Source profileQuality 90/100

vellum-ai/vellum-assistant/skills/chat-complex-documents/SKILL.md

chat-complex-documents

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready text for search, Q&A, and summarization without building a custom parsing pipeline.

Source repository stars: 1,002
Declared platforms: 0
Static risk flags: 1
Last source update: 2026-08-04
Source checked: 2026-08-04

Decision Compatibility Install Workflow Permissions Evidence Source

Decision brief

What it does—and where it fits

You have documents — contracts, reports, slide decks, scanned PDFs, spreadsheets, emails, images — and you want the assistant to reliably get the content out of them and make it usable: searchable, answerable, summarizable, or ready to feed a knowledge base or another tool.

Best for

The user wants to extract or structure content from documents (PDF, Office, images, emails, scanned files).
The user wants documents made searchable or ready for RAG / Q&A / a knowledge base.
The user asks to connect Unstructured or Unstructured Transform.

Not for

Tasks that require unconfirmed production actions or broad system permissions.
Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

Platform	Status	Evidence	What to check
Codex	Not declared	No explicit evidence	Portability before use
Claude Code	Not declared	No explicit evidence	Portability before use
Cursor	Not declared	No explicit evidence	Portability before use
Gemini CLI	Not declared	No explicit evidence	Portability before use

Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource

npx skills add https://github.com/vellum-ai/vellum-assistant --skill "skills/chat-complex-documents"

Safe inspection promptEditorial

Inspect the Agent Skill "chat-complex-documents" from https://github.com/vellum-ai/vellum-assistant/blob/32b93fb5c0f5e77d2a15e2f214d3726208c9d208/skills/chat-complex-documents/SKILL.md at commit 32b93fb5c0f5e77d2a15e2f214d3726208c9d208. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

01
Setup
Determine which command tool to use for every command in this skill:
If hostbash is available → you are on the desktop app. Use hostbash for all commands (the auth step opens your local browser).If it is unavailable → you are on the web app. Use bash for all commands (the platform handles the browser redirect).On desktop → run via hostbash (opens your local browser).
02
Step 1 — Detect your environment
Determine which command tool to use for every command in this skill:
If hostbash is available → you are on the desktop app. Use hostbash for all commands (the auth step opens your local browser).If it is unavailable → you are on the web app. Use bash for all commands (the platform handles the browser redirect).Determine which command tool to use for every command in this skill:
03
Step 2 — Add the server
Add Transform as a remote streamable-http MCP server. Keep the default risk level (high) — Transform ingests file content, so per-call approval is the safe default.
Add Transform as a remote streamable-http MCP server. Keep the default risk level (high) — Transform ingests file content, so per-call approval is the safe default.The server is registered under the id unstructured-transform — that's the name shown by assistant mcp list and used in the commands below, even though this skill is titled "Chat with Complex Documents".
04
Step 3 — Authenticate via OAuth
This opens Unstructured's authorization page. After sign-in, the assistant handles the callback and caches the tokens.
On desktop → run via hostbash (opens your local browser).On web app → run via bash (the platform handles the redirect).This opens Unstructured's authorization page. After sign-in, the assistant handles the callback and caches the tokens.
05
Step 4 — Verify
Confirm unstructured-transform shows ✓ Connected. If it shows ! Needs authentication, re-run Step 3. If its tools don't appear within 10 seconds, run assistant mcp reload.
Confirm unstructured-transform shows ✓ Connected. If it shows ! Needs authentication, re-run Step 3. If its tools don't appear within 10 seconds, run assistant mcp reload.

Permission review

Static risk signals and limitations

Network access

medium · line 48

The documentation includes network, browsing, or remote request actions.

assistant mcp add unstructured-transform -t streamable-http -u https://mcp.transform.unstructured.io

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial

Signal	Value	Evidence type	Meaning
Quality score	90/100	Computed	Documentation, specificity, maintenance, and trust rules
Repository stars	1,002	Source	Repository attention, not individual Skill quality
Compatibility	0 platforms	Source	Declared in the catalog source record
Usage guide	automated source guide	Editorial	Generated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository: vellum-ai/vellum-assistant
Skill path: skills/chat-complex-documents/SKILL.md
Commit: 32b93fb5c0f5e77d2a15e2f214d3726208c9d208
License: MIT
Collected: 2026-08-04
Default branch: main

View the original SKILL.md

What this does (in plain terms)

You have documents — contracts, reports, slide decks, scanned PDFs, spreadsheets, emails, images — and you want the assistant to reliably get the content out of them and make it usable: searchable, answerable, summarizable, or ready to feed a knowledge base or another tool.

Unstructured Transform does exactly that. Hand it files and it turns them into clean, structured, AI-ready data across 60+ formats with one pipeline — no custom parsing or OCR to build and maintain. See the Transform overview.

Under the hood it:

Partitions each document into structured elements (titles, paragraphs, tables, lists), adjusting extraction per page for accuracy and cost.
Enriches the result with metadata, table and image descriptions, and entity recognition.

The result is structured JSON that's ready for search, Q&A, summarization, and agents.

Why people use it

Make documents searchable and answerable. Transform extracts clean, structured text and tables from your files so the assistant can search them and answer questions grounded in the source.
Handle messy, varied files. One integration covers 60+ formats (scanned PDFs, tables, images, Office files) instead of a per-format parser.

When to use

USE THIS SKILL WHEN:

The user wants to extract or structure content from documents (PDF, Office, images, emails, scanned files).
The user wants documents made searchable or ready for RAG / Q&A / a knowledge base.
The user asks to connect Unstructured or Unstructured Transform.
A Transform tool returns an auth error → re-run the auth step below.

Prerequisites

An Unstructured account to sign in with during the OAuth step (a free tier is available). See pricing.
Nothing to install locally — Transform is a hosted MCP server.

Setup

Step 1 — Detect your environment

Determine which command tool to use for every command in this skill:

If host_bash is available → you are on the desktop app. Use host_bash for all commands (the auth step opens your local browser).
If it is unavailable → you are on the web app. Use bash for all commands (the platform handles the browser redirect).

Step 2 — Add the server

Add Transform as a remote streamable-http MCP server. Keep the default risk level (high) — Transform ingests file content, so per-call approval is the safe default.

assistant mcp add unstructured-transform -t streamable-http -u https://mcp.transform.unstructured.io

The server is registered under the id unstructured-transform — that's the name shown by assistant mcp list and used in the commands below, even though this skill is titled "Chat with Complex Documents".

Step 3 — Authenticate via OAuth

assistant mcp auth unstructured-transform

This opens Unstructured's authorization page. After sign-in, the assistant handles the callback and caches the tokens.

On desktop → run via host_bash (opens your local browser).
On web app → run via bash (the platform handles the redirect).

Step 4 — Verify

assistant mcp list

Confirm unstructured-transform shows ✓ Connected. If it shows ! Needs authentication, re-run Step 3. If its tools don't appear within ~10 seconds, run assistant mcp reload.

Using Transform

Once connected, ask the assistant in plain language, e.g. "Use Unstructured Transform to parse these files and return one JSON file per source file," or "Extract the tables from this PDF." Transform partitions each file and returns structured output; to tune partitioning and enrichment behavior, see Control Transform output.

Per-request limits (Transform enforces these; plan around them):

Each file must be a supported file type.
Each file must be 50 MB or less.
Each request may include 10 files or fewer.
At most 5 requests may run at a time.

Disconnecting

assistant mcp remove unstructured-transform

This removes the config entry and cleans up the stored OAuth credentials.

SKILL COMPLETE WHEN

Connect: unstructured-transform appears in assistant mcp list as ✓ Connected and the user confirms its tools are available in the conversation.
Disconnect: assistant mcp remove unstructured-transform succeeds and the server no longer appears in assistant mcp list.