# Hn Extract

> Extract a HackerNews post (article + comments) into single clean Markdown for quick reading or LLM input.

- Skill: `demerzels-lab/hn-extract` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add demerzels-lab/hn-extract`
- Raw SKILL.md: https://api.skillmd.com/api/skills/demerzels-lab/hn-extract/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Demerzels-lab (https://skillmd.com/u/demerzels-lab)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/demerzels-lab/hn-extract

---


# HackerNews Extract

Extract a HackerNews post (article + comments) into single clean Markdown for quick reading or LLM input.

see [Examples](https://github.com/guoqiao/skills/blob/main/hn-extract/examples)

## What it does
- Accepts an HackerNews id, url, or a saved Algolia JSON file.
- Scrapes the linked article content with `trafilatura`, cleans HTML, and formats it.
- Fetches the story metadata and comment tree from `https://hn.algolia.com/api/v1/items/<id>`.
- Outputs a readable combined markdown file with original article, threaded comments, and key metadata.

## Requirements

- `uv` installed and in PATH.

## Install

No install beyond having `uv`.
Dependencies will be installed automatically by `uv` into to a dedicated venv when run this script.

## Usage Workflow (Mandatory for Agents)

When an agent is asked to extract a HackerNews post:
1.  **Run the script** with an output path: `uv run --script ${baseDir}/hn-extract.py <input> -o /tmp/hn-<id>.md`.
2.  **Send ONE combined message:** Upload the file and ask the question in the *same* tool call. Use the `message` tool (`action=send`, `filePath="/tmp/hn-<id>.md"`, `message="Extraction complete. Do you want me to summarize it?"`).
3.  **Do not** output the full text or a summary directly in the chat unless specifically requested.

## Usage

```bash
# run as uv script
uv run --script ${baseDir}/hn-extract.py <hn-id|hn-url|path/to/item.json> [-o path/to/output.md]

# Examples
uv run --script ${baseDir}/hn-extract.py 46861313 -o /tmp/output.md
uv run --script ${baseDir}/hn-extract.py "https://news.ycombinator.com/item?id=46861313"
uv run --script ${baseDir}/hn-extract.py data/item.json
```

- Omit `-o` to print to stdout.
- Directories for `-o` are created automatically.

## Notes
- Retries are enabled for HTTP fetches.
- Comments are indented by thread depth.
- Article fetch uses `trafilatura.fetch_url` with liberal SSL handling to make it more usable.
- Sites requires authentication or blocks scraping may still fail.