Install
$ agentstack add skill-cosformula-douban-sync-skill-douban-sync-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Douban Sync
Export Douban collections (books, movies, music, games) to CSV and keep them in sync via RSS.
Two Modes
1. Full Export (first time)
Use the browser tool to scrape all collection pages. Requires the user to be logged into Douban.
browser → douban.com/people/{USER_ID}/{category}?start=0&sort=time&mode=list
Categories and URL paths:
- Books:
book.douban.com/people/{ID}/collect(读过),/do(在读),/wish(想读) - Movies:
movie.douban.com/people/{ID}/collect(看过),/do(在看),/wish(想看) - Music:
music.douban.com/people/{ID}/collect(听过),/do(在听),/wish(想听) - Games:
www.douban.com/people/{ID}/games?action=collect(玩过),=do(在玩),=wish(想玩)
Each page shows up to 30 items in list mode (some pages may have fewer due to delisted entries). Paginate with ?start=0,30,60... — the script uses the paginator's "next" button to determine whether to continue.
Rate limiting: Wait 2-3 seconds between pages. If blocked, wait 30 seconds and retry.
Scripts:
scripts/douban-scraper.mjs— HTTP-only, no browser needed (may get rate-limited)scripts/douban-browser-scraper.mjs— via Puppeteer CDP, needs a running browserscripts/douban-extract.mjs— generates a browser console script for manual extraction
2. Incremental Sync (daily, via RSS)
Run scripts/douban-rss-sync.mjs — no login needed.
node scripts/douban-rss-sync.mjs
Setup: Set environment variables:
DOUBAN_USER(required): Douban user IDDOUBAN_OUTPUT_DIR(optional): Output root directory, default~/douban-sync
Recommended: Add a daily cron job for automatic sync.
Output Format
Four CSV files per user in the output directory:
douban-sync/
└── {user_id}/
├── 书.csv
├── 影视.csv
├── 音乐.csv
└── 游戏.csv
CSV columns:
title,url,date,rating,status,comment
"书名","https://book.douban.com/subject/12345/","2026-01-15","★★★★★","读过","短评内容"
status: 读过/在读/想读, 看过/在看/想看, 听过/在听/想听, 玩过/在玩/想玩
Deduplication
Both full export and RSS sync deduplicate by Douban URL — safe to run multiple times.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cosformula
- Source: cosformula/douban-sync-skill
- License: MIT
- Homepage: https://clawhub.ai/cosformula/douban-sync-skill
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.