Web Distiller

Fetch agent-ready cleaned Markdown from the Distiller API instead of relying on raw webpage fetches.

Security Scan

The skill's requirements and runtime instructions are consistent with its stated purpose (calling a Distiller web API to return cleaned Markdown); there are no obvious incoherent or overly-broad requests.

Purpose & Capability

The skill name/description (fetch cleaned Markdown from Distiller) matches what the SKILL.md instructs (POST /markdown, optional /distill, batch endpoints). The only required environment variables (DISTILLER_API_BASE and a primary API key) align with a typical API integration.

Instruction Scope

SKILL.md limits runtime actions to calling the Distiller endpoints, guiding operators to the dashboard for an API key, and polling batch jobs. It does not instruct reading unrelated host files, other env vars, or sending data to unknown endpoints; the external endpoints mentioned are consistently under webdistiller.dev.

Install Mechanism

This is an instruction-only skill (no install spec or code files). SKILL.md suggests 'pip install web-distiller' but the registry bundle contains no install spec or package provenance. This is not necessarily malicious, but you should verify the pip package identity/source before running it.

Credentials

Only DISTILLER_API_BASE and a primary API key are requested, which is proportional for a remote-API integration. No unrelated secrets or config paths are requested.

Persistence & Privilege

The skill is not always-on and does not request system-wide configuration or elevated privileges. It is user-invocable and allows autonomous invocation by default, which is the platform norm.

Assessment

This skill appears coherent for calling a hosted Distiller API, but before installing or using it: 1) Verify the webdistiller.dev service is the legitimate provider you expect (check official site or vendor docs). 2) If you plan to run the suggested 'pip install web-distiller', locate the package on PyPI or the vendor's source repo and inspect its provenance and code before installing. 3) Treat DISTILLER_API_KEY as a secret: provide it only if you trust the service and understand what web content will be sent to that API (avoid sending private/internal pages). 4) If you need stronger isolation, create a dedicated API key with limited scope or run the integration in a sandbox. 5) If you require assurance about billing or data retention (distill vs markdown, batch jobs), confirm the product's pricing/terms before enabling paid endpoints.

Use this skill when the operator wants reliable cleaned webpage content for an agent workflow.

Default behavior

• Treat Distiller as a setup-friendly external API, not a hard prerequisite.
• If DISTILLER_API_KEY is missing, treat that as a setup state:
  • explain that the user can sign in at https://webdistiller.dev
  • direct them to the dashboard to create or reveal their API key
  • continue with setup guidance instead of failing the workflow
• Default 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.

Install

pip install web-distiller

Environment

Recommended:

DISTILLER_API_BASE=https://webdistiller.dev
DISTILLER_API_KEY=your-api-key

If DISTILLER_API_KEY is not available yet:

1. Send the operator to https://webdistiller.dev/signin
2. Have them open the dashboard at https://webdistiller.dev/dashboard
3. Retrieve or regenerate the API key there
4. Resume with POST /markdown

Default command

web-distiller <url>

Useful variants:

• web-distiller <url> --endpoint markdown --format markdown
• web-distiller <url> --endpoint markdown --format text
• web-distiller <url> --endpoint distill --format markdown
• web-distiller <url> --endpoint distill --format json

Batch workflow

Submit a markdown batch by default:

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:

curl https://webdistiller.dev/batch/<job_id> \
  -H "Authorization: Bearer $DISTILLER_API_KEY"

Batch rules:

• free users should use mode="markdown"
• paid users can use mode="markdown" or mode="distill"
• mode="extract" is currently unavailable

Operator guidance

• Use --format markdown as the best default for LLM workflows.
• Use --format text when the operator wants the smallest prompt payload.
• Use --format json when a tool needs metadata and billing fields too.
• Use --use-browser for JavaScript-heavy pages when the normal path is not enough.
• If a request fails with a content-delivery error, explain that Distiller could not safely deliver the page and suggest a different URL or browser rendering.