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 programmerloverun/bilibili-to-doc --skill bilibili-to-docgit clone --depth 1 https://github.com/programmerloverun/bilibili-to-docWrote 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/programmerloverun/bilibili-to-doc/bilibili-to-doc)<a href="https://agentmods.dev/skills/programmerloverun/bilibili-to-doc/bilibili-to-doc"><img src="https://agentmods.dev/badge/skills/programmerloverun/bilibili-to-doc/bilibili-to-doc/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/programmerloverun/bilibili-to-doc/bilibili-to-doc"><img src="https://agentmods.dev/badge/skills/programmerloverun/bilibili-to-doc/bilibili-to-doc.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 | $0.00093 | $0.00892 |
| Opus 5.5 | $0.00037 | $0.00357 |
| Sonnet 5.5 | $0.00019 | $0.00178 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
bilibili-to-doc 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 2mo 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilibili Video to Document (B站视频提取文档)
Overview
Extract Bilibili video content into a structured Markdown document by: (1) downloading AI-generated subtitles via yt-dlp with browser cookies, (2) parsing the SRT subtitle file, (3) reorganizing the transcript into a logical, well-structured document with sections, tables, and code blocks.
When to Use
Trigger this skill when the user:
- Provides a bilibili.com video URL and asks to extract/converter it to a document
- "提取B站视频内容" / "B站视频转文档" / "将视频转成文章"
- "把这个B站视频整理成笔记"
- "generate document from Bilibili video"
Prerequisites
yt-dlpmust be installed:pip3 install yt-dlp- Browser cookies are needed for Bilibili access (Chrome or other browser)
- Python 3.10+ for subtitle processing
Workflow
Step 1: Download Subtitles
Use yt-dlp with browser cookies to download the AI Chinese subtitles:
yt-dlp --cookies-from-browser chrome "<BILIBILI_URL>" \
--write-subs --sub-lang ai-zh \
--skip-download \
-o "/tmp/bilibili_output"
Also get the video title:
yt-dlp --cookies-from-browser chrome "<BILIBILI_URL>" \
--print "%(title)s" --skip-download 2>&1 | tail -1
If chrome browser cookies are not available, try safari, firefox, or edge.
Step 2: Parse SRT and Generate Document
Read the downloaded .ai-zh.srt file, then:
- Strip SRT formatting: Remove sequence numbers, timestamps, empty lines
- Merge consecutive lines: Combine fragmented subtitle lines into complete sentences
- Identify logical sections: The AI should read through the full transcript and identify:
- Topic/theme divisions
- Step-by-step procedures
- Key concepts and definitions
- Configuration examples / code blocks
- Structure the document with proper heading hierarchy
Step 3: Document Structure
Generate a Markdown document following this structure (from reference template):
# {Video Title}
> 来源:B站视频 {BV号} | 主讲:{author}
---
## 一、{Topic Overview}
{Summary of what the video covers}
## 二、{Main Content Sections}
{Organized by logical topic divisions}
## N、总结
{Key takeaways}
What ships with it
1 file 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.
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.
- 2mo ago First seen · 109 lines · 93 tokens per session scan A f2b5e4cddad7
bilibili-to-doc is a skill published in the GitHub repository programmerloverun/bilibili-to-doc (12 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 892 once invoked, about $0.0004 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 2026-08-30.
bilibili-to-doc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bilibili-to-docprogrammerloverun/bilibili-to-doc | Skill | 12 | 4mo ago | MIT | A | 93 | Claude Code, Codex |
| larksnap-fetchAmbroseX/larksnap | Skill | 312 | 15d ago | Apache-2.0 | A | 111 | Claude Code, Codex |
| docs-scraperAmbroseX/larksnap | Skill | 312 | 15d ago | Apache-2.0 | A | 158 | Claude Code, Codex |
| bili-noteRimagination/bili-note | Skill | 349 | 1mo ago | MIT | A | 86 | Codex |
| install-by2kbCharlesmpc/by2kb | Skill | 156 | 18d ago | MIT | A | 37 | Claude Code, Codex |
| youtube-fetcherJimmySadek/youtube-fetcher-to-markdown | Skill | 485 | 2mo ago | MIT | A | 74 | Codex |
| obsidian-climichaeljauk/brain-starter | Skill | 5 | yesterday | MIT | A | 102 | Claude Code |