skills/aem/project-management/skills/auth/SKILL.md
Authenticate with AEM Edge Delivery Services Config Service API. Opens a browser window for Adobe ID login and captures the auth token when browser is closed. Use when generating guides/documentation that require API access.
npx skillsauth add adobe/skills authInstall 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.
This skill handles browser-based authentication for AEM Edge Delivery Services Config Service API using Playwright CLI. It opens a browser window for Adobe ID login and captures the auth token when the browser is closed.
.claude-plugin/project-config.json or user input)# Read saved org name
ORG=$(cat .claude-plugin/project-config.json 2>/dev/null | grep -o '"org"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"org"[[:space:]]*:[[:space:]]*"//' | sed 's/"$//')
If org is not saved, prompt user:
"What is your Config Service organization name? (the
{org}inhttps://main--site--{org}.aem.page)"
Save the org name:
mkdir -p .claude-plugin
# Ensure .claude-plugin is in .gitignore (contains auth tokens)
grep -qxF '.claude-plugin/' .gitignore 2>/dev/null || echo '.claude-plugin/' >> .gitignore
echo "{\"org\": \"${ORG}\"}" > .claude-plugin/project-config.json
Then fetch the first site name from Config Service (unauthenticated endpoint):
SITE=$(curl -s "https://admin.hlx.page/config/${ORG}/sites.json" | grep -o '"name"[[:space:]]*:[[:space:]]*"[^"]*"' | head -1 | sed 's/"name"[[:space:]]*:[[:space:]]*"//' | sed 's/"$//')
npx playwright --version 2>/dev/null || npm install -g playwright
npx playwright install chromium 2>/dev/null || true
IMPORTANT: Print highly visible instructions BEFORE opening the browser:
echo ""
echo "╔════════════════════════════════════════════════════════════════╗"
echo "║ ║"
echo "║ BROWSER WINDOW OPENING FOR ADOBE ID LOGIN ║"
echo "║ ║"
echo "║ 1. Sign in with your Adobe ID credentials ║"
echo "║ 2. After successful login, CLOSE THE BROWSER WINDOW ║"
echo "║ ║"
echo "║ >>> CLOSE THE BROWSER TO CONTINUE <<< ║"
echo "║ ║"
echo "╚════════════════════════════════════════════════════════════════╝"
echo ""
Then open the browser with storage save:
mkdir -p .claude-plugin
npx playwright open --save-storage=.claude-plugin/auth-storage.json "https://admin.hlx.page/login/${ORG}/${SITE}/main"
Note: This command blocks until the browser is closed. The auth token is saved to auth-storage.json when the browser closes.
After browser is closed, extract the token:
echo ""
echo "Browser closed. Extracting auth token..."
AUTH_TOKEN=$(node -e "
const fs = require('fs');
try {
const data = JSON.parse(fs.readFileSync('.claude-plugin/auth-storage.json', 'utf8'));
const cookie = data.cookies.find(c => c.name === 'auth_token');
if (cookie) {
console.log(cookie.value);
} else {
console.error('ERROR: auth_token cookie not found. Login may have failed.');
process.exit(1);
}
} catch (e) {
console.error('ERROR: Could not read auth storage file.');
process.exit(1);
}
")
ORG=$(cat .claude-plugin/project-config.json | grep -o '"org"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"org"[[:space:]]*:[[:space:]]*"//' | sed 's/"$//')
echo "{\"org\": \"${ORG}\", \"authToken\": \"${AUTH_TOKEN}\"}" > .claude-plugin/project-config.json
# Clean up storage file (contains sensitive session data)
rm -f .claude-plugin/auth-storage.json
echo "Auth token saved successfully."
AUTH_TOKEN=$(cat .claude-plugin/project-config.json | grep -o '"authToken"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"authToken"[[:space:]]*:[[:space:]]*"//' | sed 's/"$//')
ORG=$(cat .claude-plugin/project-config.json | grep -o '"org"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"org"[[:space:]]*:[[:space:]]*"//' | sed 's/"$//')
HTTP_CODE=$(curl -s -w "%{http_code}" -o /dev/null -H "x-auth-token: ${AUTH_TOKEN}" \
"https://admin.hlx.page/config/${ORG}/sites.json")
if [ "$HTTP_CODE" = "200" ]; then
echo ""
echo "╔════════════════════════════════════════════════════════════════╗"
echo "║ ✓ AUTHENTICATION SUCCESSFUL ║"
echo "╚════════════════════════════════════════════════════════════════╝"
echo ""
else
echo ""
echo "╔════════════════════════════════════════════════════════════════╗"
echo "║ ✗ AUTHENTICATION FAILED (HTTP $HTTP_CODE) ║"
echo "║ Please try again ║"
echo "╚════════════════════════════════════════════════════════════════╝"
echo ""
fi
Auth tokens are stored in .claude-plugin/project-config.json:
{
"org": "myorg",
"authToken": "eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9..."
}
Security Note: Add .claude-plugin/ to .gitignore.
AUTH_TOKEN=$(cat .claude-plugin/project-config.json 2>/dev/null | grep -o '"authToken"[[:space:]]*:[[:space:]]*"[^"]*"' | sed 's/"authToken"[[:space:]]*:[[:space:]]*"//' | sed 's/"$//')
curl -H "x-auth-token: ${AUTH_TOKEN}" \
"https://admin.hlx.page/config/${ORG}/sites/{site}/access.json"
| Issue | Solution |
|-------|----------|
| npx playwright not found | Run npm install -g playwright |
| Browser doesn't open | Run npx playwright install chromium |
| Token not found after login | Ensure login completed before closing browser |
| Login page not loading | Verify org/site names are correct |
| API returns 401 | Token expired, re-authenticate |
Called by: admin, authoring, development, handover
Invocation:
Skill({ skill: "project-management:auth" })
tools
Use the run-workflow MCP to discover, compose, execute, publish, and save Adobe Firefly workflows. TRIGGER when: user asks what actions are available, what the MCP can do, how to process images/video/3D via workflow, wants to build/run/save/publish a workflow, OR pastes any workflow/batch/execution ID. BARE ID (UUID/workflowId/batchId) = INSPECT ONLY — call inspect_run, NEVER run_workflow_submit. ALWAYS call list_actions first for capability/discovery questions. DO NOT TRIGGER for direct Firefly API calls without MCP (use firefly-api-specs).
tools
Run predefined featured workflows via run-workflow MCP. TRIGGER when user names a featured workflow (retargeting, banners at scale, localization, packaging, banner advertising, etc.) or asks to run a known marketing/production workflow. Requires run-workflow MCP. ALWAYS call get_featured_workflow before compose_workflow. DO NOT TRIGGER for custom one-off workflows with no named template — use run-workflow skill.
tools
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 or batch use) — auto mode prints a summary of all Q&A questions answered with their defaults. Pass --doc-scan-only to scan README.md and env.dist for outdated content without modifying any files. Use when the user wants to migrate an App Builder project from the Integration Starter Kit or Checkout Starter Kit to the App Management approach, or mentions upgrading their Adobe Commerce extension architecture.
development
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.