Agent skill · writing content · membranedev

unstructured

Unstructured integration. Manage data, records, and automate workflows. Use when the user wants to interact with Unstructured data.

Why this skill is useful

Provides specific commands and workflows for integrating with Unstructured data that the AI wouldn't reliably generate on its own.

What it needs

Requires @membranehq/cli installed locally. Requires membrane account access. About 4k tokens when loaded. Last updated 2026-04-28. 253 stars on the source repository.

What this skill does

Unstructured Unstructured is a document processing platform that helps developers extract data from unstructured file types like PDFs and Word documents. It's used by data scientists and engineers to clean and prepare data for machine learning models and other analytical applications. Official docs: https://unstructured-io.github.io/unstructured/ Unstructured Overview Partition Elements Layout Download Working with Unstructured This skill uses the Membrane CLI to interact with Unstructured. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing. Install the CLI Install the Membrane CLI so you can run membrane from the terminal: Authentication This will either open a browser for authentication or print an authorization URL to the console, depending on whether interactive mode is available. Headless environments: The command will print an authorization URL. Ask the user to open it in a browser. When they see a code after completing login, finish with: Add --json to any command for machine-readable JSON output. Agent Types : claude, openclaw, codex, warp, windsurf, etc. Those will be used to adjust tooling to be used best with your harness Connecting to Unstructured Use membrane connection ensure to find or create a connection by app URL or domain: The user completes authentication in the browser. The output contains the new connection id. This is the fastest way to get a connection. The URL is normalized to a domain and matched against known apps. If no app is found, one is created and a connector is built automatically. If the returned connection has state: "READY", skip to Step 2. 1b. Wait for the connection to be ready If the connection is in BUILDING state, poll until it's ready: The --wait flag long-polls (up to --timeout seconds, default 30) until the state changes. Keep polling until state is no longer BUILDING. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills membranedev/unstructured

View the source on GitHub

Browse the @skills marketplace