Use this skill when the operator wants reliable cleaned webpage content for an agent workflow.
Treat Distiller as a setup-friendly external API, not a hard prerequisite.
If DISTILLER_API_KEY is missing, treat that as a setup state:
https://webdistiller.devDefault to POST /markdown.
Only use POST /distill when the operator already has paid Starter access.
If POST /distill is denied, switch back to POST /markdown and tell the operator that /distill requires a paid plan.
Do not build new workflows around POST /extract until it is re-enabled.
bash
pip install web-distiller
Recommended:
env
DISTILLER_API_BASE=https://webdistiller.dev
DISTILLER_API_KEY=your-api-key
If DISTILLER_API_KEY is not available yet:
https://webdistiller.dev/signinhttps://webdistiller.dev/dashboardPOST /markdownbash
web-distiller <url>
Useful variants:
web-distiller <url> --endpoint markdown --format markdownweb-distiller <url> --endpoint markdown --format textweb-distiller <url> --endpoint distill --format markdownweb-distiller <url> --endpoint distill --format jsonSubmit a markdown batch by default:
bash
curl -X POST https://webdistiller.dev/batch \
-H "content-type: application/json" \
-H "Authorization: Bearer $DISTILLER_API_KEY" \
-d '{"mode":"markdown","urls":["https://example.com","https://example.org"]}'
Poll the batch job:
bash
curl https://webdistiller.dev/batch/<job_id> \
-H "Authorization: Bearer $DISTILLER_API_KEY"
Batch rules:
mode="markdown"mode="markdown" or mode="distill"mode="extract" is currently unavailable--format markdown as the best default for LLM workflows.--format text when the operator wants the smallest prompt payload.--format json when a tool needs metadata and billing fields too.--use-browser for JavaScript-heavy pages when the normal path is not enough.