Communitygithub.com

lzcjsyr/Book2Video

将中短篇专业报告、公司财报、券商研报、招股书、宏观经济分析及含有较多表格和数据的PDF文档,转化为高品质、数据精准的中文视频号/抖音口播解说稿。只要用户提到“研报”、“财报”、“商业分析报告”或需要“解读数据”、“把报告/PDF做成短视频”,务必使用此 Skill。

Book2Video 是什么?

Book2Video is a Claude Code agent skill that 将中短篇专业报告、公司财报、券商研报、招股书、宏观经济分析及含有较多表格和数据的PDF文档,转化为高品质、数据精准的中文视频号/抖音口播解说稿。只要用户提到“研报”、“财报”、“商业分析报告”或需要“解读数据”、“把报告/PDF做成短视频”,务必使用此 Skill。.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/lzcjsyr/Book2Video/tree/HEAD/skills/step1/report-video-script

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Data-Intensive Report Voiceover Script Generation Strategy

This is a skill designed specifically for medium-length professional reports, corporate financial statements, broker research reports, industry white papers, and other data-intensive materials. It transforms complex data and tables into hardcore explanatory videos that ordinary people can understand and find valuable.

This Skill is a thin entry point, breaking down report processing into several independently maintainable modules:

  • reading-and-extraction.md: High-precision text/table extraction (combining local extraction / external preprocessing), data cross-reference table initialization, and windowed reading.
  • writing-standard.md: The opening of research report scripts, logical reasoning, standards for making data conversational, and the final JSON output contract.
  • revision-workflow.md: v1 draft, v2 data verification draft, final draft, and the revision audit diff process.

Body Length Configuration

This is the sole source of truth for the body length of the final draft in this Skill. No other Reference may explicitly write specific word counts; they can only cite this section.

draft_min_chars: 1000
final_target_chars: 1200
  • _draft_v1.txt must reach draft_min_chars before saving.
  • All subsequent body drafts must not fall below draft_min_chars in principle.
  • The target length for the content in the final raw JSON is based on final_target_chars; total_length records the actual character count of content.

Main Workflow

Do not output directly in one round. Follow the steps below to ensure data authenticity and script dissemination power:

  1. Extraction and Reading: First read reading-and-extraction.md. Use a local extraction tool (e.g., PyMuPDF/fitz) to parse the PDF or directly read a pre-converted Markdown report. Divide into Bash reading windows and read 100% of the content. Establish a data cross-reference table for later verification.
  2. Determine the Logical Entry Point: Silently extract the core question of the report (e.g., industry crisis, company growth bottleneck, macro anomaly), extract the report's core explanatory framework, and bind a benefit entry point highly relevant to the audience (e.g., What does this data mean for ordinary people?).
  3. Write the First Draft: Read writing-standard.md and write _draft_v1.txt reaching draft_min_chars, focusing on "translating" cold data into spoken language and logical causality.
  4. Structure and Data Verification Revision: Read revision-workflow.md. After the second draft _draft_v2_structure.txt is determined, directly save it as a preliminary _draft_final.txt. Extract all data from it and generate a ledger _data_check_ledger.json (initially set to unchecked). Then cross-reference with the original text and perform localized corrections/deletions directly on _draft_final.txt (update status to verified/abandon/corrected). Once all data verifications are complete (no unchecked), finalize _draft_final.txt and record the diff audit in _revision_audit.json.
  5. Package and Output JSON: Generate the final JSON according to the final JSON output contract in writing-standard.md.

Self-Check Requirements

Before submitting the final JSON, silently confirm:

  • The data cross-reference table has been fully established, and every percentage, monetary amount, ratio, and other numbers appearing in the manuscript have an exact source in the cross-reference table.
  • All entries in the data verification ledger _data_check_ledger.json have their status updated (none unchecked), completing the data loop.
  • The opening provides a sharp question or core conflict within 100 characters, along with a benefit promise that matters to the audience.
  • There is a logical progression about every 250 characters, the writing is conversational, and AI summary phrases like "the book mentions" or "as can be seen from the figure above" are removed.
  • The revision process is complete, and each round of modifications has clear before/after records in _revision_audit.json.

Individual skills in this repo

This repo contains 6 individual skills — each has its own dedicated page.

lzcjsyr/Book2Video

将 PDF、EPUB、DOCX 等书籍或长文档一次性转成约 4 分钟的中文读书带货短视频口播稿,以情绪共鸣、观看留存和购买欲为核心,直接输出 Book2Video 后续流程可读取的 raw JSON。用户提到读书带货、图书推广、卖书口播、商品卡、走心书单视频、情绪型读书文案或要求生成可直接进入视频流水线的带货稿时使用。

lzcjsyr/Book2Video

将长书、长文档转成中文视频号读书解说稿;先抽取文本并建立可恢复覆盖台账,覆盖自检通过后再按入口定义的正文长度生成初稿、多轮修订和最终 raw JSON。

lzcjsyr/Book2Video

将长书、长文档、PDF、EPUB、读书资料、思想经典、社科著作、商业书或研究型长文转成更有传播感的中文视频号/抖音读书口播稿,并输出项目可用的 raw JSON。只要用户提到“读书解说”“拆书稿”“视频号口播”“把这本书做成短视频”“长文档转视频脚本”“生成标题/封面/金句/raw JSON”,都应使用此 skill。

lzcjsyr/Book2Video

Cody的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于:写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下",只要上下文涉及内容创作和公众号输出,都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容(小红书帖子、推特、朋友圈)或纯标题摘要生成。

lzcjsyr/Book2Video

简化版的文稿生成技能。能够直接读取图书/文档,提取核心论点,生成高品质、口语化的视频号/抖音读书解说文稿并输出标准 JSON 格式。

lzcjsyr/Book2Video

The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see /hyperframes); use this only as the general fallback when none fit.

相关技能