Da Auth logo

Da Auth

Organization
adobe
da-auth

Use this when another step needs to call the admin.da.live API, for example before pushing HTML content, listing documents, or triggering a DA preview, and you do not already have a valid DA_TOKEN in scope from an earlier step in the same session. Covers obtaining a valid Adobe IMS access token for the DA (Document Authoring) API.

Overview

Publisheradobe
Repositoryskills
Skill nameda-auth
Stars
298
Forks
92
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by adobe on GitHub. Read the source before you install it.

Installation

Install the Da Auth AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/adobe/skills/tree/main/plugins/aem/edge-delivery-services/skills/da-auth
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/adobe/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/aem/edge-delivery-services/skills/da-auth .claude/skills/da-auth
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Da Auth in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Da Auth on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Da Auth is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

DA Authentication

Gets a valid Adobe IMS access token and stores it in DA_TOKEN for use in subsequent admin.da.live API calls.

When to Use This Skill

Use this skill whenever you need to call the DA Admin API (admin.da.live) and do not already have a valid token in scope. Common cases:

  • Pushing or updating page content in DA
  • Listing documents in a DA repository
  • Triggering a DA content preview

Do NOT use this skill when:

  • You already obtained a DA_TOKEN earlier in the same session and it has not expired (tokens are valid for ~1 hour with a 60-second buffer)
  • The create-site skill is already handling authentication as part of its own flow
  • A DA MCP server is active in the session — use its authentication tool directly instead

Prerequisites

  • Node.js 18+ installed
  • A browser accessible from the machine (for the OAuth flow)
  • Network access to ims-na1.adobelogin.com

Related Skills

  • create-site — includes its own DA auth step for new site onboarding; do not invoke da-auth separately within that flow
  • content-driven-development — use da-auth before pushing authored content to DA
  • building-blocks — use da-auth if test content needs to be pushed to DA for block development
  • snowflake — invoke da-auth before Phase 5 (round-trip) so $DA_TOKEN is set when snowflake PUTs the converted page to DA
  • da-content — the reference for what to do with $DA_TOKEN once you have it (Source API, preview/publish)

Step 1: Check for a Cached Token

Before triggering a browser login, check whether a valid token is already cached.

bash
DA_TOKEN=$(node -e "
  const fs = require('fs');
  const p = process.env.HOME + '/.aem/da-token.json';
  try {
    const t = JSON.parse(fs.readFileSync(p, 'utf8'));
    if (t.expires_at > Date.now() + 60000) process.stdout.write(t.access_token);
  } catch {}
")

If DA_TOKEN is non-empty, skip to Step 3.

Step 2: Obtain a Token (login required)

Choose the option that fits the environment:

Option A (preferred) — da-auth-helper CLI:

The da-auth-helper tool handles the full IMS OAuth 2.0 implicit flow, caches the token at ~/.aem/da-token.json, and prints the token to stdout.

bash
# Run directly without a global install
DA_TOKEN=$(npx github:adobe-rnd/da-auth-helper token)

If npx is unavailable or slow, install globally first:

bash
npm install -g github:adobe-rnd/da-auth-helper
DA_TOKEN=$(da-auth-helper token)

This opens a browser window. Instruct the user:

Please complete the Adobe IMS login in the browser window that just opened. The token will be captured automatically once you log in.

Success: DA_TOKEN is a non-empty JWT string starting with eyJ.

Option B — DA MCP server:

If a DA MCP server is configured in the session, use its authentication tool to start the OAuth flow and retrieve the token from the response.

Option C — Manual paste (last resort):

I need an Adobe IMS access token to push content to DA. You can copy one from your browser:

  1. Open da.live and log in
  2. Open DevTools → Network tab → find any request to admin.da.live
  3. Copy the Authorization: Bearer <token> value (without the Bearer prefix)
  4. Paste it here

Step 3: Verify the Token Works

Confirm the token is accepted by the DA API before proceeding:

bash
curl -s -o /dev/null -w "%{http_code}" \
  -H "Authorization: Bearer {{DA_TOKEN}}" \
  "https://admin.da.live/list/{{ORG}}/{{REPO}}"

Success: HTTP 200. The token is valid — DA_TOKEN is ready for use by the calling skill.

Troubleshooting

SymptomLikely causeFix
DA_TOKEN is empty after Step 1No cached token or token expiredProceed to Step 2
Browser window does not opennpx / da-auth-helper blocked or headless environmentUse Option B (MCP) or Option C (manual paste)
npx github:adobe-rnd/da-auth-helper failsNetwork restrictions on GitHub package registryUse Option B (DA MCP server) or Option C (manual token paste)
Step 3 returns 401Token expired between stepsRe-run Step 2 to refresh
Step 3 returns 403Authenticated user lacks access to {{ORG}}/{{REPO}}Ask the user to verify their DA permissions for that org/repo

Reference

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Da Auth AI skill do?

Use this when another step needs to call the admin.da.live API, for example before pushing HTML content, listing documents, or triggering a DA preview, and you do not already have a valid DA_TOKEN in scope from an earlier step in the same session. Covers obtaining a valid Adobe IMS access token for the DA (Document Authoring) API.

Why use Da Auth on TypingMind?

Because you install it once and use it with any model. Da Auth is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Da Auth in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/adobe/skills/tree/main/plugins/aem/edge-delivery-services/skills/da-auth. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Da Auth?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Da Auth?

As many as you like. As long as a model supports skills, you can use Da Auth with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Da Auth AI skill free?

Yes. It is published on GitHub by adobe under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇