Skills
99,064 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Deploy the dispatcher PCF for a third-party `.ppmplugin` control to a Power Platform environment via `pac pcf push`. The dispatcher PCF is the Studio-side control that dispatches the composite key `<name>/<receiver>` over the wrap shell's `SendMessagePlugin` bridge to the control's native module. Verifies deploy prereqs (Node.js 20+ with npm, .NET SDK, and active `pac auth`), then three confirmation gates — publisher prefix (2–8 chars; defaults to `pamext` or the last-used value from `.extension-state.md`), version bump (patch / minor / major / no-bump), target environment URL (from `pac org who`). Builds the PCF if needed, then pushes. Decoupled from /generate-pcf-companion so the engineer can scaffold and customize locally, then deploy when ready. Updates `.extension-state.md` with deployment history (timestamp, env URL, version, prefix used).
Activate a brutally honest, skeptical architectural partner that stress-tests ideas, architectures, and assumptions. Use when the user says "reality check", wants their design challenged, asks if their idea is sound, wants a devil's advocate review, or wants architectural critique without hand-holding.
Use to unblock Blocked, stalled, or pending-decision items in a development plan; not to write a plan from scratch, conduct an overall review, or implement a plan. Investigate and resolve blockers; when user input is needed, use blocking questions via tools; hand off external dependencies through CRD; record decisions and update the plan.
Use when the user says 'set up respira', 'respira not connecting', 'check my respira connection', or 'fix respira'. Walks through first-time setup and diagnoses connection failures: timeouts, 401s, 403s, and plugin or server version mismatches.
Revit 2026 API documentation lookup and reference. Triggered when the user asks about Revit API classes, methods, properties, or enum usage, looks up APIs related to Revit development, or needs to confirm API signatures and parameters. Covers: (1) looking up members and usage of a specific class/interface (2) searching for the APIs needed to implement a feature (3) viewing method signatures and parameter descriptions (4) understanding namespace structure and inheritance (5) confirming the correct way to call the Revit API. Keywords: RevitAPI, Autodesk.Revit, Element, Document, Transaction, FilteredElementCollector, ExternalCommand, ExternalApplication, Wall, Floor, FamilyInstance, FamilySymbol, Parameter, BuiltInParameter, BuiltInCategory, Selection, GeometryElement, Solid, Face, CurveLoop, Level, View, ViewSheet, XYZ, Line, Arc, IExternalCommand, IExternalApplication, UIApplication, UIDocument, Ribbon, PushButton, ExtensibleStorage, SubTransaction, TransactionGroup, ElementId, Reference, TaskDialog.
Building Roblox UI — engine primitives (GuiObjects, UDim2, AnchorPoint, layouts, inputs, containers) plus the Fusion 0.3 reactive framework. Use when writing, reviewing, or debugging UI components, sizing/positioning, layout structures, input handling, render order, or component lifecycle. UI layer only — engine semantics live in roblox-dev; language rules live in luau-expert; Rojo/Wally workflow lives in roblox-toolchain.
Scout Rule — identify the top 3 highest-impact improvement opportunities in files you're already touching. Analyzes entire file content, not just changed lines. Focuses on pre-existing code quality, not PR bugs. Use when preparing a PR, during code review, or after completing a feature.
Set up a Sui Move smart contract project with OpenZeppelin Contracts for Sui. Use when users need to: (1) install the Sui CLI and Move toolchain, (2) create a new Sui Move package, (3) discover and add OpenZeppelin Sui dependencies to Move.toml via the Move Registry (MVR), (4) learn the integration pattern from the library's examples and API docs before implementing, or (5) understand Sui Move import conventions and build/test commands for OpenZeppelin.
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry point (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review evidence, lands it through the supported path, and cleans up only proven-stale branches and worktrees. Stops at the requested endpoint and never bumps versions, edits changelogs, tags, or publishes. Triggers: “ship it,” “ship this,” “open a PR,” “push and PR,” “land this PR,” “merge PR and clean up,” “check CI on my PR,” “resume the ship run,” “/ship-workflow.”
Apply this opinionated workflow when reverse-engineering legacy or undocumented systems: scope, explore the code, trace data flows, document in EARS format, flag uncertainties. For code archaeology, onboarding, and requirements extraction.
Fetch upstream, merge (worktree) or rebase (tracked branch), stage all changes, enforce gitignore hygiene, run ADR compliance checking on modified artifacts, rebuild stale artifact indexes, generate a descriptive commit message from the diff, commit, and push to the current branch's upstream. Handles merge conflicts by preferring local changes for config/project files and upstream for scaffolding.
Implement ContextMenuStripEx enhanced context menus in Windows Forms applications. Use this when working with context menus, right-click functionality, or popup menus with custom items. Covers menu configuration, multi-level menus, keyboard shortcuts, and appearance customization in WinForms.
Comprehensive guide for implementing and managing Syncfusion Windows Forms licensing. Use this when troubleshooting license validation errors, generating or registering license keys, or configuring CI/CD license validation. This skill covers license key management, trial vs licensed versions, NuGet package licensing, and build server scenarios.
Decompose high-level objectives into atomic implementation tasks for Python/React projects. Use when breaking down large features, multi-file changes, or tasks requiring more than 3 steps. Produces independently-verifiable tasks with done-conditions, file paths, complexity estimates, and explicit ordering. Creates persistent task files (task_plan.md, progress.md) to track state across context windows. Does NOT cover high-level planning (use project-planner) or architecture decisions (use system-architecture).
Systematic technical debt analysis across architecture, testing, documentation, and infrastructure. Investigates the codebase, scores findings by impact and effort, and generates a prioritized TECH_DEBT.md remediation plan. Delegates to specialized skills for code quality (scout) and linting (lint-fix). Use when assessing overall project health, planning cleanup sprints, or onboarding to an unfamiliar codebase.
Builds Python Tilebox workflows for Earth observation and geospatial processing, including satellite imagery queries, AOI and time-series pipelines, mosaics, spectral indices, classification, segmentation, change detection, and tiled ML or object detection. Use when implementing or modifying this processing, including when Tilebox is not named and no other execution platform is established.
Split a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — as text edges in one file per ticket locally, or as native blocking links on a real tracker.
Use this skill when the user needs to create or update Trae IDE rules (.trae/rules/*.md) to constrain AI behavior. Applies to: enforcing code style, naming conventions, commit message formats, or making the AI always follow a specific pattern. Not for skills (use project-skill-writer) or agents (use project-agent-writer). Trigger words: 'create rules,' 'add rule,' 'set code style,' 'enforce conventions,' 'configure AI behavior,' 'AI rules,' 'always do X', or when the user needs consistent AI behavior across sessions.
Creates new uni-app projects via the official CLI or HBuilderX with Vue 2/Vue 3 template selection, manifest.json and pages.json configuration, and directory structure setup. Use when the user wants to scaffold a new uni-app project, initialize project files with a single command, or set up the development environment.
Integrates uCharts data visualization into UniApp projects including easycom configuration, pages.json and manifest.json setup, platform-specific handling (H5, mini-program, App, nvue), and chart lifecycle management. Use when the user needs to add charts to a UniApp project, configure uCharts components, or handle cross-platform chart rendering.
Building games and interactive experiences with Unity engine, C#, MonoBehaviours, and modern Unity patternsUse when "unity, unity3d, unity game, unity development, monobehaviour, prefab, scriptableobject, ecs unity, dots unity, unity physics, unity ui, addressables, unity coroutine, burst, unity jobs, unity, unity3d, gamedev, game-engine, csharp, c#, monobehaviour, prefabs, scriptableobjects, ecs, dots, mobile, console, pc, vr, ar" mentioned.
Build on vibenet — Base's devnet for native account abstraction (EIP-8130), payer gas sponsorship (ERC-8168), and Cobalt 200ms native blocks. Use whenever the user mentions vibenet, EIP-8130, ERC-8168, 8130 accounts, native account abstraction, session keys, actors, policies, payers, gas sponsorship on Base, 200ms blocks, Cobalt, BaseTime, timestampMs / blockTimestampMs, sub-second or millisecond block timestamps, migrating from Flashblocks, or newHeads / WebSocket streaming on vibenet — or is writing code that creates or operates 8130 smart accounts, authorizes session-key actors, sends batched calls, sponsors gas with a payer, queries or streams vibenet blocks, times a transaction's inclusion, or wires a frontend/script against the vibenet devnet or Base Sepolia.
Refactor cluttered or flat interfaces so users instantly see what matters, using size, weight, contrast, and whitespace — not more color. Use when the user says 'it looks cluttered', 'everything competes for attention', 'it looks amateur/flat', 'users can't find the button', 'make this scannable', 'this screen is overwhelming', or shares a screen where nothing stands out. Audits the actual component: lists every element's current visual weight vs intended priority, then delivers refactored component code (CSS/TSX) with a before/after hierarchy table explaining each change. De-emphasizes secondary elements before amplifying primary ones, and applies Gestalt grouping via spacing.
Use this skill when reviewing or changing an existing Vite + TanStack Router project architecture, especially routes, loaders, validateSearch, services, hooks, Vite/TanStack Router platform setup, and nested shared folders such as src/lib or src/services. Do not use for TanStack Start or generic Vite apps without TanStack Router.
Generate accurate Volcengine SDK examples by locating an API through API Explorer search, fetching its swagger, and calling api/common/explorer/make-code with user-provided Params. Use when the user asks how to write Volcengine SDK code, generate SDK samples, or call a Volcengine API in Python, Go, Java, PHP, cURL, Node.js. Supports Chinese and English API names such as "角色扮演", "AssumeRole", or "STS AssumeRole". Also use for explicit SDK configuration questions about retry, timeout, AK/SK, STS, AssumeRole, temporary credentials, proxy, connection pooling, SSL, debug mode, request signing, response parsing, and error handling. If the user only needs API parameters, enum values, required fields, error codes, response schemas, pagination, or API comparisons, hand off to volcengine-api. If they need CLI-based operations, hand off to volcengine-cli.
Integrates MetaMask Embedded Wallets (Web3Auth) for non-custodial wallets via social login or custom JWT (Firebase, Auth0, Cognito). Use when integrating @web3auth/modal (React, Vue, Next.js, Vite, Angular), @web3auth/react-native-sdk (Expo/bare RN—Custom Dev Client, not Expo Go), web3auth_flutter, native Android/iOS, Unity, or @web3auth/node-sdk. Invoke for Sapphire devnet/mainnet, dashboard client ID, grouped connections (same address across Google + email passwordless), implicit vs JWT auth flows, useWeb3AuthConnect, id_token server-side verification, or SDK migration (web v11, RN v9, OPENLOGIN_NETWORK/LOGIN_PROVIDER legacy). Also use when users get different wallet addresses per login method or need RN Metro setup/withWeb3Auth migration. Do NOT use for MetaMask browser extension only, RainbowKit/ConnectKit without embedded wallets, or unrelated smart-contract work.
Use when an Adapty question has no page already linked in the skill you are holding — how a product or dashboard feature behaves, what a setting does, a limit, store connections, Flow Builder, the Developer CLI, the server-side API, or an SDK method on any platform. Also use when you need a docs page and have no URL for it, or when a docs URL you tried returned 404. Not for making a change to an app's Adapty setup — connecting a store, or creating products, access levels or placements — which `adapty-integration` carries out through the Adapty CLI.
Use this skill to gate Elixir, OTP, Ecto, and Phoenix code with a pass/fail adversarial review — a single blind reviewer subagent judges a diff or file set against 19 decidable rules that catch architecture ported from an alien paradigm, covering enterprise layering (repository wrappers over Ecto, service-object tiers, DI behaviours with a single implementation, logic trapped in effectful callbacks), processes as objects (GenServer-per-entity, Agents as mutable variables, leaked message protocols, singleton managers), anemic data (bare maps as entities, boolean-flag state, hand-rolled type dispatch, 32+-field structs), defensive control flow (raise/rescue as branching, nil-guard swallowing, raw input past the boundary), transliterated loops, and needless metaprogramming (macro DSLs for data, use-as-import, compile-time coupling). Trigger it before merging Elixir work, or to check agent-authored code. It renders verdicts only, never fixes; Ecto-dependent rules go N/A without Ecto.
Manage App Store Connect authentication using the `asc` CLI tool. Use this skill when: (1) Logging in with an API key: "asc auth login", "save my credentials", "set up authentication" (2) Managing multiple accounts: "asc auth list", "switch account", "use work account", "add another account" (3) Switching the active account: "asc auth use NAME", "switch to personal account" (4) Logging out: "asc auth logout", "remove credentials", "remove account" (5) Verifying current credentials: "asc auth check", "which account am I using?" (6) Updating account settings: "asc auth update --vendor-number", "save my vendor number" (7) Explaining the credentials file format (~/.asc/credentials.json) (8) Troubleshooting 401 auth errors or "missing credentials" errors
Manage power and performance metrics and diagnostic logs using the `asc` CLI tool. Use this skill when: (1) Listing performance metrics for an app: "asc perf-metrics list --app-id <id>" (2) Listing performance metrics for a build: "asc perf-metrics list --build-id <id>" (3) Filtering metrics by type: "asc perf-metrics list --app-id <id> --metric-type LAUNCH" (4) Listing diagnostic signatures for a build: "asc diagnostics list --build-id <id>" (5) Filtering diagnostics: "asc diagnostics list --build-id <id> --diagnostic-type HANGS" (6) Viewing diagnostic logs: "asc diagnostic-logs list --signature-id <id>" Also trigger when the user mentions: performance metrics, launch time, hang rate, disk writes, memory usage, battery life, termination, animation hitches, diagnostic signatures, call stacks, power metrics, app performance monitoring, "why is my app slow", "check hangs", "check launch time"
Release an app version to the App Store using `asc` CLI. Guides the agent through: bump version, archive, upload, update metadata, and submit. Use this skill when: (1) User says "release", "ship", "submit to App Store", "publish new version" (2) User says "bump version and upload" (3) User says "prepare release for iOS/macOS" (4) User says "update What's New and submit"
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.