adobe/aem-edge-delivery-services
Skills for AEM Edge Delivery Services development, including Content Driven Development workflow, block building, testing, content modeling, code review, and page migration.
Use when a new or changed AEM Edge Delivery Services block needs an entry in the block library that authors use to find and insert it: the Experience Workspace (formerly DA, Document Authoring) library or the Sidekick Library for Word and Google Docs projects. Covers finding the project's library, the block page, variants, the sheet row, library metadata and the steps that happen outside the repo. For tests that run against the library page use testing-blocks.
Use this when running or troubleshooting the local Edge Delivery dev server or the Adobe AEM CLI (@adobe/aem-cli, formerly helix-cli; aem up, aem content, aem import). Covers starting aem up and its port (git worktrees, a port already in use), serving local test pages from ./content/, cloning da.live content locally with aem content clone to preview, inspect or edit it and pushing edits back, aem up failures (cert errors, proxy 404s, local pages not found), .env / AEM_* configuration, HTTPS, installing or upgrading the CLI, and the importer server. For da.live content-format rules or the DA Source API use da-content; for writing EDS block code use content-driven-development.
Use when block or site code of an AEM Edge Delivery Services project authored in Experience Workspace (EW, formerly DA, Document Authoring) must stay editable in layout view, the WYSIWYG page editor that renders the page with the site's own code: authors can't edit a block's text or images, blocks duplicate or misbehave after edits, a request fails only in layout view, or a branch needs testing there. Not for the Universal Editor (ue-component-model) or projects authored in Word or Google Docs.
Use this when the page-import pipeline needs to determine the authoring approach (default content vs blocks) for scraped content before generating import HTML for AEM Edge Delivery Services. Covers validating block selection and section styling for import/migration. Do not invoke directly — called by page-import as a pipeline step.
Use this when you are starting AEM Edge Delivery Services (EDS, Franklin, Helix) development and want an existing reference to build from, such as a block, build tool, code snippet, integration pattern, or plugin. Searches the Block Collection and Block Party repositories, matches candidates against the need, and returns a suitable starting point to clone or adapt.
Use when a fresh AEM Edge Delivery Services boilerplate project should take on the brand basics of an existing website being migrated to EDS — colors, body and heading fonts, font sizes, header height, favicon and logo. Triggers include "set up the brand from <site>", "match the source site's look", "apply the client's fonts and colors", "use their favicon and logo". Not for projects whose styles were already customized, and not for full design-system extraction (spacing scales, components, motifs).
Use this before writing or changing AEM Edge Delivery Services (EDS, Franklin, Helix) block or site code: a block's decorate(block), block CSS and variants, scripts.js loading phases (eager, lazy, delayed), images, fragments, and LCP or performance fixes. EDS conventions don't always match standard front-end practice because of its architecture and page-loading model, and the boilerplate keeps evolving past model training cutoffs, so check here rather than relying on memory. For new blocks or changes to the authored structure, start with content-driven-development.
Use when asked to review AEM Edge Delivery Services (EDS, Franklin, Helix) code: a pull request, branch, diff, or your own changes before opening a PR. Lists the EDS-specific checks to apply on top of normal code review.
Use this when building a new AEM Edge Delivery Services (EDS, Franklin, Helix) block, or when changing what authors put into an existing block (new rows or cells, author-selectable variants, a different table structure). Runs the content-first workflow: find or create test content before code, design an author-friendly content model, and validate against that content. For code-only changes that keep the authored structure (CSS fixes, JavaScript bugs, scripts.js, performance, lint) use building-blocks directly.
Use this to decide what authors type for an AEM Edge Delivery Services (EDS) block, in any editor (Word, Google Docs, Experience Workspace, Universal Editor): the table layout (rows, cells, columns), variants, per-item options such as featured, lists, tabular data, forms, and whether something should be a block at all. Also use it to review or simplify a block's author-facing structure, before writing block code for a new block or a changed structure. Not for decorate JS or CSS once the model is set.
Use this when a user wants to create a brand-new AEM Edge Delivery site from scratch: no GitHub repository or content exists yet, or a repo made from the boilerplate template is not connected to content yet. Triggers include 'set up a new site', 'create a new EDS project', 'onboard a new site'. Covers creating the repo from the boilerplate, installing aem-code-sync, choosing the content store (DA at admin.da.live or Source Bus at api.aem.live), seeding nav, footer and homepage, and returning a live preview URL. For importing existing pages use page-import; for blocks on an existing site use content-driven-development.
Use this to obtain, reuse, refresh or troubleshoot Adobe IMS authentication for Experience Workspace (formerly DA) content APIs: admin.da.live (DA) or api.aem.live (Source Bus). Use before pushing HTML content, listing documents or triggering a preview when no credential is known to work for that API, or for 401/403 (Unauthorized/Forbidden) and authentication checks where status 200 is insufficient. Not for choosing a content store or planning content changes when authentication already works.
Use before writing, fixing or answering questions about the HTML of pages that authors edit in Experience Workspace / DA (da.live), including hand-written sample pages for local testing. The pipeline silently drops or rewrites markup in ways that are not guessable, so check here first when a generated page previews empty, loses its metadata, icons, Section Metadata style or block, shows about:error images, turns a table into a block, loses span classes or bold in block cells, or has its links rewritten; when uploading pages or media to the DA source API or the Source Bus API at api.aem.live (200 but nothing written, SVG over 40 KB returns 409); or when you need to see how the pipeline read a page. Not for block JS/CSS (building-blocks), tokens (da-auth) or the aem CLI (aem-cli).
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 da.live", or providing a figma.com URL for a page. Reads the frame (and any annotations) via a Figma MCP, resolves each section to an existing block, a new isolated block, or default content (inferred against the project's existing blocks and confirmed with you, or read from annotations when the frame happens to have them), generates DA-compliant body-fragment HTML, and deploys via the DA Source API + preview.
Use this when you need real pages that already use a specific block or block variant on an AEM Edge Delivery Services site (local dev, .aem.page or .aem.live): to audit usage before removing, renaming or restyling a block, or to find real pages to regression-test a change when the block has no library test page. For creating or cloning local test pages use aem-cli; for importing an external URL use page-import; for searching Adobe's Block Collection or Block Party use block-collection-and-party.
Use this when the page-import pipeline needs to produce structured HTML from authoring analysis for AEM Edge Delivery Services. Covers building section structure, applying block tables, handling metadata, and managing the images folder. Do not invoke directly — called by page-import as a pipeline step.
Use this when the page-import pipeline needs to identify section boundaries and content sequences within a scraped webpage for AEM Edge Delivery Services import. Outputs an ordered list of sections, the content sequence within each section, and candidate block-type annotations via two-level analysis (sections, then sequences per section). Do not invoke directly — called by page-import as a pipeline step.
Use this when rebuilding an existing website's header as the header block of an AEM Edge Delivery Services project so that it matches the source 1:1 — closed at every width, with every menu open, with the mobile menu open, and while scrolling. Captures the source header with the web CLI (web header capture), installs a configurable header block and its nav document, then runs a ladder of web header check commands against the live source until nothing differs. Triggers include "migrate the header of <site>", "rebuild this header in EDS", "header 1:1 with the source". For whole pages use page-import; to keep the source DOM as it is use snowflake; for other blocks use content-driven-development.
Use this when the page-import pipeline needs to analyze the content sequences within a single section and describe them neutrally for AEM Edge Delivery Services. Covers identifying breaking points between default content and blocks, one section at a time. Do not invoke directly — called by page-import per section.
Use this when importing or migrating a single webpage from any URL into canonical EDS block format — structured HTML that authors edit in DA — including when the request uses terms like migrate, migration, or migrating. Covers scraping the page, analyzing structure, mapping to existing blocks, and generating HTML for immediate local preview. Use the snowflake skill instead when the user wants to preserve the original DOM byte-for-byte (static-to-EDS overlay); for building new blocks from scratch use content-driven-development.
Use this when you need to preview and verify content you imported into a local AEM Edge Delivery Services (EDS, Franklin, Helix) dev server on localhost. Starts the dev server against the imported HTML, checks block rendering, inspects DOM structure, compares against the original page, and troubleshoots broken references and 404s.
Use this when the page-import pipeline needs to fetch a source webpage and prepare it for import/migration to AEM Edge Delivery Services. Covers scraping content, extracting metadata, downloading images, and returning analysis JSON with paths, metadata, cleaned HTML, and local images. Do not invoke directly — called by page-import as a pipeline step.
Use this when the user asks to continue work in the SLICC browser agent or to install a skill into SLICC, for example "handoff to slicc", "move to the browser", "test in the browser", "install this skill in slicc", or "upskill slicc with this repo". Covers handing off the current task to the SLICC browser agent and installing a new skill into SLICC from a GitHub repo.
Use this when converting an AI-generated static HTML page (Stardust, Mobirise, Relume, Lovable, v0, Figma-derived, etc.) into an Edge Delivery Services page while preserving the original design and making content authorable in Document Authoring — triggers include "convert this page to EDS", "static-to-EDS overlay", "convert to EDS blocks", "next experimentation", "next run", "start run", or providing a source URL to make editable in DA. Covers two modes — page-level (overlay template with slot markers) and block-level (each section becomes an independent EDS block). For canonical EDS block-rewrite migrations use page-import instead.
Use before writing unit or Playwright E2E tests for an AEM Edge Delivery Services block or script, when deciding what tests a block change needs, or when validating block, script or style changes in a browser before a pull request. EDS block testing has non-obvious conventions (how to locate elements without breaking on author edits, library page vs drafts, analytics assertions, no-framework-addition rule, and waiting on decoration), so check here first. Not for implementing block code (building-blocks) or PR review comments (code-review).
Use this to set up an AEM Edge Delivery Services block for the Universal Editor in an AEM-authoring (xwalk) project: the block's component definition, model (properties-panel fields) and filters in blocks/<name>/_<name>.json, adding it to the editor's add menu, option fields, multi-value fields, and tabs or containers. Also use it to fix a block missing from the add menu, or edits to component-definition.json, component-models.json or component-filters.json that disappear (those files are generated by build:json). Use content-modeling first to decide the block's structure; this skill only maps that structure to Universal Editor fields. Not for document-based authoring (Word, Google Docs, DA) or for decorate JS and CSS.