Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Guide for building Graph Neural Networks with PyTorch Geometric (PyG). Use this skill whenever the user asks about graph neural networks, GNNs, node classification, link prediction, graph classification, message passing networks, heterogeneous graphs, neighbor sampling, or any task involving torch_geometric / PyG. Also trigger when you see imports from torch_geometric, or the user mentions graph convolutions (GCN, GAT, GraphSAGE, GIN), graph data structures, or working with relational/network data. Even if the user just says 'graph learning' or 'geometric deep learning', use this skill.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Explain and use Truto's core concepts and APIs — unified/proxy/custom APIs, integrated accounts, environments, webhooks, connection flows — and write application code against them. Covers what each concept is, how to call it, and data-access patterns for the user's codebase.
Enforce portable Turborepo + workspace monorepo house style: apps/packages layout, catalog pins, turbo.jsonc transit/cache rules, package scopes and exports, env ownership, scripts, filters, and dependency boundaries. Use when scaffolding a monorepo, adding a workspace, reviewing turbo/package layout, or when the user asks for turborepo-architecture. Optional with-* overlays for catalog, Knip, Oxlint/Oxfmt, Vitest workspaces, env packages, Effect packages, typegen, nested scopes, Docker prune, boundaries, and local compose. Not a Turbo CLI docs skill.
Harden code with patient, layered defense. The turtle carries its shell — bone-deep protection grown from within, not strapped on. Use when building new features to ensure they're secure by design, or when auditing existing code for deep vulnerabilities that slip through standard reviews.
Expert tvOS decisions for iOS developers: when to use custom focus effects vs system defaults, Siri Remote gesture trade-offs, Top Shelf content strategies, and 10-foot UI adaptation patterns. Use when building tvOS apps, debugging focus issues, or designing TV-optimized interfaces. Trigger keywords: tvOS, Focus Engine, @FocusState, isFocused, focusable, focusSection, Siri Remote, Top Shelf, TVTopShelfContentProvider, 10-foot UI, CardButtonStyle, large cards
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
Automates non-PHP TYPO3 upgrade migrations with Fractor for FlexForms, TypoScript, Fluid, YAML, XLIFF translation files, Htaccess, and composer.json changes. Use when running or configuring Fractor, upgrading non-PHP TYPO3 files, migrating FlexForms or TypoScript, modernizing Fluid templates, or combining Rector and Fractor for v14 work.
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.
Specialist in ViewComponent implementation, component architecture, slots, previews, and method exposure patterns. Invoke this agent when creating or modifying ViewComponents, implementing component slots, setting up previews, debugging component rendering issues, or ensuring proper method delegation from services.
Best practices and integration guide for Visa developer APIs and payment protocols — covers platform setup, authentication, encryption, and product-specific workflows. Trigger keywords: VDP, Visa Developer Platform, VIC, Visa Intelligent Commerce, MPP, Machine Payments Protocol, X-Pay Token, Two-Way SSL, Mutual TLS, MLE, JWE, MCP integration, HTTP 402, network tokens, Visa Developer, Visa MLE.
Vue 3 with Composition API. Covers reactivity, composables, lifecycle hooks, and component patterns. USE WHEN: user mentions "Vue", "Composition API", "composables", "ref", "reactive", "v-model", "v-if", "v-for", asks about "Vue 3 patterns", "reactive state in Vue" DO NOT USE FOR: Vue 2 Options API - use legacy Vue documentation instead, React - use `frontend-react`, Angular - use `angular`, Svelte - use `svelte`
Build or maintain controller-based ASP.NET Core APIs when the project needs controller conventions, advanced model binding, validation extensions, OData, JsonPatch, or existing API patterns. USE FOR: working on controller-based APIs in ASP.NET Core; needing controller-specific extensibility or conventions; migrating or reviewing existing API controllers and filters. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Master orchestration workflow for reverse engineering complex Web/JS sites. Covers reversing sign/token/cookie/header/body/websocket fields, heavy obfuscation, junk instructions, control flow flattening, JSVMP, worker/wasm, browser vs. Node differentials, environment patching, local reproduction and regression, and case leads such as Akamai/Kasada/PX/reese84/Tongdun/a_bogus/Tencent captcha/Alibaba captcha/JSVMP/227/226/wasm/protobuf/rid/fuid/fs/bx-pp/run_js/storage.estimate/animationend. By default it coordinates the three MCPs jshook + js-reverse + chrome-devtools-mcp for debugging and analysis, switching to specialized skills at the locate, recover, runtime, env-patch and replay stages.
Complete reference for WoW Retail Encounter Journal, Mythic+/Challenge Mode, Instance, Scenario, Raid Lock, and Season APIs. Covers EncounterJournal (dungeon/raid boss database, loot tables, section navigation), C_ChallengeMode (M+ keystones, affixes, timers, best times), C_MythicPlus (weekly runs, seasonal data, rating), ScenarioInfo (delves/scenarios objectives and stages), InstanceLeaverInfo (deserter), RaidLocks (saved instances), C_SeasonInfo (seasonal info), and related events. Use when working with dungeon/raid encounter data, M+ keystones, mythic plus scores, scenario stages, raid lockouts, or seasonal content.
Clones a live WordPress (or other CMS-driven) site into a static HTML site deployable on any static host (Cloudflare Pages, Netlify, Vercel, S3+CloudFront, plain Apache/nginx). Use when the user wants to "scrape", "freeze", "archive", "static-ify", or "move to [host]" a WordPress site, or asks to turn a sitemap into deployable static HTML. Pulls every URL from sitemap_index.xml, fetches all assets, rewrites paths to be root-relative, strips WP runtime markup, and outputs a flat directory ready to deploy with no build command.
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
Create web interface designs that match Chinese aesthetic sensibilities. Use when the user needs to design web pages, components, pages, or app interfaces. Focuses on a clean, refined, harmonious design style and generates front-end code that can be used directly. Not for reviewing existing UI code, optimizing existing component implementations, or generating pure back-end code or non-web UI.
WCAG 2.1/2.2 compliance, WAI-ARIA implementation, screen reader optimization, keyboard navigation, and accessibility testing expert. Use PROACTIVELY for accessibility violations, ARIA errors, keyboard navigation issues, screen reader compatibility problems, or accessibility testing automation needs.
Design and audit admin audit logs covering privileged actions, configuration changes, user/role management, billing/admin settings, data export/delete, API tokens, integrations, security events, retention, tamper evidence, customer access, filters, exports, SIEM, alerting, privacy, and enterprise evidence. Use when customers or operators need trustworthy administrative traceability.
Clarifies the relationship between aggregates and transaction boundaries, and detects and corrects the anti-pattern of including multiple aggregates in a single transaction. Applies the principle that an aggregate is a strong consistency boundary, and that when a use case updates multiple aggregates it should use eventual consistency. Use when detecting transaction boundary issues during code review, use case design, or refactoring. Target languages: language-agnostic (Java, Kotlin, Scala, TypeScript, Go, Rust, Python, and all others). Triggers: activated by transaction boundary related requests such as "updating multiple aggregates in the same transaction", "the use case has @Transactional", "how to keep consistency between aggregates", "should we use the Saga pattern", "transaction boundary design", "one transaction one aggregate", "implementing eventual consistency", "transactions spanning aggregates".
Optimize e-commerce search relevance across the full pipeline from query understanding to result presentation. Use this skill when the user needs to improve search quality, implement query processing features, or diagnose search relevance issues — even if they say 'search results are bad', 'improve product search', or 'search relevance optimization'.
Transform vague intent or incomplete requirements into validated, testable requirements through diagnostic state progression and structured dialogue. Use when user has an idea, feature request, problem statement, or existing requirements document that needs clarification or validation before design or implementation.
Comprehensive guide for AntV L7 geospatial visualization library. Use when users need to: (1) Create interactive maps with WebGL rendering (2) Visualize geographic data (points, lines, polygons, heatmaps) (3) Build location-based data dashboards (4) Add map layers, interactions, or animations (5) Process and display GeoJSON, CSV, or other spatial data (6) Integrate maps with AMap (GaodeMap), Mapbox, Maplibre, or standalone L7 Map (7) Optimize performance for large-scale geographic datasets
Specialized skill for working with NextAuth.js authentication including session management, JWT tokens, role-based access control, and protected routes. Use when implementing authentication features, securing routes, managing user sessions, or debugging auth issues.
Use when encrypting data, signing payloads, verifying signatures, generating keys, using Secure Enclave, migrating from CommonCrypto, or adopting quantum-secure cryptography. Covers CryptoKit design philosophy, AES-GCM, ECDSA, ECDH, Secure Enclave keys, HPKE, ML-KEM, ML-DSA, and cross-platform interop with Swift Crypto.
Use when implementing passkey sign-in, replacing passwords with WebAuthn, configuring ASAuthorizationController, setting up AutoFill-assisted requests, adding automatic passkey upgrades, or migrating from password-based authentication. Covers passkey creation, assertion, cross-device sign-in, credential managers, and the Passwords app.
Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing pytest/JUnit tests) — and wants the target patched until those failures are closed without breaking what already works. It points straight at the failed cases (normalize any source with tools/ingest.py), fixes one root-cause class per iteration, and re-checks with tools/verify.py — oracle mode against a red-team oracle, or tests mode against the test suite — keeping a patch only if it closes a class while nothing that passed before regresses, else reverting; loops until every class is closed (dry) or the budget runs out, then opens a pull request with the patch set. The defensive fixer half of a find→fix setup. Not for discovering new failures (that is red-team), and not for editing the oracle, tests, or holdout that define ground truth.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
Configure clang-format code formatting. Use when: user mentions clang-format or .clang-format, analyzing code style/patterns, creating/modifying formatting config, troubleshooting formatting, brace styles/indentation/spacing/alignment/pointer alignment, or codifying conventions.
Validate or generate commit messages per the Conventional Commits specification. Use when: checking a commit message before pushing, generating a compliant message from a diff or change description, or integrating commit quality into a CI/CD workflow. Grounded in prompts/coding/standards/cicd/commit_standards.md.
Analyses code and produces a structured violation report against clean coding standards. Use when: auditing code before a refactoring task, reviewing a PR for clean coding compliance, or establishing a baseline before applying clean-code-refactor. Produces a violation report that clean-code-refactor and data-engineer Implement Mode can act on. Supports Python, JavaScript/TypeScript, C#, and Rust. Supports both general (Clean Code) and OB (BORO Quick Style Guide) convention sets via the `standard` parameter.
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.