Claude Skills by NeverSight

Meta (Facebook & Instagram) advertising strategy for AI agents. Covers fundamentals, ad creative best practices, campaign structure, audience targeting, budget management, and performance analysis. Use when the user wants to plan, create, launch, or optimize Meta ads, or when they need to understand how the platform works before spending money. Not for Google Ads, TikTok Ads, LinkedIn Ads, or general marketing strategy outside Meta.

AI agent for managing Google Ads and Meta (Facebook & Instagram) Ads. Create and publish campaigns, ad sets/groups, and ads; manage drafts; upload images and video; research keywords and audiences; browse the ad library; and generate ads with AI. Works through the AdKit CLI or MCP. Load when the user wants to execute ad operations or is ready to publish a campaign. Not for strategy, copywriting, creative advice, or learning about ads.

Reference for AdKit (CLI or MCP). Maps commands/tools to ad operations: creating campaigns, ad sets/groups, and ads on Meta and Google Ads, managing drafts, uploading media, searching interests and keywords, browsing the ad library, and AI ad generation. Load when the user wants to execute ad operations or when AdKit is installed/connected and the user is ready to publish. Not for strategy, copywriting, creative advice, or learning about ads.

Specialised skill for the AMT Docker Bench — a multi-container simulation of a T264 autonomous truck. Use when asked about docker_bench containers (rpk1, rpk2, rpk3, platform-sim, avi-radio, test-manager, vas-aht), Docker Compose configuration, network topology (onboard/offboard/CAN/local-fms-network), NAT setup, CIC/RPK version selection, T264 simulator, VAS:AHT integration, DDS QoS profiles, IP address remapping, overlay files, run_tests.sh, Docker Bench version compatibility, compatible FM...

ghostDDS is a C++17 application that reads RTI Connext DDS recordings from SQLite databases and provides controllable playback with filtering, QoS visualization, type decoding, and multiple front-end options. Use when asked about ghostDDS architecture, storage layer, playback engine, CDR decoding (XCDR1, XCDR2/D_CDR2, type evolution, bulk decode), type system, XML type parsing, filtering, QoS inspection, REST API, web server, WebSocket streaming, SSE events, client-side CDR decoding, JavaScri...

Expert in integrating GhostDDS into an IRIS-like web visualisation platform to enable playback of RTI Connext DDS recording databases without any RTI runtime or licence, while preserving existing live DDS mode. Use when asked about integrating GhostDDS, adding recording playback to IRIS, removing RTI replay dependency, creating a DataBridge abstraction, adding playback endpoints, migrating replay frontend to unified API, or troubleshooting GhostDDS integration issues.

Specialised skill for running and troubleshooting Docker Bench within the Imperium FMS local development environment. Use when asked about Imperium Docker Bench, AMT Docker Bench in the context of Imperium, startAssetDockerBench, startAsset -useDockerBench, asset-docker-compose files, .env-asset-AHT001-docker-bench, .env-asset-AHT002-docker-bench, Docker Bench networking in Imperium, AVI radio NAT in Imperium local-environment, CIC/RPK version selection for Imperium assets, DDS configuration ...

Copywriter sênior especialista em direct response. Escreve copies, VSLs, scripts de ads, headlines, leads, páginas de vendas, emails e qualquer peça de copy usando frameworks consagrados de Breakthrough Advertising, Great Leads, Copy Logic, Architecture of Persuasion, Halbert Copywriting Method, Quick Start Copywriting System, A Carta de Vendas de 16 Palavras, As Armas da Persuasão e Playbook VSL DR Expert. ATIVAR sempre que o usuário pedir para escrever copy, VSL, anúncio, ad, script de vend...

Use when creating or refactoring Astro sections, reusable section modules, section-specific markup, or section-level CSS in this repository. Trigger for section extraction, repeated section cleanup, CTA block restructuring, and static-vs-client decisions inside Astro components.

Use when planning or restructuring homepage, service page, about page, campaign page, or section order for this marketing website. Trigger for narrative flow changes, section sequencing, proof placement, CTA pacing, and page-level composition decisions.

Use when adding or changing animations, smooth scrolling, carousel behavior, lazy loading, service worker behavior, hydration strategy, or other performance-sensitive front-end behavior in this Astro site. Trigger for Lenis, Embla, reveal effects, runtime media loading, and interaction code that can affect responsiveness.

Identify and exploit file path traversal (directory traversal) vulnerabilities that allow attackers to read arbitrary files on the server, potentially including sensitive configuration files, credentials, and source code.

Provide a comprehensive command reference for penetration testing tools including network scanning, exploitation, password cracking, and web application testing. Enable quick command lookup during security assessments.

Provide comprehensive techniques for escalating privileges from a low-privileged user to root/administrator access on compromised Linux and Windows systems. Essential for penetration testing post-exploitation phase and red team operations.

Audit a project and recommend the highest-value skills to add or update.

Guía al usuario, paso a paso y con preguntas, para diseñar su propio harness — un flujo de trabajo chico y de un solo propósito, armado con la combinación de skills, reglas o hooks que la tarea realmente necesite — para una tarea recurrente de su proyecto, como revisión de deuda técnica, seguridad, despliegue, bug fixing, lo que necesite. Use when the user wants to build their own lightweight harness/workflow for a recurring project task, or asks how to package a repeatable agent process from...

Analiza un requerimiento sobre un ecosistema multirepo (carpeta padre con varios repos hijos documentados) y lo descompone en specs acotados por repo más los contratos de comunicación entre ellos. Use when the user describes a feature or requirement that spans a multirepo ecosystem and needs to know which repos are affected and what to build in each.

Despieza un PRD + Technical Design Document en un backlog ordenado de specs implementables, cada una lista para arrancar un ciclo de Spec-Driven Development (SDD). Use when the user asks to break down, decompose, or turn a PRD/technical design into a backlog, roadmap, list of features, or list of specs to implement.

Despieza un PRD + Technical Design Document en un backlog ordenado de specs implementables, cada una lista para arrancar un ciclo de Spec-Driven Development (SDD). Use when the user asks to break down, decompose, or turn a PRD/technical design into a backlog, roadmap, list of features, or list of specs to implement.

Genera el Technical Design Document + ADRs (formato MADR) + criterios de aceptación de un proyecto, entrevistando al usuario decisión por decisión a partir de su PRD (y opcionalmente su Design.md o un repo existente). Use when the user asks to generate, draft, or create a technical design document, system architecture, or architecture decision records (ADRs) for a project, greenfield or brownfield.

Revisa de forma adversarial un Technical Design Document y sus ADRs, buscando activamente huecos, riesgos y decisiones débiles en vez de validarlos. Use when the user asks to challenge, stress-test, get a second opinion on, or adversarially review a technical design document, architecture decisions, or ADRs.

Generates a PR description by reading docs/pull_request_template.md and filling it with bulleted points derived from the git diff, commit log, and changed files on the current branch. ALWAYS use this skill whenever the user asks to create a PR, push a PR, open a pull request, or make a PR — in any form. This skill MUST run before `gh pr create` is called, every single time.

Use BEFORE writing any code, planning, or brainstorming. This is the entry point for all UX Superpowers skills. Activates when a user wants to build, create, or implement anything — web apps, CLIs, APIs, mobile apps, infrastructure, internal tools, or any software. Guides through a structured UX discovery phase: problem definition, persona creation, user journeys, jobs-to-be-done, and success metrics. Accepts raw user data (interviews, feedback, analytics) OR guides from scratch. Produces a U...

Commit all working changes on the current branch, push to origin, and open a GitHub PR against main using the loaded spec for context. Adnan reviews and squash-merges manually on GitHub.

Full-featured Nextcloud integration for Hermes — manage files, notes, tasks, calendar events, and contacts via WebDAV, Nextcloud Notes API, and CalDAV/CardDAV. Works with self-hosted Nextcloud instances.

Use when working with the Adobe I/O CLI plugin @adobe/aio-cli-plugin-ffcpe (FFCPE — Firefly Creative Production for Enterprise). Covers installation, authentication, env overrides, and all `aio ffcpe catalog` commands. Use for terminal workflows, scripting catalog changes, or explaining how developers should invoke this plugin. Some users still say **Workflow Builder**; that name referred to the same product area — the CLI topic is **`ffcpe`** (`aio ffcpe`).

Use when authoring or validating an FFCPE (Firefly Creative Production for Enterprise) custom-action catalog-entry.json for the run-workflow service (App Builder actions). Covers installing the Adobe I/O CLI and this plugin, schema shape, org/auth, agent discovery, customActionConfig, validation, workflow usage, and troubleshooting. Use **`aio ffcpe catalog`** to validate/register—never raw curl. Older searches may say **Workflow Builder**; same plugin and topic **`ffcpe`**.

Use when optimizing a hot path in @adobe/data — especially when an interface (Column, TypedBuffer, ManagedArray, etc.) has many concrete instances created from closure-returning factories and is dispatched from a tight per-row loop. Provides the closure→class refactor pattern, the V8 hidden-class reasoning behind it, accept/reject criteria, and the discipline that keeps the public API closure-free even when implementations are class-based.

Helps Adobe App Builder developers build FFCPE (Firefly Creative Production for Enterprise) custom actions using @adobe/ffcpe-custom-node-core and @adobe/ffcpe-custom-node-app-builder (OpenWhisk web + worker actions, Hono, submit/status HTTP contract, inputs/outputs, IMS-aware routes). Use when the user is wiring a custom-action app in App Builder, implementing FfcpeNodeWorkerHandler, mounting routes with mountFfcpeNodeRoutes, configuring web: raw OpenWhisk actions, debugging submit/statusUrl...

Review code for AEM Edge Delivery Services projects. Use at the end of development (before PR) for self-review, or to review pull requests. Validates code quality, performance, accessibility, and adherence to EDS best practices.

Generate structured HTML from authoring analysis for AEM Edge Delivery Services. Creates section structure, applies block tables, handles metadata, and manages images folder.

Analyze content sequences within a section and provide neutral descriptions for AEM Edge Delivery Services. Invoked per section during page import to identify breaking points between default content and blocks.

Import a single webpage from any URL to structured HTML content for authoring in AEM Edge Delivery Services. Scrapes the page, analyzes structure, maps to existing blocks, and generates HTML for immediate local preview. Also triggered by terms like "migrate", "migration", or "migrating".

Preview and verify imported content in local AEM Edge Delivery Services dev server. Validates rendering, compares with original page, and troubleshoots common issues.

Scrape webpage content, extract metadata, download images, and prepare for import/migration to AEM Edge Delivery Services. Returns analysis JSON with paths, metadata, cleaned HTML, and local images.

Guide for testing code changes in AEM Edge Delivery projects including blocks, scripts, and styles. Use this skill after making code changes and before opening a pull request to validate functionality. Covers unit testing for utilities and logic, browser testing with Playwright/Puppeteer, linting, performance validation, and guidance on which tests to maintain vs use as throwaway validation.

Generate accessible color themes using @adobe/leonardo-contrast-colors. Use when the user needs help building contrast-based color palettes, checking WCAG accessibility, creating adaptive themes, or using the Leonardo API.

Set up CI/CD pipelines for Adobe App Builder projects. Generates GitHub Actions workflows using adobe/aio-cli-setup-action@3 and adobe/aio-apps-action@3.3.0, plus patterns for Azure DevOps and GitLab CI. Handles OAuth S2S secrets injection, multi-workspace promotion (stage → prod), deploy gating with manifest validation. Use this skill whenever the user mentions CI/CD for App Builder, GitHub Actions for aio deploy, automated deployment pipelines, continuous integration, continuous delivery, d...

Use this skill whenever the user wants browser-based end-to-end tests for an Adobe App Builder application. Covers Playwright E2E testing for ExC Shell SPAs, AEM extension UIs, and full-stack flows. Use when the user mentions: "E2E test", "end-to-end test", "Playwright", "browser test", "test my SPA in the browser", "test my AEM extension", "test the full flow", "integration test with UI", "headless browser test", "E2E in CI". This skill is for BROWSER-based testing only. For Jest unit tests ...

Generate React Spectrum UI components for Adobe Experience Cloud Shell SPAs and AEM UI Extensions. Provides patterns for pages, forms, data tables, dialogs, and navigation using @adobe/react-spectrum. Guides ExC Shell integration with @adobe/exc-app including runtime.done(), IMS token passthrough, and shell theming. Guides AEM UI Extension development with @adobe/uix-guest for Content Fragment Console, CF Editor, Universal Editor, and Assets View surfaces. Trigger on: building App Builder UI,...

Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.

Adobe Experience Platform 블루프린트 저장소에 대한 새로운 사용 사례 패턴 콘텐츠의 생성 안내서입니다. 새 사용 사례 패턴을 추가하거나 구현 지침 콘텐츠를 만들거나 사용자가 블루프린트 사이트에 패턴 추가를 언급할 때 이 기술을 사용합니다. 전체 워크플로를 처리합니다. 패턴 정보를 수집하고 올바른 템플릿 구조로 Markdown 파일을 생성하며 모든 상호 참조 페이지(TOC.md, overview.md)를 업데이트합니다.

Criação de guia de novo conteúdo padrão de caso de uso para o repositório de blueprints do Adobe Experience Platform. Use essa habilidade ao adicionar um novo padrão de caso de uso, criar conteúdo de orientação de implementação ou quando o usuário mencionar adicionar padrões ao site de blueprints. Lida com o fluxo de trabalho completo: coleta de informações de padrão, geração do arquivo do Markdown com a estrutura de modelo correta e atualização de todas as páginas de referência cruzada (TOC....

Routes docs-driven repository work to the correct workflow stage and preserves handoff context. Use when the next step is unclear between bootstrap, clarification, roadmap planning, task preparation, or execution.

Use when initializing, bootstrapping, creating, or scaffolding the minimum docs-driven workflow layout for a repository before roadmap planning, specs, or implementation tasks exist.

Use when a request or repository needs roadmap decomposition before spec writing because milestone boundaries, module grouping, or independently reviewable tasks are unclear.

Use when task-local spec or plan work is complete and a concrete docs/tasks task should be implemented through the repository's simple direct execution path.

Use when a docs-driven repository has a selected or selectable concrete docs/tasks task and needs task-local spec or implementation governance before code changes.

FastAPI authentication with JWT, OAuth 2.1, RBAC, and API keys using python-jose + passlib. Use for: login endpoints, token issuance, protected routes, role checks, social login. Triggers: auth, JWT, token, login, OAuth, RBAC, password, bearer, session, middleware.

Break down epics into implementable user stories with acceptance criteria, estimates, dependencies, and sprint groupings. This skill should be used for epic planning and backlog grooming.