bili-note

bili-note is a skill for Claude Code, Codex from Rimagination/bili-note. It costs 86 tokens per session (6,324 once invoked), scanned A, original, MIT.

A tool for turning Bilibili videos and posts into readable Markdown notes. Bilibili is a Chinese video and social-content platform; the tool can work with subtitles, article text, images, code, and selected comments.

In plain words
What is it for?
Use it to extract subtitles, transcribe audio when needed, save video or post notes, download post images, summarize multi-part videos, and include relevant comments.
Why use it?
It makes Bilibili material easier to search and reuse, while warning when subtitles do not capture important information shown in slides, code, or other visuals.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rimagination/bili-note/bili-note
Any agent
npx skills add Rimagination/bili-note --skill bili-note
Clone the repo
git clone --depth 1 https://github.com/Rimagination/bili-note

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for bili-note

README.md
[![agentmods](https://agentmods.dev/badge/skills/rimagination/bili-note/bili-note.svg)](https://agentmods.dev/skills/rimagination/bili-note/bili-note)
Your own site
<a href="https://agentmods.dev/skills/rimagination/bili-note/bili-note"><img src="https://agentmods.dev/badge/skills/rimagination/bili-note/bili-note.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.06324
Opus 5 $0.00043 $0.03162
Sonnet 5 $0.00017 $0.01265
Haiku 4.5 $0.00009 $0.00632

Measured 7d ago against content hash c4d80165a0bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bili-note scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl.exe -s http://localhost:3456/targets
SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bili Note

把 B站视频和图文动态变成可检索、可复用的 Markdown 知识笔记。视频优先拿字幕;字幕拿不到时再转写音频;图文优先抓正文、图片和代码块;用户要评论区时抓取评论并过滤无关讨论。

联网或登录态操作必须先使用 web-access

网页 AI 字幕当前只支持 Chrome + web-access 路线:让已登录的 B站页面自己请求字幕接口。不要把 Edge、Playwright 临时浏览器或原生 CDP 端口当成等价替代,除非脚本已经明确支持。

Bili Note 与 DyNote 共享可复用本地资源。默认共享目录是 %USERPROFILE%\.cache\rimagination-notes,Qwen3-ASR 环境默认是 %USERPROFILE%\.cache\rimagination-notes\qwen3-asr-venv。如果任一 skill 已经安装过 Qwen3-ASR,另一个 skill 必须优先复用,不要重复安装。Hugging Face、Whisper 和 faster-whisper 缓存按本机通用缓存复用。

字幕密度与视觉理解

B 站视频优先拿字幕,但字幕/转写不等于完整理解。长视频如果字幕字数明显偏少,可能说明核心信息在画面、PPT、板书、代码演示、屏幕操作或无解说片段中。

  • 归档后必须读取 metadata/note_budget.json。如果 visual_dependency.needs_visual_review=true,不要把稀疏字幕写成完整学习笔记。
  • 这种情况下,先采用更合适的技术:抽取代表性关键帧或截图,再做 OCR 或多模态视觉理解;必要时重新抓网页 AI 字幕或补本地自动语音识别。
  • 如果当前接入的模型或工具不能看图,必须告诉用户:关键帧理解属于高级视觉能力,需要多模态模型、OCR 工具或人工查看;当前只能基于字幕/元数据生成有限笔记并标注覆盖范围。
  • 最终笔记和用户回复要转述 visual_dependency.warnings,并说明是否已经补了视觉证据。

依赖与环境检查

默认路线尽量零第三方 Python 依赖:视频元数据、公开字幕、图文正文、图片清单、评论、归档、证据索引和笔记预算都用标准库完成。网页 AI 字幕和音频转写是增强路线,不是启动门槛。

第一次使用、换机器、用户怀疑依赖不全,或准备使用网页 AI 字幕 / 音频转写兜底时,先运行:

$skill = "$env:USERPROFILE\.codex\skills\bili-note"
$py = "python"
& $py "$skill\scripts\check_environment.py"

根据检查结果选择路线:

  • public_subtitles_comments_archive=OK:优先走默认字幕/图文、评论和归档流程。
  • browser_ai_subtitles=OK:当公开接口只有 ai-zhsubtitle_url 为空时,走 Chrome + web-access 网页 AI 字幕。
  • audio_asr_fallback=OK:只有字幕和网页 AI 字幕都不可得、且用户确实需要完整转写时,才走音频转写。中文或未指定语言优先共享 Qwen3-ASR;明确外语视频优先 Whisper 系后端。
  • 某个增强能力缺失时,只说明该路线暂不可用;不要把它说成整个 skill 不可用。
  • 网页登录态只通过 web-access 已授权的 Chrome 页面使用;不要读取或复制 Cookie/profile,不要强制结束用户浏览器进程。没有 Chrome + web-access 时就跳过网页 AI 字幕并说明覆盖范围。

默认流程

  1. 读清用户要什么:视频或图文链接、是否要评论区、保存路径、是否需要全文材料或只要提炼。
  2. 如果是首次使用、依赖状态不明、字幕抓取失败或用户要求音频转写,先用 check_environment.py 判断当前可走路线。
  3. 优先用 run_bili_note.py 一键完成可自动化部分。它会自动识别 /video/BV.../opus/.../dynamic/... 或纯 opus id。
  4. 如果是图文/动态,走 extract_bilibili_opus.py 路线:抓正文、标题、作者、发布时间、图片、代码块、图文证据索引;用户加 --comments 时抓图文评论。
  5. 如果是视频,优先下载字幕:
    • 普通字幕 URL 可用时,直接用 --download-subtitles
    • 如果普通接口显示 ai-zhsubtitle_url 为空,不要说“没有字幕”;改走“网页 AI 字幕”流程。
    • 如果字幕仍不可得,再按需要下载音频并用本地自动语音识别转写。中文优先 Qwen3-ASR,明确外语优先 Whisper 系后端。
  6. 用户要求评论区时,用 --comments 抓取主评论和子评论;写入笔记时过滤打卡、求资料、广告、闲聊等技术无关内容。
  7. 归档原始材料:把完整字幕或图文正文、图片、完整评论、元数据和 JSONL 索引存到知识库旁边的长期目录。
  8. 写前定标:必须先读取 metadata/note_budget.json,把推荐字数区间、压缩比目标、写作粒度、互动质量倍率、证据块数量和 visual_dependency 作为本次笔记的写作目标。视频按时长、字幕字数、证据块、评论量和互动质量定标;图文按正文长度、图片/代码/证据块、评论量和互动质量定标。
    • 如果 visual_dependency.riskmediumhigh,先补关键帧/OCR/多模态视觉理解,或明确告诉用户当前缺少视觉理解能力,不能写成完整解析。
  9. 按预算写 Markdown:默认写成“学习型笔记”,目标是让人或 Agent 像学完一节课或读完一篇教程一样获得概念、方法、判断标准、实践步骤和自测题;根据预算决定详略,不要把长课和短视频写成差不多字数。来源、覆盖范围和归档路径放到后半部分。正文证据默认用论文式编号 [1][2],不直接堆长证据 ID。
  10. 写后验收:用 score_bili_note.py 校验笔记字数、压缩比、每分钟/每篇笔记密度和证据引用比例。评分只做 QA 和微调,不代替写前定标;太短时优先补“学习收获、知识地图、概念卡、实战流程、坑点、自测题”,不要只堆分P摘要或段落摘要。

Read the full file on GitHub · 346 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 346 lines · 86 tokens per session scan A c4d80165a0bb

Subscribe to this mod's changes

bili-note is a skill published in the GitHub repository Rimagination/bili-note (281 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 6,324 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

larksnap-fetch

把飞书/Lark 文档或普通网页抓取并保存到本地,也能编辑用户有权限的飞书文档,并用已登录浏览器执行一次网页搜索。用户要求下载、导出、抓取、写入飞书文档,或联网搜索资料/参考链接时使用本技能,即使没有提到 larksnap。底层通过技能自带 daemon 桥接已登录的 larksnap 浏览器扩展;arXiv 使用独立脚本。.

AmbroseX/larksnap · 111 tokens

markdown-documents

Use when creating or editing Markdown documents, notes, reports, briefs, drafts, or other editable writing where Markdown should be the primary artifact format.

agent0ai/agent-zero · 33 tokens

bilibili-to-doc

This skill should be used when the user asks to "提取B站视频", "B站视频转文档", "bilibili视频提取", "将B站视频转文字", or provides a bilibili.com video URL and wants to extract its content into a structured Markdown document. Automatically downloads AI subtitles (Chinese) via yt-dlp, parses SRT, and generates a well-formatted…

programmerloverun/bilibili-to-doc · 93 tokens

cv-update-review

Run a confirmation-gated CV update workflow for Word CV documents: set up a reusable profile, scan configured local activity sources plus public evidence such as PubMed through NCBI E-utilities and configured website/RSS feeds, prepare a CV update packet, ask the user to approve completed/public/accepted items, create…

erafat/skills · 126 tokens

install-by2kb

Install, configure, update, or diagnose by2kb for an Agent user. Defaults to local faster-whisper and local Markdown; use a cloud ASR provider only when the user explicitly chooses one.

Charlesmpc/by2kb · 45 tokens

pdf-ocr-to-markdown

OCR PDFs/images into user-facing Markdown with internal JSON/quality artifacts. Preserve originals; never create or modify PDFs. Use bundled scripts, not ad hoc OCR code. Mark visual pages pending unless images are actually inspected.

jseook11/codex-pdf-ocr-to-markdown-skill · 50 tokens