Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Run end-user cmux diagnostics. Use when cmux hooks, notifications, session restore, settings, browser automation, socket access, CLI control, or agent resume behavior is not working, or when the user asks for a cmux health check, doctor report, or support-safe debug summary.
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps or the OS and must be installable without the user having Node/Python set up.
Use this skill for security scanning: check transaction safety, is this transaction safe, pre-execution check, security scan, token risk scanning, honeypot detection, DApp/URL phishing detection, message signature safety, malicious transaction detection, approval safety checks, token approval management. Triggers: 'is this token safe', 'check token security', 'honeypot check', 'scan this tx', 'scan this swap tx', 'tx risk check', 'is this URL a scam', 'check if this dapp is safe', 'phishing site check', 'is this signature safe', 'check this signing request', 'check my approvals', 'show risky approvals', 'revoke approval', 'check if this approve is safe', token authorization, ERC20 allowance, Permit2. Covers token-scan, dapp-scan, tx-scan (EVM+Solana pre-execution), sig-scan (EIP-712/personal_sign), approvals (ERC-20/Permit2). Chinese: 安全扫描, 代币安全, 蜜罐检测, 貔貅盘, 钓鱼网站, 交易安全, 签名安全, 代币风险, 授权管理, 授权查询, 风险授权, 代币授权. Do NOT use for wallet balance/send/history — use okx-agentic-wallet.
Launches an EC2 instance with secure, cost-efficient defaults including AMI selection, burstable instance sizing, least-privilege IAM roles, hardened security groups, encrypted EBS volumes, and comprehensive tagging. Use when deploying new EC2 instances following AWS best practices for security and cost optimization.
Use when users create, generate, or validate Salesforce Custom Object metadata. Trigger on custom objects, .object files, sharing models, name fields, or validation rules — e.g. "create a custom object" — and deployment errors around sharing models and Master-Detail relationships. Also keep the object's <description> current when its fields or validation rules change. Do NOT use for non-Custom-Object metadata (Apex, Flows, LWC, Permission Sets, Custom Metadata Types) or standard objects.
Build and script 2D tilemaps in Unity 6.3 LTS: the Grid + Tilemap components, the Tile Palette, tilemap colliders, rule tiles, and runtime SetTile/GetTile painting. Use when painting tile levels, adding a TilemapCollider2D, using rule or animated tiles, generating tilemaps from code, or when the user mentions Unity tilemap, tile palette, rule tile, or Grid.
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
Diagnoses and resolves Amazon S3 Files issues including mount failures, permission errors, synchronization problems, and performance issues. Use when the user has an S3 file system that is not mounting, returning access denied, not syncing changes to S3, showing files in lost+found, or performing slower than expected.
Maps intelligence for local SEO: geo-grid rank tracking, GBP profile auditing via API, review intelligence across Google/Tripadvisor/Trustpilot, cross-platform NAP verification, competitor radius mapping, and LocalBusiness schema generation. Three tiers: free (Overpass + Geoapify), DataForSEO, and DataForSEO + Google. Use when the user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", or "SoLV".
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish SKILL.md during the diagnostic loop. Not for direct user invocation — its actionable wrappers are /printing-press and /printing-press-polish.
Designs, reviews, operates and audits systems that hold, move, account for and report money — ledgers, payments, banking and open finance, reconciliation and close, risk, fraud, AML, markets and portfolio accounting, and corporate finance/FP&A. Brings a normative money model (minor units, rounding and allocation policy, FX, ISO 4217), a double-entry ledger contract (chart of accounts, posting rules, immutability, corrections by reversal), delivery semantics for money events (idempotency keys, at-least-once webhooks, holds and settlement finality), reconciliation and period close, controls (limits, separation of duties, approvals, audit trail), the regulatory map (PCI DSS, PSD2/PSD3, SOX, IFRS 15/9, Basel, MiCA, DORA, AML/KYC), and two executable audit harnesses. Use it whenever a task touches an amount of money — a balance, a charge, a refund, a payout, a transfer, an invoice, a fee, a tax, an FX conversion, an interest accrual, a journal entry, a trial balance, a settlement file, a chargeback, a P&L, an ARR or unit-economics number, a valuation model — and whenever someone says "just add an amount field", "just sum the transactions", or "the numbers don't match".
Add AI navigation in Unity 6.3 LTS: bake a NavMesh with the AI Navigation package (NavMeshSurface), move agents with NavMeshAgent.SetDestination, and handle dynamic obstacles. Use when setting up pathfinding, making an enemy chase the player, baking navigation, or when the user mentions NavMesh, NavMeshAgent, NavMeshSurface, NavMeshObstacle, or Unity pathfinding.
DEPRECATED - this skill is unmaintained. Use the official Angular skills at https://github.com/angular/skills instead. Write unit and integration tests for Angular v20+ applications using Vitest or Jasmine with TestBed and modern testing patterns. Use for testing components with signals, OnPush change detection, services with inject(), and HTTP interactions. Triggers on test creation, testing signal-based components, mocking dependencies, or setting up test infrastructure. Don't use for E2E testing with Cypress or Playwright, or for testing non-Angular JavaScript/TypeScript code.
Triage TestFlight crashes, beta feedback, and performance diagnostics using asc. Use when the user asks about TF crashes, TestFlight crash reports, beta tester feedback, app hangs, disk writes, launch diagnostics, or wants a crash summary for a build or app.
Creates an API Gateway stage with CloudWatch logging, X-Ray tracing, throttling, WAF integration, and IAM roles following AWS best practices. Use when deploying a REST API to different environments such as dev, test, or production.
Queries the schedule, venue, registration deadline, and events of Korean marathon and triathlon races via the public World Athletics and Korean Triathlon Federation pages. In 돌쇠, it also carries out follow-up actions through the official pages.
Generate TypeScript/JavaScript code that reads/decodes AND writes/encodes ClickHouse RowBinary streams for the ClickHouse HTTP server. Use this skill whenever a user wants to parse or produce `RowBinary`, `RowBinaryWithNames`, or `RowBinaryWithNamesAndTypes`. Node.js only, doesn't cover browsers.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging. Use when the task is to find, screen, synthesize, and cite a body of academic or technical literature.
Vitest testing framework patterns for test setup, async testing, mocking with vi.*, snapshots, and test performance (formerly test-vitest). This skill should be used when writing or debugging Vitest tests. This skill does NOT cover TDD methodology (use test-tdd skill), API mocking with MSW (use test-msw skill), or Jest-specific APIs.
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when cleaning up legacy code, preparing code for new features by restructuring, or identifying which transformation fits a specific code smell. Covers smell-driven refactoring, safe transformation sequences, and testing guards. For code-quality foundations, see clean-code. For managing complexity, see software-design-philosophy.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live browser state.
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Visualize data as charts. Call this skill when the user needs bar charts, line charts, pie charts, scatter plots, radar charts, Sankey diagrams, mind maps, flowcharts and other charts; it calls the AntV API via the curl tool to generate chart images.
Generate Salesforce Flows using the MCP tool execute_metadata_action. Use when the user asks to create, build, or generate a flow — including Screen, Autolaunched, Record-Triggered (before/after-save), Scheduled. Also trigger for flow-like requests such as "when a record is created", "trigger daily at", "send an email when", "update the field when", "automate", "workflow", or "flow XML/metadata". This is the only skill for Salesforce Flow generation.
Produce an editor-ready content brief for a target keyword or topic. Use when the user asks for a content brief, writing guidelines, article outline, SEO brief, what to include in a blog post, or how to structure content for a keyword. For choosing which topics to write about, see find-keywords. For a full site-wide SEO audit, see audit.
Use this skill when the user asks to export audit logs, find audit log location, view command history, 导出日志, 查看日志, 日志路径, 操作记录, 调用记录, 命令历史. Do NOT use for wallet balance, token search, swap, or any other on-chain operation — use the corresponding skill instead.
Rewrites Korean text that sounds AI-generated into natural human writing. Detects translationese, AI clichés, excessive nominalization and passive voice, the rule of three, exaggerated significance, formulaic conclusions, chatbot residue, and Korean-specific AI tells such as dashes and curly quotation marks; classifies them by severity (S1/S2/S3) and rewrites while preserving meaning. If you provide a target length (e.g. "1000 characters", length=1000), it expands or shortens the text accordingly. Use for requests like "make it sound less AI-generated," "make it sound human," "polish it naturally," "fix translationese," "fix awkward phrasing," or "adjust it to N characters."
Investment analysis. Given a project (company name, BP, founder conversation records), write a deep investment analysis report. It does not follow the traditional path — the core judgment is a single question: is this project a "machine for creating order"? Use when the user says '投资报告', '投资分析', '分析这个项目', '写投资报告', 'investment report', 'invest analysis', or provides entrepreneur conversation records wanting investment evaluation. Also trigger when the user pastes or references meeting notes, pitch decks, or founder interviews and asks for analysis.
Build a PixiJS v8 render layer: create the async Application, load textures with Assets, compose the scene graph with Container and Sprite, drive the ticker loop, wire pointer events, and group draws with render groups. Use when building or debugging PixiJS v8—when the user mentions PixiJS, Pixi, Application, app.stage, Container, Sprite, Assets.load, app.ticker, or eventMode. Pins the v8 async init() API
Writes, reviews, and debugs idiomatic Rust code with memory safety and zero-cost abstractions. Implements ownership patterns, manages lifetimes, designs trait hierarchies, builds async applications with tokio, and structures error handling with Result/Option. Use when building Rust applications, solving ownership or borrowing issues, designing trait-based APIs, implementing async/await concurrency, creating FFI bindings, or optimizing for performance and memory safety. Invoke for Rust, Cargo, ownership, borrowing, lifetimes, async Rust, tokio, zero-cost abstractions, memory safety, systems programming.
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
Create and manage tickets — initiatives, epics, stories, bugs. Use when the user says "create a new initiative", "slice this initiative", "split this epic up", "break this into stories", "incept this epic", "make a ticket", "refine this ticket", "what's ready", "status of a story", "publish ticket changes", "validate these tickets", "set up the ticket store".
A step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explaining, evaluating or demonstrating the pattern before committing to the protect-mcp runtime hooks. Covers Cedar policy, Ed25519 receipts, offline verification, tamper detection, CI/CD integration and SLSA composition.
Use this skill when creating and configuring a PixiJS v8 Application. Covers new Application() + async app.init() options (width, height, background, antialias, resolution, autoDensity, preference, resizeTo, autoStart, sharedTicker, canvas, useBackBuffer, powerPreference, eventFeatures, accessibilityOptions, gcActive, bezierSmoothness, webgl/webgpu/canvasOptions per-renderer overrides), app.stage/renderer/canvas/screen/domContainerRoot access, ResizePlugin, TickerPlugin, CullerPlugin (cullable, cullArea), custom ApplicationPlugin via ExtensionType.Application, start/stop lifecycle, and app.destroy() with releaseGlobalResources. Triggers on: Application, app.init, app.stage, app.renderer, app.canvas, app.screen, app.domContainerRoot, ApplicationOptions, ApplicationPlugin, ExtensionType.Application, resizeTo, sharedTicker, skipExtensionImports, preferWebGLVersion, preserveDrawingBuffer, cullable, CullerPlugin, app.start, app.stop, app.destroy, releaseGlobalResources.
Query integrated announcement program information, support program notices, startup content, and statistical reports via the 공공데이터포털 창업진흥원 K-Startup Open API(15125364) through k-skill-proxy. Search only. In 돌쇠, proceed with follow-up actions through the official surface.
Defines model-callable tools and renders their calls in assistant-ui. The authoring model: a "use generative" file whose default export is defineToolkit({...}), compiled by withAui from @assistant-ui/next, aui() from @assistant-ui/vite, or withAui from @assistant-ui/metro, mounted with AuiConfig({ tools: Tools({ toolkit }) }), and exposed to the model with new AISDKToolkit({ toolkit }).tools({ frontend }). Covers the tool kinds (backend, "use client" frontend, humanTool(), providerTool(), externalTool(), stubTool(), defineMcpToolkit()), render and display, ToolCallMessagePartProps, approval gates, MCP servers, MCP Apps, WebMCP, and sub-agent messages. Reach for it when a tool is never called, a tool UI does not render, a frontend result never reaches the model, humanTool() throws at runtime, or an approval gate cannot be answered. For model-composed UI use generative-ui, for MCP servers users add in the browser use react-mcp, and for the styled ToolFallback and ToolGroup use elements.
Configure Amazon Route 53 to route traffic to a CloudFront distribution using a custom domain. Use when setting up DNS alias records, alternate domain names (CNAMEs), ACM certificates for HTTPS, and IPv6 support for CloudFront.
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.