brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
ernie-image-monitorThis skill should be used when the user wants to monitor, search, or analyze social media and web content about ERNIE-Image across Chinese platforms including Zhihu, Xiaohongshu, WeChat Official Accounts, and Baidu Search.
Independent GitHub snapshot · Automated classification · Original documentation governs
Monitor mentions of ERNIE-Image across Zhihu, Xiaohongshu, WeChat Official Accounts, and Baidu Search. Collect structured data including account name, content, sentiment judgment, and source URL.
~/.local/bin/opencli (v1.7.4+)~/.local/bin/opencli doctor to verify browser bridge connectivityIf OpenCLI is not installed, run:
npm install -g @jackwener/opencli --prefix ~/.local
For Chrome extension: load unpacked from ~/.local/lib/node_modules/@jackwener/opencli/extension/.
Run a full multi-platform scan (with XHS detail fetch):
python3 scripts/monitor.py --limit 20 --save
Run without XHS detail fetch (faster):
python3 scripts/monitor.py --limit 20 --save --no-detail
Run on specific platforms:
python3 scripts/monitor.py --platforms zhihu xhs --limit 20
python3 scripts/monitor.py --platforms weixin baidu --limit 10
Each collected item includes:
| Field | Description |
|---|---|
platform | 知乎 / 小红书 / 微信公众号 / 百度搜索 |
account | 发布者账号或公众号名称 |
title | 标题 |
content_snippet | 内容摘要(前 200 字) |
sentiment | 正面 ✅ / 负面 ❌ / 中性 ➖ |
url | 来源链接 |
fetched_at | 采集时间 |
The script collects raw data with sentiment field left empty. Claude must fill in sentiment judgment semantically after receiving the results — do NOT use keyword matching.
For each item, read title + content_snippet and judge:
When presenting results to the user, include the sentiment label for each item and provide a summary count at the top (e.g., "共 N 条 | 正面 X ✅ 负面 Y ❌ 中性 Z ➖").
Each item includes a published_at field:
created_time or published_at field in API responsepublished_at field in API responseResults are sorted by published_at descending (newest first). Items without a date appear at the end.
Every monitoring run must upload results to Feishu as a NEW document — never overwrite existing documents.
After generating the Markdown report:
~/feishu_report.md~ directory with relative path):
cd ~ && ~/.local/bin/lark-cli docs +create --title "ERNIE-Image 舆情监测报告 <crawl_time>" --markdown @feishu_report.md
YYYY-MM-DD HH:MM)For deeper analysis of individual posts found during monitoring:
知乎问题详情:
python3 scripts/zhihu_detail.py <question-id-or-url> --limit 10
小红书笔记详情 + 评论:
python3 scripts/xhs_detail.py <note-id-or-url> --comments --limit 20
| Platform | Method | Requires Login |
|---|---|---|
| 知乎 | opencli zhihu search | Yes (cookie) |
| 小红书 | opencli xiaohongshu search | Yes (cookie) |
| 微信公众号 | Google site:mp.weixin.qq.com | No |
| 百度搜索 | Google site:baidu.com 系列 | No |
For full OpenCLI command reference, load references/opencli_commands.md.
ERNIE-ImageERNIE-Image-TurboERNIE_Image文心图像百度文心图像生成To add more keywords, edit the SEARCH_KEYWORDS list in scripts/monitor.py.
Only content published on or after 2026-04-14 (ERNIE-Image official release date) is kept. Items with unknown dates are retained for manual review.
This is enforced via DATE_FILTER = date(2026, 4, 14) in monitor.py.
Each item must contain at least one of these keywords in title + body + tags:
ernie-image, ernie_image, ernie image, ernie-image-turbo, 文心图像, 百度文心图像
For each XHS search result, the script calls opencli xiaohongshu note <note-id> to fetch:
content / desc field, up to 200 chars)Use --no-detail flag to skip this step and speed up execution.
Each collected item in the final report includes:
| Field | Description |
|---|---|
platform | 知乎 / 小红书 / 微信公众号 / 百度搜索 |
account | 发布者账号或公众号名称 |
title | 标题 |
content_snippet | 内容大意(正文前 200 字或摘要) |
tags | 标签(小红书) |
published_at | 发布时间 |
sentiment | 正面 ✅ / 负面 ❌ / 中性 ➖(Claude 语义分析) |
url | 来源链接 |