跳到正文
TakoAPI
返回技能列表

boof

由 chiefsegundo 提供

Search & Research
585下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Convert PDFs and documents to markdown, index them locally for RAG retrieval, and analyze them token-efficiently.

描述

该技能的功能

Converts PDFs and documents to markdown using local ML (Marker), then indexes them into a semantic search store for retrieval-augmented analysis. Only relevant chunks are sent to the LLM instead of the full document. Supports batch processing and cross-document queries within a single collection.

Sending the full document to an LLM wastes tokens and causes lost-in-the-middle degradation; this retrieves only the semantically relevant excerpts while keeping everything local.

何时使用

  • Extracting key findings from a research paper without loading it in full
  • Searching a grant proposal or NOFO for specific eligibility requirements
  • Summarizing a long technical deck section by section
  • Finding where a contract or policy document mentions a particular clause
  • Comparing methodology or results across multiple academic papers

示例工作流

输入

User asks: Summarize the findings section of this 80-page research PDF

智能体
  1. 1

    Run boof.sh on the PDF to convert it to markdown and index it locally

  2. 2

    Use qmd query to retrieve chunks related to findings and results

  3. 3

    Summarize each retrieved section individually

  4. 4

    Merge section summaries into a consolidated final summary

输出

A structured summary of the paper's findings drawn from indexed excerpts, without loading the full document into context

前置要求

  • Marker (local ML PDF-to-markdown tool, see setup-guide.md)
  • QMD binary (semantic search and indexing tool, see setup-guide.md)

安装

clawhub install chiefsegundo/boof

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。

链接