capabilities

PDF Processor

Name: Pdf Processor
Author: Athina AI

Process PDFs - extract text, tables, and structured data from documents

by Athina AI

Run in Gooseworks View skill in Github

Install

Terminal

npx gooseworks install --all

# then, in Claude Code, Cursor, or Codex:
/gooseworks use the pdf-processor skill

About This Skill

PDF Processor - Extract Data from PDFs

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Extract text, tables, and structured data from PDF documents.

Workflow

Step 1: Fetch PDF Content

Use Linkup to fetch PDF URLs:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"linkup","path":"/fetch","body":{"url":"https://example.com/document.pdf"}}'

Step 2: Extract with AI

Use ScrapeGraph to extract specific content:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"scrapegraph","path":"/v1/smartscraper"}'
  "website_url": "https://example.com/report.pdf",
  "user_prompt": "Extract all financial figures, tables, and key metrics from this document"
}'

Step 3: Extract Tables

Get structured table data:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"riveter","path":"/v1/run"}'
  "input": {
    "urls": ["https://example.com/report.pdf"]
  },
  "output": {
    "tables": {"prompt": "Extract all tables with titles, headers, and rows", "contexts": ["urls"]}
  }
}'

Step 4: Convert to Markdown

Get readable markdown output:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"scrapegraph","path":"/v1/markdownify","body":{"website_url":"https://example.com/document.pdf"}}'

Example Usage

# Extract data from financial report
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"scrapegraph","path":"/v1/smartscraper"}'
  "website_url": "https://example.com/annual-report.pdf",
  "user_prompt": "Extract revenue, profit, and key business metrics with their values"
}'
 
# Extract invoice data
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"riveter","path":"/v1/run"}'
  "input": {"urls": ["https://example.com/invoice.pdf"]},
  "output": {
    "vendor": {"prompt": "Vendor name", "contexts": ["urls"]},
    "amount": {"prompt": "Total amount", "contexts": ["urls"]},
    "date": {"prompt": "Invoice date", "contexts": ["urls"]}
  }
}'

Tips

Specify exact data you need for better extraction
Use schemas for consistent structured output
Handle multi-page documents in chunks
Verify extracted numbers against source

Discover More

List all endpoints, or add a path for parameter details:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"linkup API endpoints"}' api show riveter
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"scrapegraph API endpoints"}'
 
Example: `curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/details \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"olostep","path":"/v1/scrapes`"}' for endpoint parameters.

What's included

Specify exact data you need for better extraction

Use schemas for consistent structured output

Handle multi-page documents in chunks

Verify extracted numbers against source

Video Production Harness

Full video production sequence with script review, actual ingredient choices, controlled generation, editing, evidence-based quality review, polish, captions and delivery. A host binding supplies project storage, authentic approvals, provider access and billing.

Render Street Interview

Build a vox-pop street interview video ad. An interviewer with a handheld mic asks passers-by one question about the brand's product, they give blunt wrong guesses, one gives the real answer, and the cut lands on a branded end card. Generates the takes through the GooseWorks fal proxy (Seedance 2.0 with native voice), then grades, re-cuts, captions and gates them locally. Use for the street-interview format.

Write Video Ad Script

Write the words of a short-form video ad (voiceover, dialogue, chat bubbles, on-screen lines) the way performance creative teams do instead of from a blank page. Builds the script from the buyers' own words, the beat sheet of an ad that already works and three deliberately different angles, filters them with a rule check and a second non-Claude model, and takes the strongest into the review with the other two as one-line swaps. Use it in every video ad run before any paid step, and whenever the user asks to write, rewrite or improve a video ad script or says a script sounds generic or AI-written.