user-corpus-explorer
CommunityTurn user files into a searchable local reference index.
Education & Research#reference management#document indexing#knowledge extraction#pdf parsing#agent pipeline#math modeling#user corpus
Authorwoodfishhhh
Version1.0.0
Installs0
System Documentation
What problem does it solve?
When you provide your own papers, notes, PDFs, datasets, or examples, it can be hard for a multi-stage agent to reliably find and cite the most relevant material without manually summarizing everything.
Core Features & Use Cases
- Corpus-aware indexing: Recursively scans
external/user-corpus/and builds a local AGENTS.md reference index plus a JSON inventory for downstream planning. - File-type aware extraction: Reads full text for text/markdown, extracts text for DOCX, and performs PDF parsing with fallbacks while limiting very large reads for cost control.
- Safe, pipeline-friendly output: Overwrites
external/user-corpus/AGENTS.mdeach run, does not block the main pipeline on failure, and avoids uploading full documents to external services.
Quick Start
Use user-corpus-explorer near the end of EZ_math_model intake to scan your folder external/user-corpus/ and generate external/user-corpus/AGENTS.md and .corpus_index.json.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: user-corpus-explorer Download link: https://github.com/woodfishhhh/EZ_math_model/archive/main.zip#user-corpus-explorer Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.