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.
npx skills add HYYH-code/agent-skills --skill bilibili-notegit clone --depth 1 https://github.com/HYYH-code/agent-skillsWrote 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.
[](https://agentmods.dev/skills/hyyh-code/agent-skills/bilibili-note)<a href="https://agentmods.dev/skills/hyyh-code/agent-skills/bilibili-note"><img src="https://agentmods.dev/badge/skills/hyyh-code/agent-skills/bilibili-note/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hyyh-code/agent-skills/bilibili-note"><img src="https://agentmods.dev/badge/skills/hyyh-code/agent-skills/bilibili-note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02647 |
| Opus 5.5 | $0.00029 | $0.01059 |
| Sonnet 5.5 | $0.00015 | $0.00529 |
| Haiku 4.5 | $0.00007 | $0.00265 |
Grade A, and why
bilibili-note scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilibili Note
默认 Ingest 契约
默认执行完整 ingest，而不是只生成一篇 Markdown。执行前读取 vault 的 WIKI.md、wiki/hot.md、wiki/index.md、wiki/log.md；执行完成前必须验证：
- 人类区 full 中文学习笔记：
个人写作/视频笔记/。 - 内容层原始字幕：
.raw/transcripts/，保持原语言、时间轴和证据属性，不得用翻译覆盖。 - 内容层中文翻译稿：
.raw/transcripts/，与原始字幕独立保存，并标注language: zh-CN、translated_from、confidence和source_url。 - 机器区来源笔记：
wiki/sources/，链接视频、原始字幕、中文译稿和人类区笔记。 - 仅把可复用判断蒸馏到
wiki/concepts/等目录；新概念必须挂入至少一张wiki/maps/。 - 按 vault 规则更新
wiki/index.md、wiki/log.md，必要时更新wiki/hot.md。
证据纪律
- 平台英文字幕若存在，必须原样保存为证据层；不得润色、翻译或重排后冒充原文。
- 中文译稿是派生产物，绝不反向覆盖英文字幕。
- 自动字幕、专名、内部项目名、价格和数字应明确标记
confidence: medium或low。 - 无法取得英文原始字幕时，必须在来源笔记和最终报告中说明证据缺口。
默认落位
个人写作/视频笔记/<slug>-zh.md
.raw/transcripts/<slug>-<date>-en.md
.raw/transcripts/<slug>-<date>-zh.md
wiki/sources/<slug>-<date>.md
概述
将 Bilibili / YouTube 视频转录并生成结构化的 Obsidian 笔记。当前推荐使用 V3 模块化入口：
python bilibili_note_v3.py <url>
V3 不依赖旧版 bilibili_note.py，集成了独立的 video services、transcription、cache 和 note processing 模块，并默认启用转录缓存与临时资源自动清理。
支持两种模式：
- 极简版（显式降级）：快速生成核心内容，适合只想浏览时使用
- 完整版（默认）：包含语义化重写、知识关联、待办事项，并进入完整 ingest 管线
快速开始
极简版笔记（显式降级）
python bilibili_note_v3.py https://www.bilibili.com/video/BV1234567890 --minimal
生成内容：
- 💡 一句话总结
- 🎯 核心要点
- ❓ 回答的问题
- 📊 视频结构
- 🎬 关键时刻
- 📝 原始转录（折叠）
- 🔗 相关资源
完整版笔记（默认）
python bilibili_note_v3.py https://www.bilibili.com/video/BV1234567890
额外包含：
- 🧠 语义化正文（重写后的内容）
- 🗺️ 内容结构图
- 📸 视觉信息索引
- 🔗 知识关联（手动补充）
- 🤔 质疑与思考（手动补充）
- ✅ 待办事项（手动补充）
- 📊 视频元数据（折叠）
转录策略
默认策略（推荐）
自动选择最佳方案：
- 优先尝试视频平台字幕 API（快速、免费）
- 失败后使用 StepFun 云端 ASR（准确、快速）
- 最终回退到本地 Whisper（稳定、离线）
强制本地转录
python bilibili_note_v3.py <url> --local
跳过云端 API，直接使用本地 Whisper 模型（适合隐私需求或无网络环境）。
仅使用字幕
python bilibili_note_v3.py <url> --api-only
只使用视频平台的字幕，如果没有字幕则直接失败（最快速）。
模板系统
可用模板
minimal- 极简版，只保留核心内容full- 完整版，包含所有结构化字段default- 根据模式自动选择（默认 full；--minimal时用 minimal）
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .env.example 655 B
- agents/interface.yaml 1.1 KB
- bilibili_note_v2.py 8.6 KB runs code
- bilibili_note_v3.py 17 KB runs code
- bilibili_note.py 80 KB runs code
- bilibili_note.py.backup 80 KB
- CHANGELOG.md 3.7 KB
- COMMANDS.txt 1.4 KB
- CONCURRENT_TRANSCRIPTION_PLAN.md 5.2 KB
- config.py 3.3 KB runs code
- core/__init__.py 153 B runs code
- core/cache.py 7.6 KB runs code
- core/config.py 9.7 KB runs code
- core/context_manager.py 5.4 KB runs code
- evals/output/README.md 205 B
- examples/core_utils_usage.py 1.4 KB runs code
- examples/note_processing_usage.py 1.1 KB runs code
- examples/video_services_usage.py 1.7 KB runs code
- FIX_PLAN.md 12 KB
- GETTING_STARTED.md 7.1 KB
- ingest.py 6.8 KB runs code
- note_generator.py 3.1 KB runs code
- note_processing/__init__.py 638 B runs code
- note_processing/analyzer.py 11 KB runs code
- note_processing/builder.py 7.5 KB runs code
- note_processing/summarizer.py 14 KB runs code
- OPTIMIZATION_GUIDE.md 1.0 KB
- OPTIMIZATION_SUMMARY.md 7.2 KB
- post_process.py 2.3 KB runs code
- QUICKREF.md 3.8 KB
- README.md 11 KB
- REFACTOR_PLAN.md 20 KB
- REFACTOR_PROGRESS.md 4.3 KB
- references/evidence-and-translation.md 788 B
- references/quality-rubric.md 857 B
- references/semantic-output-contract.md 1.5 KB
- references/vault-ingest-contract.md 1.3 KB
- references/workflow-modes.md 1.1 KB
- reports/artifact-design-profile.md 513 B
- reports/output_quality_scorecard.md 698 B
- reports/output-risk-profile.md 700 B
- reports/performance_v3.json 3.5 KB
- reports/performance_v3.md 2.0 KB
- reports/run_BV1V1oqBiEij_v3_full_concurrent.log 3.9 KB
- reports/run_BV1V1oqBiEij_v3_full.log 1.2 KB
- review_checklist.md 4.4 KB
- REVIEW_STATUS.md 7.5 KB
- template_loader.py 3.3 KB runs code
- templates/default.md 635 B
- templates/full.md 1.2 KB
- templates/minimal.md 635 B
- test_bilibili_note.py 36 KB runs code
- test_note_processing.py 4.2 KB runs code
- test_transcription.py 6.3 KB runs code
- test_v2.py 5.6 KB runs code
- tests/__init__.py 31 B runs code
- tests/performance_v3.py 4.9 KB runs code
- tests/test_bilibili_note_v3.py 9.6 KB runs code
- tests/test_core_utils.py 6.6 KB runs code
- tests/test_video_services.py 6.7 KB runs code
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.
- 1mo ago First seen · 319 lines · 73 tokens per session scan A a4e74a06c7aa
bilibili-note is a skill published in the GitHub repository HYYH-code/agent-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 2,647 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.