Bili Note

Turn Bilibili videos that are already registered and parsed in MindSpace, or Bilibili opus/article posts, into evidence-linked Markdown learning notes. Use whenever the user asks to 提取、提炼、总结、整理 B站/Bilibili 视频、课程、动态、图文或专栏,保存学习笔记,结合评论区补充观点,或从已解析视频中查找带时间戳的内容和关键画面。Video tasks require an authorized mediaId from the current attachment context; this skill never installs or runs its own ASR models.

341 stars 39 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mingchen666/Reviva --skill bili-note
Manual install
git clone --depth 1 https://github.com/mingchen666/Reviva.git /tmp/Reviva
mkdir -p ~/.claude/skills
cp -r /tmp/Reviva/electron/builtin-assets/skills/bili-note ~/.claude/skills/bili-note

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Bili Note

把 B 站视频或图文内容整理成可检索、可复用、可回查证据的 Markdown 学习笔记。

视频内容统一由 MindSpace 媒体模块负责字幕、语音转录、时间轴和关键帧;本技能不下载视频音频,不安装或运行 Qwen3-ASR、Whisper、Faster Whisper、FunASR、Python/CUDA 环境或模型缓存。

## 两条工作路线

先判断输入属于哪一类,不要混用流程。

### 已解析视频

当前附件上下文必须提供 `mediaId`。视频 URL 或 BVID 本身不足以开始转录。

1. 用 `media_read(mediaId="<authorized mediaId>", mode="metadata")` 检查授权、解析状态、时长和可用模式。
2. 如果解析未完成、失败或没有 `mediaId`,停止内容提炼,告诉用户先在 MindSpace 中添加并解析视频。
3. 根据用户问题先用 `media_read(mediaId="<authorized mediaId>", mode="search", query="<主题>")` 定位主题,不要默认加载整段转录。
4. 用 `media_read(mediaId="<authorized mediaId>", mode="transcript")` 读取连续上下文;下一页传入上一页的 `nextCursor` 作为 `cursor`。长视频按主题和时间段取证。
5. 需要验证 PPT、代码、界面操作、板书或无解说画面时,用 `media_read(mediaId="<authorized mediaId>", mode="frames")` 获取候选关键帧,再按需交给 `vision_analyze`。
6. `chapters` 和 `artifacts` 只在 metadata 声明可用时读取。
7. 如用户要求评论区,可运行辅助脚本抓取评论;评论失败不影响基于系统媒体证据写笔记。
8. 写作时区分转录证据、画面证据、评论/元数据和 Agent 推理。

### Opus、动态与专栏图文

图文不是视频语音解析,继续使用脚本抓正文、图片、代码块和可选评论。

```json
{
  "cmd": "python",
  "args": [
    "/skills/bili-note/scripts/run_bili_note.py",
    "https://www.bilibili.com/opus/1194341967364882439",
    "--work-dir", ".\\tmp_bili_opus",
    "--archive-dir", "D:\\knowledge\\原始材料\\O1194341967364882439",
    "--comments"
  ]
}
```

脚本型能力要求 Agent 已绑定 `exec_command` 且允许执行 `python`。如果不可用,说明限制并让用户直接提供图文正文;不要声称已经提取或归档。

## 视频输入检查

### 没有 mediaId

明确告诉用户:

- 先在 MindSpace 中添加该 B 站视频;
- 在媒体解析配置中选择服务商并完成解析;
- 再把已登记的视频作为附件交给当前 Agent。

不要自行回退到下载音频或安装 ASR。

### 解析进行中或失败
Read the full skill on GitHub

Details

Skill name
bili-note
Path
electron/builtin-assets/skills/bili-note/SKILL.md
Repo updated
15 November 2026

FAQ

What does the Bili Note skill do?

Turn Bilibili videos that are already registered and parsed in MindSpace, or Bilibili opus/article posts, into evidence-linked Markdown learning notes. Use whenever the user asks to 提取、提炼、总结、整理 B站/Bilibili 视频、课程、动态、图文或专栏,保存学习笔记,结合评论区补充观点,或从已解析视频中查找带时间戳的内容和关键画面。Video tasks require an authorized mediaId from the current attachment context; this skill never installs or runs its own ASR models.

How do I install the Bili Note skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mingchen666/Reviva --skill bili-note. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Bili Note popular?

It lives in mingchen666/Reviva, which has 341 GitHub stars and 39 forks.

Related skills

Web Access

341

mingchen666/Reviva

所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、网络交互等。 触发场景:用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容(小红书、微博、推特等)、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。

Other39

AI Animation Skill

341

mingchen666/Reviva

将科普内容文本转换为可视化PPT风格网页的完整工作流。当用户输入科普内容并希望生成演示页面时触发。支持两种模式:(1) 默认模式:将科普内容生成为仿PPT轮播的单页HTML动画网页;(2) 流程图模式:使用Animation模板将已生成的AI_Animation.html按平面UI样式重构。模板已内置于Skill中。触发词包括"生成PPT"、"生成演示网页"、"生成流程图"等。

Frontend & Design39

Cet Skill

341

mingchen666/Reviva

CET-4 and CET-6 exam preparation coach for original CET-style practice, diagnostic feedback, writing and translation correction, reading/listening drills, and study planning.

Writing & Content39

Computer Organization Visualization

341

mingchen666/Reviva

Use this skill whenever the user wants visual learning for computer organization, data representation, two's complement, floating point, cache mapping, memory hierarchy, instruction format, CPU datapath, control signals, pipeline timing, bus, I/O, DMA, interrupts, or 408 computer organization review.

Productivity & Notes39

Recall

240

entireio/skills

Use when the user describes a task and wants to know whether something similar has been done before, then turn the closest prior session into a task playbook. Triggers on phrases like "have we done this before", "recall how we did X", "find similar work", "any precedent for", "has anyone solved", "is there a template for", and "how did we do this last time

Productivity & Notes28

Knowledge Organize

341

mingchen666/Reviva

This skill should be used when the user asks to "梳理知识", "整理笔记", "画知识框架", "总结要点", "提炼知识点", "一章总结", "知识清单", "帮我整理这章", "做个知识图谱", "总结重点", "画思维导图", "归纳知识点", "整本书的要点", "帮我提炼考点", or when the user provides textbooks, lecture notes, slides, or documents and wants structured knowledge outlines, key point extraction, chapter summaries, one-page review sheets, or knowledge maps.

Productivity & Notes39

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.