports, cross-repo wiring, what breaks if I change it), locate behavior, map a system, diagnose a failure, RCA. Also for external repositories, npm packages, upstream/prior art, and general research. Plan a coding flow before writing, validate it after. Triggers on 'research this' or 'use octocode'. Gives exact file:line/PR/commit evidence with confidence. Skip trivial edits whose blast radius is already known. Not for authoring or copyediting the docs themselves, or for building skill folders: docs deliverable → octocode-documentation; SKILL.md folders → octocode-skills
OpenMP skill for shared-memory parallel programming. Use when writing parallel for loops, reductions, task parallelism, SIMD directives, GPU offloading, or profiling with Score-P/TAU. Activates on queries about OpenMP, pragma omp, schedule static dynamic, reduction, false sharing, or OMP_NUM_THREADS.
Use when the user asks to "build a mobile app", "scaffold React Native project", "create SwiftUI views", "set up Jetpack Compose", "optimize mobile performance", "configure Expo Router navigation", "implement offline-first storage", "submit to App Store", or "profile mobile rendering". Expert mobile development covering iOS (Swift/SwiftUI), Android (Kotlin/Compose), React Native, and Flutter for native and cross-platform applications.
Full Sentry SDK setup for Svelte and SvelteKit. Use when asked to "add Sentry to Svelte", "add Sentry to SvelteKit", "install @sentry/sveltekit", or configure error monitoring, tracing, session replay, or logging for Svelte or SvelteKit applications.
Implement and customize Syncfusion Angular Accumulation Charts (Pie, Doughnut, Pyramid, Funnel) with data binding, labels, legends, and tooltips. Use this when creating accumulation charts, configuring chart types, customizing data visualization, adding annotations, or handling interactive chart events in Angular applications
Implement the Syncfusion Angular Ribbon component. Use to create Microsoft Office-style ribbon interfaces, organize application commands into tabs and groups, implement file menus or backstage views, or build sophisticated command interfaces. Includes setup, configuration, event handling, layouts, and customization. Use for all Ribbon component implementation needs.
Use when work changes the repository: feature, fix, refactor, migration, integration, audit, PR review; фича, баг, интеграция, аудит. Runs a substantial task through gated stages to acceptance; 'waves'/'волнами' closes the board. Not for questions or one-line edits; 'без пайплайна' opts out.
ALWAYS use when writing code that imports "vue-router", "vue-router/vite", "vue-router/auto-routes", or "vue-router/experimental". Consult for debugging, best practices, or modifying vue-router, vue router, router, file-based routing, typed routes, data loaders.
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.