sn-search-social-cn
用于搜索中文社交平台。脚本入口覆盖 B站视频、知乎问答和抖音视频;小红书、微博当前没有脚本入口,只能通过 browser-use / 公开网页兜底。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
用于搜索中文社交平台。脚本入口覆盖 B站视频、知乎问答和抖音视频;小红书、微博当前没有脚本入口,只能通过 browser-use / 公开网页兜底。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
用于用户请求深度研究、系统性研究、竞品分析、方案对比、趋势分析或事实核查时。**遇到以下任一情况就主动使用本 skill,不要自行搜几条就回答**:①用户出现触发词:深度研究 / 深度调研 / 深入研究 / 全面研究 / 系统研究 / 调研 / 调查 / 尽调 / 行业研究 / 市场研究 / 竞品分析 / 政策研究 / 技术研究 / 趋势研究 / 事实核查 / 写一份研究报告 / 调研报告 / 深度报告 / research / deep research;②请求需要跨多来源取证、多维度对比、交叉验证才能给出可靠结论;③用户要求产出报告、白皮书、行业分析或尽调文档;④话题涉及最新政策/市场/产品/价格/法规,需要系统核查。明确要求核验来源的单点事实可走 quick;无核验要求的简单常识问答不使用。模糊或宽泛的"研究/了解一下 X"也优先触发。仅不用于:一句话摘要、已给定单一来源的整理、纯文字润色改写。
Standard and fast PPT pipeline. All LLM / VLM / T2I calls are wrapped in a single CLI entry (scripts/run_stage.py). The main agent's job is simple: emit ONE shell command per stage, never write loops, never write prompts. Standard mode plans thoroughly with a three-sample deck preview checkpoint (three concatenated deck images plus a preview URL), web research, image search, and user-selected final output format (PPTX or PDF) for polished, delivery-ready presentations. Fast mode builds a complete draft immediately with autonomous decisions, then provides structured refinement suggestions so the user can iterate quickly. Supports AI-generated infographics (U1) for diagrams and flowcharts, web image search (Serper) for real photos, and ECharts for data charts.
Open the AI PPT editing WebUI for previously generated SenseNova HTML slides. Use when the user asks to preview, inspect, edit, or open an existing/generated PPT deck in the WebUI/workbench without regenerating slides. Accepts an explicit deck_dir or auto-detects the newest local ppt_decks entry containing HTML pages. Does not run style/outline/page-html/export generation.
Creative-mode PPT pipeline. One full-page 16:9 PNG per slide. LLM / VLM calls go through sn-ppt-standard/lib/model_client.py (shared thin client). Text-to-image (the actual png rendering) goes through sn-image-base/scripts/sn_agent_runner.py. Falls back to web image search when T2I generation fails. Expects task_pack.json + info_pack.json already written by sn-ppt-entry.
Entry point for PPT generation. Asks the user to choose a mode (fast, standard, or creative), then collects role / audience / scene / page_count as needed. For standard mode, also asks how images should be sourced (AI generation, web search, or none), whether charts should use AI-generated infographics or ECharts, and whether the final deliverable should be PPTX or PDF. Parses uploaded pdf/docx/md/txt files, produces task_pack.json + info_pack.json in a new deck_dir, then dispatches to sn-ppt-creative or sn-ppt-standard. Fast mode skips optional questions and gets straight to building. Use when the user asks to make a PPT / presentation / 演示 / PPT. If the user asks to open, preview, inspect, or edit previously generated HTML slides in the WebUI/workbench without regenerating, dispatch to sn-ppt-workbench instead of this generation entry.
Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.
| name | sn-search-social-cn |
| description | 用于搜索中文社交平台。脚本入口覆盖 B站视频、知乎问答和抖音视频;小红书、微博当前没有脚本入口,只能通过 browser-use / 公开网页兜底。 |
API key、token 与 cookie 统一建议写在仓库根目录 .env(参考 .env.example),并由 runtime 或用户在执行前加载为同名环境变量。脚本仍只从环境变量或显式 CLI 参数读取凭证;不要把真实密钥写入 skill payload、报告、日志或提交。
脚本搜索 B站、知乎、抖音三个中文社交平台。小红书、微博当前没有可用脚本入口,如研究必须覆盖这两类来源,使用 browser-use 打开公开网页结果或平台搜索页,并在结果中说明该来源来自网页兜底。
中文社交平台没有稳定的公开搜索 API,所有脚本依赖内部 API 或第三方库,可能因平台更新而失效。
| 脚本 | 平台 | 稳定性 | 认证方式 |
|---|---|---|---|
bilibili_search.py | B站 | 较高 | 无需(可选 cookie 提高质量) |
zhihu_search.py | 知乎 | 中等 | 需 ZHIHU_COOKIE |
douyin_search.py | 抖音 | 较低 | 需 DOUYIN_COOKIE |
| 无脚本 | 小红书 | 低 | browser-use / 公开网页兜底 |
| 无脚本 | 微博 | 低 | browser-use / 公开网页兜底 |
首次运行或脚本提示缺库时,使用本技能的依赖清单安装到当前 Python 环境:
python3 -m pip install -r requirements.txt
不要在脚本内部自动安装依赖。若安装失败、网络不可用或包不可用,停止使用对应脚本并改用 browser-use 搜索免费可见网页,说明缺少依赖。
Cookie 字段XHS_COOKIE / WEIBO_COOKIE。python3 scripts/bilibili_search.py <query> [选项]
| 参数 | 说明 | 默认值 |
|---|---|---|
query | 搜索关键词(必填) | — |
--limit, -n | 返回结果数量 | 10 |
--cookie | B站 Cookie(也可通过 BILIBILI_COOKIE 环境变量设置,可选,提高结果质量) | — |
--order | 排序:空=综合, totalrank=最佳匹配, click=播放, pubdate=最新, dm=弹幕, stow=收藏 | 综合 |
python3 scripts/bilibili_search.py "机器学习教程" --limit 5
python3 scripts/bilibili_search.py "Python" --order click --limit 10
python3 scripts/zhihu_search.py <query> [选项]
| 参数 | 说明 | 默认值 |
|---|---|---|
query | 搜索关键词(必填) | — |
--limit, -n | 返回结果数量 | 10 |
--cookie | 知乎 Cookie(也可通过 ZHIHU_COOKIE 环境变量设置,必填) | — |
--type | 搜索类型:general, topic, people, zvideo | general |
ZHIHU_COOKIE="..." python3 scripts/zhihu_search.py "Python 异步编程" --limit 5
python3 scripts/zhihu_search.py "大模型" --cookie "..." --type topic --limit 5
python3 scripts/douyin_search.py <query> [选项]
| 参数 | 说明 | 默认值 |
|---|---|---|
query | 搜索关键词(必填) | — |
--limit, -n | 返回结果数量 | 10 |
--cookie | 抖音 Cookie(也可通过 DOUYIN_COOKIE 环境变量设置,必填) | — |
DOUYIN_COOKIE="..." python3 scripts/douyin_search.py "编程教程" --limit 5
标准 JSON:{"success": true, "query": "...", "provider": "bilibili|zhihu|douyin", "items": [...], "error": null}
小红书、微博通过 browser-use / 公开网页兜底时,不承诺以上脚本 JSON 结构;记录打开的页面 URL、检索词、可见结果和限制即可。