chain-of-density
由 killerapp 提供
PDF & Documents简介
Iteratively densify text summaries using Chain-of-Density technique.
描述
该技能的功能
Chain-of-Density (CoD) is an iterative summarization method from a 2023 research paper. It compresses text through 5 passes, each identifying missing entities from the source and injecting them into the summary while holding word count constant. The result is a fixed-length summary that grows progressively more specific with each iteration.
Unlike one-shot summarization, CoD forces entity accumulation across iterations, so the final summary contains more named specifics at the same length rather than generic paraphrase.
何时使用
- Condensing verbose API documentation into a fixed-length reference
- Compressing long requirements documents for executive review
- Summarizing research papers while preserving key terminology
- Reducing overlong agent skill files to meet length limits
- Creating dense briefings from detailed incident reports
示例工作流
User asks: Summarize this 600-word architecture document in 80 words
- 1
Pass source text to cod-iteration agent as iteration 1 to produce a sparse base summary
- 2
Parse the Missing_Entities line and Denser_Summary from the response
- 3
Pass both the previous summary and original source to cod-iteration for iterations 2 through 5
- 4
Track accumulated entities across all iterations
- 5
Return the final dense summary and optionally the full iteration history
An 80-word summary containing 9+ specific entities from the source, with optional YAML history showing entity accumulation per pass
安装
clawhub install killerapp/chain-of-density运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。