plugins/app-builder/skills/appbuilder-project-init/SKILL.md
Initialize an Adobe App Builder project end-to-end without Developer Console UI clicks. Creates the Console project and workspace, subscribes APIs (including those needing a product profile), maps user intent to the right template, runs non-interactive `aio app init`, and guides post-init customization. Use whenever the user mentions creating an App Builder app, scaffolding a project, `aio app init`, setting up an Experience Cloud extension, adding actions or web assets, creating a Console project or workspace, adding APIs, or bootstrapping App Builder — even if they don't say "App Builder". Also for SPA templates, AEM extensions, API Mesh, Asset Compute workers, and MCP server projects. Also handles debugging init failures — template not found, `aio app init` hangs or times out, Node version mismatches, npm install failures, post-init build errors, `aio login` issues, `aio app run` showing nothing, or `aio console project create` / `workspace create` / `workspace api add` errors.
npx skillsauth add adobe/skills appbuilder-project-initInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Maps user intent to the right Adobe App Builder template and runs non-interactive aio app init. Default: @adobe/generator-app-excshell (SPA + actions). For headless/bare projects, use init-bare.
When a Developer Console project / workspace / API subscription does not yet exist, this skill walks the agent through creating them non-interactively by calling aio console … directly — see the Bootstrap section and references/bootstrap.md. The latest @adobe/aio-cli bundle exposes non-interactive aio console project create / workspace create / api list / workspace api add (with --license-config for services that require a product profile), and non-interactive aio app init --org/--project/--template-options. Together they remove every blocking "open the Developer Console UI and click" step from the agentic setup path. Just install the latest CLI (npm install -g @adobe/aio-cli) and use them.
If the user is starting from zero — no Developer Console project yet, or an existing project that is missing a workspace or API subscription — bootstrap that state before aio app init. Otherwise aio app init / aio app use / aio app deploy have nothing to wire the local app to.
The full bootstrap is just aio commands; call them directly, not through a wrapper script. They are already non-interactive in the recent plugin releases, and per-step calls let you react to "already exists" or "needs a product profile" responses without baking those decisions into bash.
Make sure the CLI is current — that's what brings in the non-interactive Console + app init commands:
npm install -g @adobe/aio-cli
aio --version
Don't try to assert specific plugin versions; just take the latest. If a console or app subcommand below is rejected as "command not found" or "unknown flag" after this, the CLI install genuinely failed (PATH issue, permissions, registry mirror) — fix the install rather than working around it.
Confirm an org is selected (or pass --orgId on every command below):
aio console org list --json # if needed, then:
aio console org select <orgId>
| User state | Next action |
| --- | --- |
| "Create a project + workspace + add APIs from scratch" | Run the bootstrap chain (project → workspace → APIs), then aio app init. |
| Project exists, workspace missing | Skip project-create. Run aio console workspace create, then optionally aio console workspace api add. |
| Project + workspace exist, only need to add an API | Run aio console api list to discover service codes, then aio console workspace api add. |
| Everything already wired | Skip bootstrap. Go straight to Initialize via Script. |
Always check what already exists with aio console project list --json and aio console workspace api list --projectName <p> --workspaceName <w> --json before creating — these commands fail loudly on "already exists" and there is no built-in idempotency.
Step 1 — create the Console project:
aio console project create -n my-project --json
# optional: -t "Title" -d "Description" -o <orgId>
Step 2 — create a workspace inside it (Stage is the conventional first non-Production workspace; pick a more descriptive name in long-lived shared projects):
aio console workspace create \
--projectName my-project \
--name Stage \
--json
# optional: --orgId <orgId> --title "Stage workspace"
Step 3 — discover and subscribe the APIs the app needs:
aio console api list --json # see all service codes available to the org
# entries flagged for whether they need a product profile
# Free-tier service:
aio console workspace api add \
--projectName my-project \
--workspaceName Stage \
--service-code AdobeIOManagementAPISDK \
--json
# Service that requires a product profile:
aio console workspace api add \
--projectName my-project \
--workspaceName Stage \
--service-code AdobeAnalyticsSDK \
--license-config AdobeAnalyticsSDK=AnalyticsProductionProfile \
--json
--service-code accepts a comma-separated list to subscribe several free-tier services in one call. --license-config is repeatable when several profile-bound services are added together.
| Failure | What to do |
| --- | --- |
| project create fails with "already exists" | Read aio console project list --json, reuse the existing project's name, and continue at step 2. |
| workspace create fails with "already exists" | List workspaces with aio console workspace list --projectName <p> --json and continue at step 3. |
| workspace api add returns "product profile required" | The service code requires --license-config. Ask the user (or the org admin) for the profile name and retry with --license-config CODE=PROFILE. |
| Any step returns an org-selection error | Pass --orgId <id> explicitly, or aio console org select <id> once before retrying. |
Two equivalent ways to point a fresh aio app init at the project/workspace you just created:
Pass them as flags to init itself (cleanest):
skills/appbuilder-project-init/scripts/init.sh init \
"@adobe/generator-app-excshell" ./my-project \
--org <orgId> --project my-project
The wrapper passes --org / --project / --template-options straight through to aio app init, on top of the existing -y --no-login --no-install flags.
Run aio app use after init (works on any plugin version):
cd ./my-project
aio app use --no-input # adopts the currently selected project/workspace, no prompts
Either route ends with the local .aio and .env pointing at the workspace you just bootstrapped, so aio app deploy publishes to the right namespace.
When the user's intent maps unambiguously to a single template — for example, they name a template directly or describe an app that clearly matches exactly one entry below — skip straight to Initialize via Script below. Use the matched template and any project name the user provided (or a sensible default).
Examples of fast-path triggers:
@adobe/generator-app-excshell" → use that template, run init@adobe/generator-app-asset-compute, run init@adobe/generator-app-excshell, run initinit-bare, run initIf there is any ambiguity — multiple templates could fit, or the user's constraints are unclear — use the full template decision table and workflow below.
Pick the template that matches the user's intent. When unclear, default to @adobe/generator-app-excshell.
| User wants | Template | | --- | --- | | SPA with actions + React UI | @adobe/generator-app-excshell | | AEM Content Fragment Console extension | @adobe/aem-cf-admin-ui-ext-tpl | | AEM React SPA (WKND-based) | @adobe/generator-app-aem-react | | Adobe API Mesh (GraphQL) | @adobe/generator-app-api-mesh | | Asset Compute custom worker | @adobe/generator-app-asset-compute | | Remote server on App Builder | @adobe/generator-app-remote-mcp-server-generic | | Bare / from-scratch project (no pre-scaffolded actions or UI) | init.sh init-bare |
For a headless/backend-only request, prefer init-bare when possible. If the user still needs a template that generates UI files, plan a post-init cleanup so the final project has no web-src frontend directory or web manifest wiring.
The aio app * wrappers go through a single script: scripts/init.sh. (Console bootstrap commands are called directly — see the Bootstrap section above for the rationale.)
Note: The path to this skill's scripts may be
skills/,.augment/skills/, or.github/skills/depending on your platform and repository layout. Adjust the prefix in the commands below accordingly.
With a template:
skills/appbuilder-project-init/scripts/init.sh init "@adobe/generator-app-excshell" ./my-project
With a template, fully wired to a specific Console org/project (no post-init aio app use needed):
skills/appbuilder-project-init/scripts/init.sh init \
"@adobe/generator-app-excshell" ./my-project \
--org <orgId> --project my-project
--org, --project, --template-options (base64-encoded JSON), and --no-config-validation are passed straight through to aio app init. Use the latest @adobe/aio-cli so they're all recognised; --no-config-validation is the escape hatch for the rare case where a partial scaffold shouldn't yet have to pass schema validation.
Bare project (no template):
skills/appbuilder-project-init/scripts/init.sh init-bare ./my-project
Use init-bare only when the user explicitly wants to configure everything from scratch. In that case, "bare" means the generated project should stay minimal:
app.config.yaml exists with an empty or minimal application.runtimeManifestpackage.json exists with only the basic project dependenciessrc/, web-src/, or actions/ directoriesWhy this matters: if the user asked for a bare project, pre-generated actions or web assets contradict that intent and remove the clean starting point they requested.
The script outputs JSON with success, path, and output fields. Check success before proceeding.
Ask the user (or infer from conversation context):
| Question | Examples | | --- | --- | | What type of app? | SPA shell, headless API, AEM extension, Asset Compute worker, API Mesh, remote server | | Needs a UI? | Yes (React Spectrum in ExC Shell), No (actions only) | | Extension point? | dx/excshell/1, aem/cf-console-admin/1, dx/asset-compute/worker/1, or N/A | | Additional actions? | Names and purposes of custom actions beyond the default | | Console state? | Existing project + workspace? Or do we need to create them and subscribe APIs first? | | APIs needed? | e.g. Adobe I/O Management, Analytics, Target — including any that require a product profile |
If the user simply says "create an App Builder app" with no specifics, default to @adobe/generator-app-excshell.
If the Console state is "from scratch" or unknown, run the Bootstrap the Developer Console flow before continuing to template selection. See references/bootstrap.md for the full agentic bootstrap playbook.
Consult the Template Decision Table above and references/templates.md to map the user's intent to a template.
Follow the Initialize via Script, Post-init customization, and Validate sections below.
Consult references/templates.md for template-specific post-init guidance. Common tasks:
npm install in the project directory. The init script uses --no-install to keep initialization fast, but dependencies are required before building or testing.mesh.json is at the project root — After aio app init with @adobe/generator-app-api-mesh, confirm ./mesh.json exists before treating the scaffold as ready. If the file only exists at node_modules/@adobe/generator-app-api-mesh/templates/mesh.json, copy it into place with cp node_modules/@adobe/generator-app-api-mesh/templates/mesh.json ./mesh.json. The file under node_modules/ is the generator's template source, not the project's active API Mesh configuration. Then customize the root mesh.json with the user's real source handlers; for multi-backend scenarios, configure at least two handlers.init-bare, inspect the generated project. If the initializer created actions/, src/, or web-src/, remove those directories before continuing. A bare project should not keep auto-generated action code or web assets.aio app init: rm -rf web-src/ or the template-specific path such as rm -rf src/<extension>/web-src/. Then remove matching web-src config from app.config.yaml or ext.config.yaml if present, especially web: web-src and operations.view / impl: index.html entries. This avoids unnecessary frontend build artifacts and stale manifest wiring in a backend-only project.cd ./my-project && skills/appbuilder-project-init/scripts/init.sh add-action "my-action".skills/appbuilder-project-init/scripts/init.sh add-web-assets.runtime: nodejs:22 for production. Stage workspaces also accept runtime: nodejs:24.inputs: for environment variables the action needsannotations.require-adobe-auth: true if the action needs IMS tokensweb: 'yes' or web: 'raw' depending on HTTP access needs$include entries.appbuilder-action-scaffolder skill's boilerplate pattern for production-ready action code with logging, input validation, and error handling.Verify the project structure by checking these items directly:
app.config.yaml** exists** and contains valid YAML$include paths resolve to real filesext.config.yaml (if present) has runtimeManifest.packages with at least one actionfunction: pathspackage.json** exists** with name, version, and an Adobe SDK dependency (@adobe/aio-sdk or @adobe/aio-lib-core-logging)runtimeManifest in app.config.yaml (see Manifest guardrail below)Read the relevant files and verify each check. Fix any issues before proceeding.
If the user wants to go beyond scaffolding:
aio app build # Build
aio app test # Run tests
aio app deploy # Deploy to Adobe I/O Runtime
aio app dev # Run locally for development (use `aio app run` instead if actions use State SDK, Files SDK, or sequences)
Extension projects: Actions are defined under runtimeManifest in ext.config.yaml, referenced via $include from app.config.yaml.
Standalone apps: Actions go under application.runtimeManifest in app.config.yaml.
Do not place a root-level runtimeManifest directly in app.config.yaml: the CLI ignores those actions, so they will not deploy. If you see this shape, move it under application.runtimeManifest or into ext.config.yaml.
aio** CLI not installed:** If aio --version returns command not found or fails, stop before initialization. Ask the user to install Adobe I/O CLI, complete aio auth login, and retry only after the CLI is available.npm install** fails after init:** The scaffold can still be created because init runs with --no-install, but builds/tests will fail until dependencies install cleanly. Capture the first package error, confirm the Node/npm version is compatible, rerun npm install from the project root, and only continue once it succeeds.@adobe/generator-app-excshell and state that assumption explicitly.aio console …** subcommand or flag not recognised:** Almost always means the CLI bundle is stale. Run npm install -g @adobe/aio-cli and retry — that's the supported way to refresh every plugin (console, app, runtime, ims-oauth, telemetry). Only dig deeper if the same command still fails after a clean reinstall.aio console api list --json to confirm, ask the user (or org admin) for the profile name, and retry with --license-config CODE=PROFILE.aio console org list then aio console org select <orgId> (or pass --orgId to every command) before retrying.aio app * versions validate app.config.yaml by default against an OpenWhisk-aligned schema. The validation runs on every aio app * command that reads or writes the manifest — concretely: aio app init, aio app add (action|web-assets|extension|event|service), aio app delete (action|web-assets|extension|event|service), aio app build, aio app deploy, aio app undeploy, aio app run, aio app dev, aio app use, and aio app info. The escape hatch flag is the same on all of them: --no-config-validation. Use it on the single command you need to unblock (e.g. aio app build --no-config-validation while you're still mid-refactor), then drop it as soon as the manifest is whole. Don't bake it into scripts — silent drift between local config and the deployed shape is exactly what the validator was added to catch.HTTP_PROXY / HTTPS_PROXY during the template registry SSL handshake. Run npm install -g @adobe/aio-cli to pick up the proxy fix, confirm HTTPS_PROXY is exported in the same shell, and retry.After initialization, hand off to:
appbuilder-action-scaffolder — For scaffolding actions with playbook, checklist, boilerplate templates, and manifest validationappbuilder-ui-scaffolder — Build React Spectrum UI for ExC Shell SPAs and AEM extensions| Task | Reference | Command |
| --- | --- | --- |
| Bootstrap Console project + workspace + APIs | references/bootstrap.md | aio console project create → aio console workspace create → aio console workspace api add |
| Discover org's available APIs | references/bootstrap.md | aio console api list --json |
| Subscribe an existing workspace to an API | references/bootstrap.md | aio console workspace api add --service-code … [--license-config …] |
| Initialize an App Builder project from a template | references/templates.md | scripts/init.sh init |
| Wire local app to a Console workspace post-init | references/bootstrap.md | scripts/init.sh init … --org … --project … or aio app use --no-input |
| Debug project init issues | references/debugging.md | — |
aio console … commands from the latest @adobe/aio-clidevelopment
Start AEM Workflows on AEM as a Cloud Service using all available triggering mechanisms. Use when starting workflows manually via the Timeline UI, programmatically via WorkflowSession.startWorkflow(), via the HTTP Workflow API, through Manage Publication, or passing initial metadata and payload to a workflow instance.
development
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 workflows, triaging incidents with Cloud Manager logs, thread pool analysis, and Sling Job diagnostics for the Granite Workflow Engine.
development
[BETA] Implement custom AEM Workflow Java components on AEM as a Cloud Service. This skill is in beta. Verify all outputs before applying them to production projects. Use when writing WorkflowProcess steps, ParticipantStepChooser implementations, registering services via OSGi DS R6 annotations, reading step arguments from MetaDataMap, accessing JCR payload via WorkflowSession adapter, reading and writing workflow metadata and variables, and handling errors with WorkflowException for retry behavior.
development
Start AEM Workflows on AEM 6.5 LTS using all available triggering mechanisms. Use when starting workflows manually via the Timeline UI, programmatically via WorkflowSession.startWorkflow(), via the HTTP Workflow API, through Manage Publication, through replication triggers, or passing initial metadata and payload to a workflow instance.