adobe

Migrates legacy AEM (6.x, AMS, on-prem) to AEM as a Cloud Service using BPA CSV/cache, CAM/MCP discovery, and a one-pattern-per-session workflow. Use to review/scan a project for AEMaaCS migration (generates a read-only migration-runbook.md covering all…

Crawl an existing website (capped, multi-page) and seed stardust/current/ with PRODUCT.md, DESIGN.md, DESIGN.json, a per-page inventory, and the consolidated brand surface — the captured design system, palette, typography, motifs, and voice of the live site.…

Same-design migration — re-platform a site to AEM Edge Delivery (or any clean front end) keeping its current design near pixel-perfect. Recreates key pages (one archetype per page type) as clean re-authored HTML/CSS (never DOM copies), verifies each against…

Convert per-page styled HTML prototypes (stardust under stardust/prototypes/**, or claude-design / Mobirise / Relume / Lovable / v0 / Figma-derived pages, or JSX prototypes pre-rendered to HTML, often under samples/) into Edge Delivery Services (EDS / AEM)…

Reconcile a converted/built web page against its source prototype with two complementary probes — a PIXEL/layout diff (stretched images, dropped wraps, blank renders, colour flips) and a STRUCTURAL content+typography diff (dropped/mis-slotted headings,…

Apply DESIGN, canon, and modules to every page in the inventory, producing a deployable static HTML site. Use to migrate or render the whole captured site into the redesigned static tree ("migrate the pages", "render the migrated site", "apply the design to…

Use this to turn a Figma design into an AEM Edge Delivery Services (EDS / AEM / Franklin / Helix) content page in Document Authoring (DA, da.live). Triggers: "build this Figma frame in EDS", "turn this Figma design into a DA page", "publish this design to…

Use when validating an App Builder app before submitting to Adobe Exchange, or when the user mentions Adobe Commerce app compliance, extension review, marketplace submission, or Adobe Exchange listing. Checks security requirements, project structure,…

Wire built features into a running application — import peer schemas, lazy-load peers, and mount the root UI.

Build a feature's data/ layer — data-type namespaces and the State spec. The first, foundational feature phase.

Build a feature's system-database — the real-time tick loop (systems the scheduler runs each frame). For real-time features only.

Build a feature's services/ layer — async capability contracts (ports to the outside world). Optional.

Build a feature's transaction-database — atomic mutations over the store.

Iteratively build an application or game phase-by-phase in clean subagents, reviewing each phase and refining the build-* skills / rules until each is optimal, then summarizing.

Review built feature/application output against the @adobe/data feature rules; report whether it is optimal and where any fix belongs. Read-only.

Build a feature's action-database — async orchestration over services and transactions. If the feature has async flows or side effects outside of the main store.

Generates GitHub pull request and issue descriptions — title, labels, and body — following Spectrum Web Components conventions. Prompts for a linked ticket if none is provided.

Defines when and how to run a consistency and validity self-audit on changed files and the migration plan. Apply before declaring any migration phase or significant implementation task complete.

Phase 1 of 1st-gen to 2nd-gen component migration. Use to understand the component, plan breaking changes, and define scope before any refactoring begins.

Dispatches to the correct design token update workflow (custom tokens only vs @adobe/spectrum-tokens version bump). Use whenever asked to update, bump, or upgrade design tokens, or when told to run a token update.

Phase 7 of 1st-gen to 2nd-gen component migration. Use to author the per-component MDX docs page and finalize Storybook stories so the component is usable and understandable by others.

Phase 3 of 1st-gen to 2nd-gen component migration. Use to move properties, methods, and types from 1st-gen to 2nd-gen while maintaining a clear public API.

Phase 8 of 1st-gen to 2nd-gen component migration. Use to run final checks, verify lint/tests/build/Storybook, update the workstream status table, and open a PR.

Author dedicated Storybook visual regression stories for 2nd-gen components. Use when adding or reviewing `.vrt.ts` files, Chromatic VRT coverage, forced-colors coverage, pseudo-state snapshots, global stylesheet coverage, or custom-property VRT coverage.

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.

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.

Analyze content sequences and determine authoring approach (default content vs blocks). Validates block selection and section styling for import/migration to AEM Edge Delivery Services.

Survey available blocks from local AEM Edge Delivery Services project and Block Collection to understand the block palette available for authoring. Returns block inventory with purposes to inform content modeling decisions.

Searches the aem.live documentation for information on AEM Edge Delivery Services features. Use this skill when you need more information about a feature, want guidance on how to implement a feature, and using existing tools you have to search the web isn't…

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

Identify section boundaries and content sequences within a scraped webpage for AEM Edge Delivery Services import. Performs two-level analysis (sections, then sequences per section) and surveys available blocks.

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.

Single entry point for all AEM as a Cloud Service Workflow skills. Covers workflow model design, custom process step and participant chooser development, launcher configuration, workflow triggering, and production support including debugging stuck/failed…

Debug AEM Workflow issues on AEM as a Cloud Service including stuck workflows, failed steps, missing Inbox tasks, launcher failures, stale instances, thread pool exhaustion, queue backlogs, purge failures, and permissions errors. Use when the user reports…

Design and create AEM Workflow models on AEM as a Cloud Service. Use when creating workflow models via the Workflow Model Editor or content package XML, defining step types (PROCESS, PARTICIPANT, DYNAMIC_PARTICIPANT, OR_SPLIT, AND_SPLIT), configuring step…

AEM as a Cloud Service Java/OSGi best practices, guardrails, and legacy-to-cloud pattern transformations. Use for Cloud Service–correct bundles, deprecated APIs, schedulers, ResourceChangeListener, replication, Replicator, JCR observation…

Create, modify, review, and harden configuration for the Adobe Dispatcher Apache HTTP Server module and Apache HTTPD in AEM as a Cloud Service environments only. Use for `.any`, vhost, rewrite, cache, and filter changes.

Investigate and triage runtime incidents involving the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration in AEM as a Cloud Service environments only, using runtime-backed MCP evidence.

Optimize performance of the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration for AEMaaCS cloud workflows only, with cloud-specific baseline and runtime verification.

Perform security audits for the Adobe Dispatcher Apache HTTP Server module and Apache HTTPD in AEMaaCS cloud workflows only, with cloud-specific hardening verification.

Feature guidance for Donut chart advanced labels (swatch + segment name + value/% + optional detail row, connected to the slice by a leader line). Use when generating a Donut with advanced labels enabled. Token values referenced here are defined in…

Feature guidance for the Benchmark Donut variant (2-segment donut with a reference line/target marker). Use when generating a Donut with a benchmark comparison line. Token values referenced here are defined in donut-chart-tokens.

Feature guidance for the 2-segment (binary) Donut chart variant. Use when generating a Donut with exactly 2 segments and no separate swatch legend. Token values referenced here are defined in donut-chart-tokens.

Donut-chart-specific design tokens (colors, sizes, typography, spacing, hover/emphasize behavior, and validation rules), sourced from the Figma "S2 – Charts" file. Use when generating, styling, or reviewing a Donut chart to get exact values instead of…

Feature guidance for Donut chart direct labels (segment name + value text placed directly around the ring, no connector line). Use when generating a Donut with direct labels enabled. Token values referenced here are defined in donut-chart-tokens.

Shared collision-avoidance algorithm for donut chart labels (Direct or Advanced) that stack vertically within the same hemisphere. Use whenever multiple small/adjacent segments produce overlapping label positions.

Feature guidance for the Donut chart's center-hole metric total/label (the summary number shown in the middle of the ring). Use when generating a Donut with Metric value/Metric label enabled. Token values referenced here are defined in donut-chart-tokens.

Feature guidance for the regular (multi-segment, non-binary) Donut chart variant. Use when generating a standard Donut with 2-6 segments and no benchmark. Token values referenced here are defined in donut-chart-tokens.

Analyze the partner's existing codebase across all detected surfaces and write service cards into service-cards/ — one per-surface card set (backend/, plus a UI set in mobile/, web/, ios/, or android/), always the shared context in shared/, and a…

Produce a fully branded, runnable partner app from partner-supplied mocks by reproducing the partner's UI on top of a reference app that already contains all the Adobe integration capabilities (claim, find-subscription, cancel, notify). Every partner's UI is…

Generate production-ready Adobe backend clients in the partner's existing backend stack: Phase 0 — a reviewable design approved before any code is written; Phase 1 — the IMS OAuth token service; Phase 2 — the typed Adobe Integration API client (Workflow, Get…

Generate a complete .env.example with all required Adobe integration variables, add .env to .gitignore, and add startup config validation to the backend.

Scan the entire codebase and produce a definitive integration checklist — what's done, what's partial, and what's missing. Share this with Adobe partner engineering when requesting stage access review.

Generate reviewable backend and UI Low-Level Designs (LLDs) for one feature, before any code is written — Phase A (backend LLD, the DG-3 gate) then Phase B (UI LLD, the DG-4 gate). See ../../manual/methodology/card-model.md#lld-section-contract and…

Generate comprehensive unit and integration tests for all Adobe integration code, using the partner's existing test framework and patterns.

Implement one Adobe integration feature end-to-end across all detected surfaces (backend route, mobile/native screen(s), web component(s)), from the feature's approved LLD, following the target repo's own conventions.

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.

Generates GitHub pull request title and body following Adobe Labs website conventions.

Scaffold and implement a new EDS block for the Adobe Labs website. Use when adding a new block — covers file structure, the decorate(block) function contract, autoblocking, CSS conventions, and when to use per-page authoring vs fragments vs an autoblock.

Review a diff for performance cost and lifecycle fragility — before opening a PR, when a change touches scripts.js, aem.js, head.html, images, fonts or dependencies, or when a block wants to hook into core page load for "speed". Analyses the change against…

Follow Adobe content writing standards when writing documentation for the Adobe Labs website.

Guidelines for drafting and formatting Jira tickets and GitHub issues

Write Jest unit tests for Edge Delivery Services (EDS) blocks using jsdom HTML fixtures and decorate assertions. Use when adding or updating block tests, co-locating *.test.js files, mocking /scripts/ imports, or documenting the project's block testing…

Generate and update S3Mock project documentation. Use when asked to document code, update CHANGELOG.md, update README.md, update AGENTS.md files, or fix formatting, wording, or style in any existing documentation file. Also invoked at the end of the implement…

Implement features, fix bugs, and modify production source code in S3Mock. Use when asked to add functionality, change behavior, or modify source files in server/, integration-tests/, or testsupport/. Not for documentation-only or test-only changes.…

Fix code style issues and ensure linting CI gates pass in S3Mock. Use when ktlint or Checkstyle violations are reported, when asked to fix formatting, or as a required final step after any code change. Runs ktlint for Kotlin source files and Checkstyle for…

Improve code readability, enforce idiomatic Kotlin conventions, and enhance documentation quality in S3Mock without changing behavior. Use when asked to clean up code, improve naming, add KDoc, or align with Kotlin/project idioms. Also invoked by the…

Review code changes in pull requests or local diffs for S3Mock. Use when asked to review a PR, inspect changes, or provide structured feedback on correctness, conventions, test quality, and documentation. Outputs findings structured as Must fix / Should fix /…

Write, update, and fix tests in S3Mock. Use when asked to add test coverage, create test cases, fix failing tests, or verify test correctness. Covers unit tests (*Test.kt in server/), controller slice tests (@WebMvcTest), and integration tests (*IT.kt in…

Add or modify Commerce and external event subscriptions, configure event field extraction and filter rules in an Adobe Commerce app. Use when the user wants to set up event-driven workflows triggered by Commerce operations (such as order placement or catalog…

Integrate App Builder Database Storage (@adobe/aio-lib-db) into an Adobe Commerce app and scaffold a runtime action that reads and writes documents. Use when the user wants persistent, queryable storage backing a Commerce app — either from a web action…

Add or modify webhook interceptors in an Adobe Commerce app. Use when the user wants to intercept Commerce operations to validate input, append data, or modify behavior — before or after execution. Requires a base app initialized with commerce-app-init.

Migrate an Adobe Commerce App Builder project from the Integration Starter Kit or Checkout Starter Kit to the new App Management approach. Run from the root of the App Builder project to be migrated. Pass --auto to skip confirmation prompts (suitable for CI…

Scaffold a new Adobe Commerce app using the aio-commerce-sdk. Creates the base project structure and app.commerce.config file with metadata. Use when the user wants to create a new Commerce app from scratch or initialize a bare Commerce app project. After…

Onboard a domain into SpaceCat/ASO via POST /plg/onboard using an admin IMS token, so it can target any IMS org (not just the caller's own tenant). Use when asked to "onboard <domain>" for a customer/org, run PLG onboarding manually, onboard on behalf of an…

Inspect and drive the PLG "SuggestionGrant" token-gated fix system for a site's opportunities (broken-backlinks, alt-text, cwv) — check which suggestions currently hold a grant, revoke stale ones, and trigger a regrant of the best available suggestion. Use…

Use when writing end-to-end/e2e tests for a new spacecat-api-service endpoint, or extending an existing e2e suite after an endpoint enhancement.

Orchestrates incident response when the spacecat-api-service Lambda is failing broadly after a deploy. Drives a diagnose-first workflow — confirm the outage, correlate it with the most recent release, and verify the suspect build locally — then gates a…

Diagnose why CWV code patches are not being generated for a site, site ID, or opportunity.

Scaffold and implement a new EDS block for Spectrum Hub. Use when adding a new block — covers file structure, the init(el) function contract, template injection, CSS conventions, and when to use templates vs per-page authoring vs fragments.

Review a diff against the core page lifecycle (scripts.js, ak.js, lazy.js, postlcp.js) for fragility, duplication, and unearned performance cost. Use before opening a PR that touches scripts.js or ak.js, when a block wants to hook into core page load for…

Stylesheet organization, design token usage, light/dark mode, and CSS conventions for Spectrum Hub. Use when adding global styles, creating block CSS, or structuring new stylesheet files.

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.

Create conventional commit messages following best conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits specification.