Skip to content
Agentmart
Submit a tool

parse

Parse PDFs, images, Office files, and HTML into Markdown or JSON for AstroWiki raw staging.

Skill by ChineseCricket

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/chinesecricket-parse

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

Parse PDFs, images, Office files, and HTML into Markdown or JSON for AstroWiki raw staging. Inspired by z-smart-xparse.

Use cases: documents, frontend

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/parse

What's inside

Skill name
parse
Description
Parse PDFs, images, Office files, and HTML into Markdown or JSON for AstroWiki raw staging. Inspired by z-smart-xparse.
License
MIT
Instructions
34 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Astro Document Parse

Use this skill when a local document must be prepared for downstream AstroWiki compilation.

## Preferred Parser

Use `xparse-cli` when available:

```bash
xparse-cli parse path/to/file.pdf --view markdown --output raw/documents/file.md
```

For large PDFs, split before parsing:

- split if file size exceeds 5 MB or page count exceeds 100;
- default chunk size: 50 pages;
- parse chunks serially;
- merge Markdown chunks in page order.

## Fallback

If `xparse-cli` is unavailable:

- stage the original file in `raw/documents/`;
- create a short metadata sidecar;
- report that parsing remains pending.

## Rules

- Do not discard the original document.
- Do not write parsed output directly to `wiki/`.
- Never silently skip failed chunks.

From ChineseCricket/AstroWiki, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 12, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ChineseCricket

Cite this page

parse skill. Agent Mart. https://agentmart.dev/skills/chinesecricket-parse (last updated 2026-10-24)