Skip to content
Agentmart
Submit a tool

ingest-link

Ingest web URLs and online PDFs by extracting rendered content via an external qt-web-extractor service.

Skill by UynajGI

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/uynajgi-ingest-link

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Ingest web URLs and online PDFs by extracting rendered content via an external qt-web-extractor service. Use when the user wants to save web pages, articles, or online PDFs into their DrBrain library. Trigger on "save this webpage", "ingest this URL", "add this article to my library", "download and save this page".

Use cases: writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ingest-link

What's inside

Skill name
ingest-link
Description
Ingest web URLs and online PDFs by extracting rendered content via an external qt-web-extractor service. Use when the user wants to save web pages, articles, or online PDFs into their DrBrain library. Trigger on "save this webpage", "ingest this URL", "add this article to my library", "download and save this page".
License
MIT
Instructions
40 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Ingest Web Links

Extract rendered content from web URLs via an external qt-web-extractor service
and save as paper records in DrBrain.

## Prerequisites

An external `qt-web-extractor` service must be running (default: `http://127.0.0.1:8766`).
Set `WEBEXTRACT_URL` to configure a custom endpoint.

## Quick Start

```bash
drbrain ingest-link https://example.com/page
drbrain ingest-link https://example.com/report.pdf --pdf
drbrain ingest-link https://a.com https://b.com
drbrain ingest-link https://example.com --dry-run
```

## How it works

1. POSTs the URL to the external extractor service
2. Receives rendered text (markdown), title, and metadata
3. Registers the body **canonically** through the same write path as file ingest
   (document revision + content blocks + leaves); no per-paper `raw.md` is written
4. Records `raw` (canonical fingerprint) and `tree` (skipped — `rag prepare` builds the
   hierarchy) artifacts and registers the paper with status `uploaded`
5. A canonical write failure rolls the URL back and makes the command exit non-zero

## CLI Reference

| Command | What it does |
|---------|--------------|
| `drbrain ingest-link <url>` | Ingest a single URL |
| `drbrain ingest-link <url1> <url2>` | Batch ingest |
| `drbrain ingest-link <url> --pdf` | Force PDF extraction |
| `drbrain ingest-link <url> --dry-run` | Preview only |
| `drbrain ingest-link <url> --json` | JSON output |

From UynajGI/drbrain, MIT.

More from UynajGI/drbrain

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 16, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/UynajGI/drbrain
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from UynajGI

Cite this page

ingest-link skill. Agent Mart. https://agentmart.dev/skills/uynajgi-ingest-link (last updated 2026-10-24)