Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Best practices and workflow guide for Git version control. Use when: (1) writing Git commit messages (applying Conventional Commits); (2) creating and managing branches (based on GitHub Flow); (3) creating PRs and choosing merge strategies; (4) cleaning up Git history (rebase, squash, cherry-pick); (5) resolving merge conflicts; or (6) tasks include the keywords “git,” “.git,” “commit,” “branch,” “merge,” or “rebase”
Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate coding tasks to Codex, run codex exec, generate or refactor code, or get a Codex code review; phrases like 'codex', 'run codex', 'codex exec', 'delegate to codex'.
nginx C module development guidelines based on the official nginx development guide. This skill should be used when writing, reviewing, or refactoring nginx C modules to ensure correct memory management, request lifecycle handling, and event-driven patterns. Triggers on tasks involving nginx module development, ngx_http_module_t, handler/filter/upstream implementation, pool allocation, or nginx configuration directives.
Route repeated pattern, rule, and anomaly work into one detection packet before suggesting tools or fixes. Use when the user needs reusable scans, suspicious repeated shapes, grouped outlier candidates, or first-pass anomaly triage across code, logs/events, telemetry, and metric tables. Choose one packet: text-prefilter, structural-code-rule, log-event-pattern, or metric-anomaly. Triggers on: repeated bug, suspicious spike, odd cohort, noisy event, code smell family, rule pack, anti-pattern, outlier, anomaly, fraud signal, or recurring issue. Route root-cause incident work to log-analysis, KPI/business explanation to data-analysis, repo tracing to codebase-search, remediation to specialist skills, and alert/incident operations to monitoring-observability
Implement speech-to-text voice input in Blazor applications using the Syncfusion SpeechToText component. ALWAYS use this when users need voice input, speech recognition, audio transcription, or the SpeechToText component in Blazor. Trigger for Syncfusion.Blazor.Inputs, microphone input, voice-to-text conversion, language support, transcript binding, listening states, error handling, browser speech API, or any speech recognition requirements.
/c-level-agents:vpe-review [plan] — Throughput-first VP of Engineering interrogation of any plan that touches delivery, eng hiring, team structure, or production discipline. Use when cycle time balloons, DORA metrics slide, or before committing to an eng hiring wave or a reorg.
WordPress theme development workflow covering theme architecture, template hierarchy, custom post types, block editor support, responsive design, and WordPress 7.0 features: DataViews, Pattern Editing, Navigation Overlays, and admin refresh.
Use when you need to analyze Java profiling data collected during the detection phase — including interpreting flamegraphs, memory allocation patterns, CPU hotspots, threading issues, systematic problem categorization, evidence documentation with profiling-problem-analysis and profiling-solutions markdown files, or prioritizing fixes using Impact/Effort scoring. This should trigger for requests such as Analyze JFR profile; Analyze the profile; Analyze the performance; Analyze the memory; Analyze the threading; Analyze GC logs from profiling; Prioritize Java profiling bottlenecks by impact. Part of Plinth Toolkit
This skill should be used when the user asks about a "caching strategy", "cache invalidation", "what to cache", "read-through vs write-through vs write-back", "cache eviction" (LRU/LFU/TTL), "Redis vs Memcached", "stale reads", or hits "thundering herd", "cache stampede", "cache penetration", or "hot key" problems, or is choosing a Redis `maxmemory` eviction policy (allkeys-lru, volatile-lru, noeviction) vs TTL expiry for sessions or other cached state. Use it whenever a design is read-heavy or a datastore is overloaded by reads, even if the user doesn't say "cache".
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.
This skill should be used when the user asks to "set up the SDK", "initialize BankrClient", "configure wallet", "set up payment wallet", "connect wallet to Bankr", "get wallet address", "set up environment variables", "configure private key", "two wallet setup", "separate payment and trading wallets", or needs help with SDK client initialization, two-wallet configuration, wallet address derivation, environment setup, or BankrClient options.
Expert multiplayer for desync, rollback, dedicated --headless servers, interest culling, and bandwidth spikes: ENet/WebRTC choice, authority, secure RPCs, client prediction/reconcile, and adaptive sync. Trigger on rubber-banding, cheat-able clients, peer floods, late join, or profiler Network spikes — not only greenfield online games. Keywords: multiplayer, RPC, ENetMultiplayerPeer, MultiplayerSynchronizer, authority, client prediction, rollback, interest management, headless, desync.
Migrates a React project from Metabase Modular embedding (embed.js web components) to the Modular embedding SDK (@metabase/embedding-sdk-react). Use when the user wants to switch from embed.js web components to React SDK components (MetabaseProvider). This is not a version upgrade — it changes the embedding technology.
Build AI applications with OpenAI Agents SDK: text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
Use when the user asks to create a feature, write a PRD or TRD, add user stories, write scenarios, create acceptance criteria, plan implementation, initialize product docs, set up product documentation, create, approve, amend, or validate a Product Constitution, run the Constitution Grill, create or maintain Product Vision, run a Vision Grill, or work anywhere in the product development lifecycle from project setup through implementation planning
High-level overview of what Sui is, how it works, and what the Sui Stack provides. Use when explaining Sui to someone new, comparing Sui to other blockchains (Ethereum, Solana, Bitcoin), discussing the object-centric data model conceptually, choosing which Sui Stack primitives to use (randomness, zkLogin, Walrus, Nautilus, DeepBook, Kiosk, Seal), exploring use cases Sui enables (DeFi, gaming, NFTs, identity, social, supply chain), or migrating from Ethereum or Solana to Sui.
Use when you need to generate Architecture Decision Records (ADRs) for a Java project through an interactive, conversational process that systematically gathers context, stakeholders, options, and outcomes to produce well-structured ADR documents. This should trigger for requests such as Generate ADR; Create Architecture Decision Record; Document architecture decision; Architecture Decision Record for Java. Part of Plinth Toolkit
Reconstruct an OKF bundle by event-sourcing a repository's history (git log and Claude session transcripts). Use when creating an `.okf/` bundle for an existing repository that predates this skill, or when resuming an interrupted backfill session. Triggers on: "reconstruct the OKF bundle", "backfill the knowledge bundle", "event-source the history".
Use this skill when encountering authentication errors, API key errors, 401 errors, "invalid API key", "BANKR_API_KEY not set", job failures, or any Bankr API errors. Provides setup instructions and troubleshooting guidance for resolving Bankr configuration issues.
Keep a Blume docs site in sync with the product it documents. Audit recently merged pull requests, changelogs, config schemas, CLI help, and public APIs against the docs content, update only pages that are factually stale, verify the docs build, and open (or update) a maintenance pull request — or report a clean no-op. Use when asked to check docs for drift, refresh stale documentation, run a scheduled docs audit, or keep docs current after a release.
Linux kernel architecture skill for subsystem overview. Use when navigating kernel source, understanding boot flow, initcalls, or major subsystems (VFS, scheduler, MM). Activates on queries about kernel architecture, boot process, initcall levels, subsystem layout, or where code lives in linux.git.
Migrate Python Agno applications to Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports `agno` or relies on Agno agents, teams, workflows, sessions, memory, knowledge, tools, hooks, guardrails, approvals, skills, streaming, or AgentOS.
Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports `@mastra/*` or relies on Mastra agents, tools, workflows, memory, processors, streaming, approvals, skills, or subagents
Use when starting, designing, organizing, finishing, or shipping an n8n workflow. Covers visual layout (sticky notes), descriptions that capture the *why*, node names, validation, testing, folders/projects, and publishing. Triggers on create_workflow_from_code, update_workflow, validate_workflow, publish_workflow, archive_workflow, "design", "lay out", "organize", "structure", "sticky", "describe this workflow", "ship", "deploy", "publish", "name this workflow", or any folder/project organization request.
Implement performant responsive images with srcset, sizes, lazy loading, and modern formats. Covers aspect-ratio for CLS prevention, the picture element for art direction, and fetchpriority for LCP optimization. Use when adding images to pages, optimizing Core Web Vitals, preventing layout shift, implementing art direction, or converting to modern formats.
Set up a Deepgram MCP server for your AI coding tool. Offers three paths: the Deepgram CLI MCP proxy (dg mcp), the standalone deepgram-mcp package, and the credential-free hosted documentation MCP. Use when someone wants to install Deepgram's agentic tools, set up the MCP server, or connect their editor to Deepgram.
Build responsive card layouts with Syncfusion Blazor Card component. Use this when creating reusable card containers with headers, images, content, action buttons, and custom styling. This skill covers setup, structure, layouts, interactivity, and advanced customization.
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.
Wire Credyt billing into your application code. Adds customer creation to registration, usage event tracking, balance checks, cost tracking, and billing portal links. Run after /credyt:billing-setup and /credyt:billing-verification. Use when the user wants to add Credyt to their app, integrate billing, send events from code, show balances, or add a billing page.
Integrates Base Account SDK for authentication and payments. Covers Sign in with Base (SIWB), Base Pay, Paymasters, Sub Accounts, Spend Permissions, Prolinks, and batch transactions. Use when building apps with wallet authentication, USDC payments, sponsored transactions, smart wallet features, recurring subscriptions, shareable payment links, or any onchain interaction on Base. Covers phrases like "add sign in with Base", "SIWB button", "accept USDC payments", "Base Pay", "paymaster setup", "gas sponsorship", "smart wallet", "sub account", "spend permissions", or "payment link".
Entry-point for adding CometChat Voice & Video Calling to any React, React Native, Angular, native Android, native iOS, or Flutter project. Detects the framework, picks standalone (calls-only) vs additive (calls on top of existing chat) mode, and routes to the per-family calls skill. Invoked by the top-level `cometchat` dispatcher when `product === "voice-video"` or `chat-messaging+voice-video`, and directly when the user asks for calls explicitly.
Localization (i18n) across all CometChat UI Kit families — React, React Native, Angular, Android (V5/V6), iOS, Flutter (V5/V6). Covers CometChatLocalize.init signature differences (positional vs object), bundled languages, custom-language registration, RTL support, fallback to English, and cross-family drift risks. Cross-family — applies wherever the agent is configuring CometChat localization
Build integrations with the Factorial HR API using the official TypeScript (@factorialco/api-client) and Python (factorial-api-client) SDKs. Use when authenticating, calling endpoints, paginating list results, subscribing to webhooks, or typing webhook handler payloads against the Factorial API
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.