zeelin-social-watch

Zeelin Social Watch

This skill allows you to monitor social media sentiment (舆情), trending events (热点), platform rankings (榜单), and account data across platforms like Weibo, Xiaohongshu, and Douyin — powered by the GSData open platform.

Prerequisites: This skill requires the requests library. If a module cannot be found, you may need to run pip install requests once.

Credentials: Authentication is handled via the GSDATA_APP_KEY and GSDATA_APP_SECRET environment variables. Do not attempt to use hardcoded test keys.

Adapter Usage

Use the bundled python script to interact with the API:

python3 ./gsdata_adapter.py

Note: The script and its mapping gsdata_tool_mapping_v1.json are bundled in this skill's directory. Always run the script via relative path (./gsdata_adapter.py) from this directory.

Rules

1. For a new request, run --dry-run first to verify route/action mapping.
2. Default to read-only actions.
3. CRITICAL FOR CONVERSATIONS: If you are answering a user in a chat interface (like Telegram), you MUST append --param size=5 (or a similarly small number) to prevent dumping enormous JSON payloads into the chat context.
4. Never run write-like actions unless user explicitly confirms.
5. For write-like actions, require --allow-write.
6. Return a concise summary first; included route + key fields used.
7. PAGINATION LIMIT: The API strictly enforces a maximum of 20 items per page (e.g., passing size=100 defaults to 20). To fetch large datasets, use a loop with --param page=1, --param page=2, etc. Do NOT attempt to fetch more than 20 items in a single call.
8. TOTAL COUNT ESTIMATION: Before scraping multiple pages for gsdata_pubsent_search, ALWAYS probe the total volume first by running a test search with --param limit=1 and checking the numFound field in the response JSON. Calculate total pages as ceil(numFound / 20). (Note: The dedicated num_found action has a bug with date parameters and should NOT be used for this purpose).