Skills + CLI

# Install globally
npm install -g @thunderbit/thunderbit-cli

# Or run one-shot via npx
npx -y @thunderbit/thunderbit-cli --help

export THUNDERBIT_API_KEY=tb_YOUR_API_KEY

thunderbit --api-key tb_YOUR_API_KEY distill https://example.com

# Per call
thunderbit --base-url https://api.your-domain.com distill https://example.com

# Or set via environment variable
export THUNDERBIT_API_BASE_URL=https://api.your-domain.com
thunderbit distill https://example.com

thunderbit --version
# or
thunderbit -V

# Basic usage
thunderbit distill https://example.com/article

# Stream Markdown to stdout
thunderbit distill https://example.com --format markdown

# Save to file
thunderbit distill https://example.com --format markdown > article.md

# Use the basic JS renderer (covers most modern sites)
thunderbit distill https://example.com --render-mode basic

# Use the full headless browser (slowest, highest fidelity)
thunderbit distill https://example.com --render-mode full

# Geo-target for region-aware sites
thunderbit distill https://example.com --country-code DE

# Bump per-page timeout
thunderbit distill https://example.com --timeout 60000

# Use sync /distill instead of the default async submit + poll
thunderbit distill https://example.com --sync

# Inline schema — flat map of field → instruction
thunderbit extract https://example.com/product \
  --schema '{"name":"product name","price":"the listed price as a number","currency":"3-letter currency code"}'

# Schema from file
thunderbit extract https://example.com/product --schema ./schema.json

# Save the extracted JSON
thunderbit extract https://example.com/product --schema ./schema.json --format json -o data.json

{
  "success": true,
  "data": {
    "url": "https://example.com/product",
    "data": [
      { "name": "iPhone 15 Pro", "price": 999, "currency": "USD" }
    ]
  }
}

# AI proposes fields, you toggle/edit, then extraction runs with the curated schema
thunderbit extract https://example.com/product --interactive

# Steer the suggestion with a prompt
thunderbit extract https://example.com/product -i --prompt "focus on pricing and availability"

# Persist the schema for reuse
thunderbit extract https://example.com/product -i --save-schema ./product-schema.json

# Bump page-render time for SPAs
thunderbit extract https://example.com --schema ./schema.json --render-mode full

# Sync mode
thunderbit extract https://example.com --schema ./schema.json --sync

# Longer timeout for complex pages
thunderbit extract https://example.com --schema ./schema.json --timeout 120000

# Basic
thunderbit suggest-fields https://example.com/product

# Steer with a prompt
thunderbit suggest-fields https://example.com/listings --prompt "extract job postings only"

# Region-aware
thunderbit suggest-fields https://example.com --country-code DE

thunderbit suggest-fields "$URL" --format json \
  | jq 'map({(.name): .instruction}) | add' > schema.json

thunderbit extract "$URL" --schema ./schema.json

# URLs as positional args
thunderbit batch distill https://a.com https://b.com https://c.com

# Or read URLs from a file (one per line)
thunderbit batch distill --file urls.txt

# Submit only — print the job ID and exit (use webhook or poll later)
thunderbit batch distill --file urls.txt --no-poll

# Bump per-page timeout
thunderbit batch distill --file urls.txt --timeout 60000

# Pipe results into another tool
thunderbit batch distill --file urls.txt --format json \
  | jq -r '.data.results[] | select(.success == true) | .markdown' \
  > distilled.md

thunderbit batch cancel-distill <jobId>

# URLs as positional args + inline schema
thunderbit batch extract https://a.com https://b.com \
  --schema ./schema.json

# Read URLs from a file
thunderbit batch extract --file urls.txt --schema ./schema.json

# Submit only
thunderbit batch extract --file urls.txt --schema ./schema.json --no-poll

thunderbit batch cancel-extract <jobId>

# Pipe Markdown into another tool
thunderbit distill https://example.com --format markdown | head -50

# Redirect to a file
thunderbit distill https://example.com --format markdown > output.md

# Save extraction JSON
thunderbit extract https://example.com --schema ./schema.json --format json > data.json

# Markdown body straight to disk
thunderbit distill https://example.com --format markdown

# Full structured response
thunderbit distill https://example.com --format json

# Distill an article
thunderbit distill https://example.com/article --format markdown

# Save HTML-converted Markdown to disk
thunderbit distill https://example.com --format markdown -o page.md

# Distill a docs site listed in urls.txt and write each page to disk
thunderbit batch distill --file urls.txt --format json \
  | jq -r '.data.results[] | select(.success == true) | "\(.url)\t\(.markdown)"' \
  > corpus.tsv

# Step 1: AI proposes fields, you curate, schema saved to disk
thunderbit extract https://example.com/product -i --save-schema ./schema.json

# Step 2: re-use across the catalog
thunderbit batch extract --file urls.txt --schema ./schema.json --format json > products.json

thunderbit extract "$URL" --schema ./schema.json --format json \
  | jq -e '.data | length > 0'

# Extract URLs from a search-result JSON
thunderbit distill https://example.com --format json \
  | jq -r '.data.metadata.canonicalUrl'

# Pipe distilled content into a model for summarisation
thunderbit distill "$URL" --format markdown \
  | claude -p "summarise the article in 5 bullets"

# Count successful pages in a batch
thunderbit batch distill --file urls.txt --format json \
  | jq '[.data.results[] | select(.success == true)] | length'