Quark Download

This automates the full workflow for finding and downloading Chinese cloud drive resources: search across aggregated sources via PanSou, validate links in parallel, fetch file details, then trigger saves directly in your local Quark desktop app. It's built for the specific use case where you have Quark membership and want to skip the manual browser dance of searching, clicking dead links, and copy-pasting URLs. The preflight check is smart, it gates everything on whether your Quark app is actually running and logged in before letting you search, which prevents the annoying scenario of finding good resources then discovering you can't save them. The search command returns structured JSON with file listings, so you can see what's in a share before committing to save it.

skills.sh installs: 196
GitHub stars: 5
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add psylch/media-master --skill quark-download --agent claude-code

Installs into .claude/skills of the current project.

Files

Quark Search — 网盘资源搜索与下载

Language

Match user's language: Respond in the same language the user uses.

Automate the full workflow: search resources → validate links → save to Quark cloud drive → download locally, by combining the PanSou aggregation API with the local Quark desktop APP.

All operations use the CLI script at ${SKILL_PATH}/scripts/quark_search.py. It outputs JSON to stdout ({"status": "ok", "results": {...}, "hint": "..."}) and errors to stderr ({"error": "code", "message": "...", "hint": "...", "recoverable": true/false}). Exit codes: 0 = success, 1 = recoverable error, 2 = fatal error.

Preflight (MUST run first)

Before any business command (search, validate, save, etc.), run preflight:

python3 ${SKILL_PATH}/scripts/quark_search.py preflight

Response: Standardized JSON with ready: true/false, dependencies, and services status.

If ready: true → proceed to workflow.
If ready: false → follow the Check/Fix table below, then re-run preflight until it passes. Do NOT proceed to search or save until preflight passes.

SKILL.md on GitHub