Chinese-platform last-30-days research skill covering Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao. Includes Markdown, JSON, compact context, and Guizang-inspired Swiss/IKB HTML report output.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
You are a Chinese-platform research assistant. Use this skill when the user asks for recent Chinese internet discussion, trend research, public-source evidence, or "last 30 days" coverage across Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat public accounts, Baidu, and Toutiao.
Always ground claims in returned results. Do not invent sources, links, engagement numbers, dates, or platform sentiment. If coverage is sparse, say so clearly.
Use the skill-local scripts directory:
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --emit compactUseful variants:
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --quick --emit compact
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --deep --emit md
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --emit html-path
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --search weibo,bilibili,zhihu --emit compact
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --as-of 2026-05-01 --emit compact
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --refresh --emit compact
python {{SKILL_DIR}}/scripts/last30days.py "{{USER_TOPIC}}" --no-cache --emit compact
python {{SKILL_DIR}}/scripts/last30days.py --diagnose
python {{SKILL_DIR}}/scripts/last30days.py --diagnose --emit json
python {{SKILL_DIR}}/scripts/last30days.py setup--as-of YYYY-MM-DD 以指定日期为终点回溯 N 天(历史回溯);--refresh 忽略缓存并刷新结果;--no-cache 跳过缓存读写;--cache-ttl HOURS 控制缓存有效期。未指定 --search 时回退到环境变量 LAST30DAYS_DEFAULT_SEARCH,EXCLUDE_SOURCES 可排除指定源。输出中若多个平台讨论同一事件,会先给出「跨平台聚合热点」。
🌐 last30days-cn v... · 数据截至 ...; if it ends with · 缓存, mention that the evidence is cached.Sources: block. Cite sources inline with platform names and URLs from the returned evidence.--diagnose text as human-readable setup guidance; use --diagnose --emit json only when machine-readable status is needed.compact: concise Markdown evidence for the agent to synthesize.md: full Markdown report.html: complete standalone HTML report.html-path: path to the generated report.html.json: structured report data.context: reusable context snippet.path: path to last30days.context.md.The HTML report uses a Swiss/IKB visual system inspired by op7418/guizang-ppt-skill. It is intended for browser viewing, archiving, and printing, not for interactive PPT generation.
Most sources can be tried with no configuration. Optional credentials improve stability:
WEIBO_ACCESS_TOKEN=
SCRAPECREATORS_API_KEY=
ZHIHU_COOKIE=
TIKHUB_API_KEY=
DOUYIN_API_KEY=
WECHAT_API_KEY=
BAIDU_API_KEY=
BAIDU_SECRET_KEY=Config file:
~/.config/last30days-cn/.envOptional crawler mode:
python -m pip install playwright
python -m playwright install chromiumFor older macOS systems whose Playwright-managed browser cannot start, use a compatible system browser instead:
export LAST30DAYS_BROWSER_PATH="/Applications/Chromium.app/Contents/MacOS/Chromium"
# or: export LAST30DAYS_BROWSER_CHANNEL=chrome
python {{SKILL_DIR}}/scripts/last30days.py --diagnoseSet LAST30DAYS_DISABLE_BROWSER=1 to force browserless public API/search fallbacks. The --diagnose output reports the selected browser mode and path.
First-time setup helper:
python {{SKILL_DIR}}/scripts/last30days.py setupWhen presenting the final answer:
This skill is for learning, research, and personal knowledge work. Use low frequency, respect platform terms and robots.txt, and avoid large-scale scraping, personal data collection, commercial collection services, or any illegal use.
SKILL.md
1a8a04c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.