bilibili-video-analyzer

Analyzes Bilibili academic/educational videos to extract knowledge points and generate clean-style study notes with screenshots. Use this skill when users pr...

Security Scan

The skill's files and instructions are consistent with its stated purpose (download/transcribe/analyze Bilibili videos and produce notes); there are minor documentation/automation mismatches and an external PyPI dependency you should review before installing.

Purpose & Capability

Name/description match the code and instructions: subtitle parsing, ffmpeg screenshots, LLM-driven analysis, and Markdown report generation. The required tools called in SKILL.md (bili-dl/railgun-bili-tools, ffmpeg, Whisper) are consistent with downloading/transcribing Bilibili videos and generating reports.

Instruction Scope

SKILL.md instructs the agent/user to run bili-dl login/download/transcribe, call ffmpeg for screenshots, and to have an LLM perform analysis. The code implements subtitle parsing, screenshot capture, an LLM prompt builder, and report generation. Minor scope notes: SKILL.md explicitly names 'Claude' as the analyzer, but the included llm_analyzer performs an interactive flow (user pastes LLM JSON output) rather than making an automatic API call — so full automation may require additional API integration and credentials. The workflow asks the user to run bili-dl login which may store local credentials/cookies — expected for a downloader but worth noting.

Install Mechanism

Registry has no automated install spec, but SKILL.md tells users to 'pip install railgun-bili-tools' and to install FFmpeg. Installing a third-party PyPI package is common for this purpose, but 'railgun-bili-tools' is not a widely-known standard package name here — verify package provenance/source on PyPI/GitHub before installing. No downloads from arbitrary URLs appear in the skill code; code uses local subprocess calls to ffmpeg/ffprobe.

Credentials

The skill declares no required env vars or credentials, which aligns with the included code (it uses local files, ffmpeg, and user-driven LLM interaction). However SKILL.md and README reference using 'Claude' and Whisper for transcription/analysis: if you want automated calls to a hosted LLM you will need to supply appropriate API keys (not declared here). Also 'bili-dl login' may require Bilibili account auth stored locally — expected but worth being aware of.

Persistence & Privilege

The skill does not request persistent 'always' privileges and does not modify other skills or global agent configs. It writes generated reports and screenshots to output directories (normal for this functionality).

Assessment

This skill appears coherent for producing study notes from Bilibili videos, but check these before installing/using: 1) Verify the PyPI package 'railgun-bili-tools' (author, code repository, recent versions) — installing unknown packages is a common supply-chain risk. 2) The workflow requires ffmpeg and bilibili downloader login; bili-dl login may store your Bilibili cookies/credentials locally — only proceed if you trust the downloader tool. 3) The SKILL.md names 'Claude' for analysis but the included llm_analyzer is interactive (expects you to paste LLM JSON output); if you want automatic LLM calls you will need to provide API keys and possibly modify code. 4) Review the full analyze_video.py and any code you will run for unexpected network calls or obfuscated behavior before running on sensitive machines. 5) For safety, run initial tests in an isolated environment (container/VM) and inspect generated outputs (reports/screenshots) and any network activity. If you want, I can: (a) fetch and summarize analyze_video.py for additional checks, (b) list what to search for in the PyPI package, or (c) suggest a minimal sandboxed test plan.

Overview

This skill analyzes Bilibili academic and educational videos to generate professional clean-style learning notes (清洁版学习笔记). It automates the complete workflow from video download and transcription to AI-powered content analysis and report generation with key screenshots.

📚 Extended Resources:

• 📖 Best Practices Guide - 全面的最佳实践指南
• ✅ Quality Checklist - 28项质量检查清单
• 📁 References Index - 参考文档导航

When to Use This Skill

Trigger phrases:

• "分析这个B站视频: [link]"
• "帮我总结这个视频的知识点"
• "生成这个视频的学习报告"
• "提取这个视频的关键内容"

---

Installation

Prerequisites

• Python 3.7+
• FFmpeg (for video processing)
• Sufficient disk space (~1-2GB per video analysis)

Install from PyPI

pip install railgun-bili-tools

Verify Installation

bili-dl --version

Install FFmpeg

macOS:

brew install ffmpeg

Ubuntu/Debian:

sudo apt install ffmpeg

Windows: Download from ffmpeg.org and add to PATH

---

Workflow

7-Step Automated Process:

Step 1: Login Check

bili-dl status
# If not logged in: bili-dl login

Step 2: Parse Video Information

Extract metadata (title, uploader, duration) using BilibiliParser

Step 3: Download Video

bili-dl download <video_url> --quality 1080p --output <output_dir>

Step 4: Transcribe Audio

bili-dl transcribe <video_path> --model medium --srt

Step 5: AI Content Analysis ⭐

Claude analyzes the subtitle content and extracts:

• 6-10 核心知识点 (knowledge point cards)
• Each point includes:
  • title (10-15字)
  • core_concept (20-30字核心概念)
  • details (200-400字详细说明,Markdown格式)
  • key_points (3-5个关键要点)
  • timestamp (视频时间戳)

Output JSON Structure:

{
  "summary": "视频总览(100-200字)",
  "knowledge_points": [...],
  "key_screenshots": [
    {"timestamp": 280, "description": "截图描述", "reason": "选择原因"}
  ],
  "knowledge_framework": "知识体系结构",
  "practical_value": "实践价值说明",
  "learning_suggestions": ["学习建议1", "学习建议2", ...]
}

Step 6: Capture Screenshots

# 使用 scripts/screenshot_tool.py
ffmpeg -y -ss <timestamp> -i <video_path> -vframes 1 -q:v 2 <output.jpg>

Step 7: Generate Report

Use scripts/report_generator.py to create clean-style learning notes

Output Format:

• 标题: 《{视频标题}》学习笔记
• 概览: 视频时长 + 知识点数量
• 核心内容: 📌 知识点卡片(核心概念 + 详细说明 + 关键要点 + 配图)
• 全文总结: 核心知识框架 + 实践价值 + 学习建议

Quality Standards

Based on successful case (BV1ms4y1Y76i):

Metric	Standard	Example
知识点数	6-10个	7个
单点字数	200-400字	平均320字
核心概念	20-30字	简洁有力
关键要点	3-5个/点	便于记忆
截图数量	10张	均匀分布
质量评分	≥25/28	优秀标准

📋 Use Quality Checklist for self-assessment

---

Key Features

✅ Content Structure

• Card-based layout (卡片式布局)
• Balanced information density (200-400字/点)
• Clear hierarchy (##/###/####)

✅ Knowledge Extraction

• 4-dimensional model: 现象+原因+方案+案例
• Core concept in one sentence (20-30字)
• 3-5 key points per card

✅ Visual Support

• 10 key screenshots
• 600px uniform width
• Precise timestamp alignment

✅ Summary Framework

• Knowledge structure tree
• Multi-dimensional practical value
• 6 actionable learning suggestions

---

Technical Implementation

Extract Subtitles

from srt_parser import parse_srt_file, get_full_transcript
segments = parse_srt_file(srt_path)
full_text = get_full_transcript(segments, include_timestamps=False)

Batch Screenshots

import subprocess
for ts in timestamps:
    cmd = ["ffmpeg", "-y", "-ss", str(ts), "-i", video_path,
           "-vframes", "1", "-q:v", "2", output_file]
    subprocess.run(cmd)

Safe JSON Output

import json
output_path.write_text(
    json.dumps(analysis, ensure_ascii=False, indent=2),
    encoding='utf-8'
)

---

Resources

Scripts

• scripts/srt_parser.py - Parse SRT subtitle files
• scripts/screenshot_tool.py - Capture video frames at specific timestamps
• scripts/report_generator.py - Generate clean-style learning notes

Reference Docs

• 📖 BEST_PRACTICES.md - 全面的最佳实践指南(535行)
• ✅ QUICK_QUALITY_CHECKLIST.md - 28项质量检查清单
• 📁 references/README.md - 参考文档导航

---

Quick Start Guide

For First-Time Users:

1. Read this SKILL.md to understand the workflow
2. Check BEST_PRACTICES.md sections 1-5
3. Review the example case: reports/2026-02-28/BV1ms4y1Y76i_*/
4. Use Quality Checklist to evaluate your output

For Experienced Users:

1. Generate notes using the skill
2. Quick check with the quality checklist
3. Reference best practices when needed
4. Optimize using technical implementation code

---

Version

Current: v1.1.0 (2026-02-28)

• ✅ Enhanced content generation guidelines
• ✅ Comprehensive best practices documentation
• ✅ 28-item quality checklist
• ✅ Real successful case examples

See CHANGELOG.md for version history.