skills.rest
xiaoyuge886
xiaoyuge886COMMUNITY
Explore all skills by this author →
GitHub

docs-management

Scrape, index, and enrich official Claude documentation with hash-based drift detection.

196|20|Updated Jan 17, 2026
Search Tags:#documentation#indexing#knowledge management#search#claude#scraping
One-click install
npx skills add https://github.com/xiaoyuge886/aigc --skill docs-management-xiaoyuge886
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docs-management
Source: https://github.com/xiaoyuge886/aigc/tree/main/.claude/skills/docs-management
Command: npx skills add https://github.com/xiaoyuge886/aigc --skill docs-management-xiaoyuge886

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, requests, beautifulsoup4, markdownify, spacy, yake, python-docx, pdfplumber, PyPDF2, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of maintaining an accurate, searchable, and token-efficient local cache of official Claude documentation, preventing link rot and reducing reliance on live web searches for routine queries.

Core Features & Use Cases

  • Canonical Storage: Maintains a single source of truth for official documentation with hash-based drift detection.
  • Token-Optimized Extraction: Provides subsection-level retrieval, saving 60-90% of tokens compared to full document loading.
  • Intelligent Discovery: Enables natural language search, keyword-based lookup, and category-based filtering across the entire documentation set.

Quick Start

Use the docs-management skill to search for documentation regarding Claude Code hooks and return the relevant sections.

Frequently Asked Questions about docs-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scrape and index Claude documentation for local search?▼

Token-optimized extraction retrieves subsection-level content from indexed Claude documentation, saving 60-90% of tokens compared to loading full documents and reducing context window consumption.

Does this documentation management tool support natural language search queries?▼

Hash-based drift detection compares content hashes to identify changes in the official Claude documentation, triggering updates to the local cache and preventing link rot or stale information.

Can I extract specific subsections from PDF and DOCX files without loading the entire document?▼

Using pdfplumber, PyPDF2, and python-docx dependencies, the skill parses documents and performs token-efficient subsection extraction, returning only relevant sections to save processing overhead.

What is the best way to maintain a local cache of official documentation and prevent link rot?▼

Yes, keyword extraction is powered by spacy and yake dependencies, which analyze scraped documentation content to enrich metadata and support intelligent discovery across the indexed knowledge base.

Related Skills

Explore More Software Engineering Skills→
pengfitpengfit

huhehaote-price

Extract and transform Huhehaote government website price data via ETL.

Community
Advanced
Renzo-TognellaRenzo-Tognella

Token & Context Optimization

Optimizes token consumption and manages contexts in TheSearch pipeline stages.

Community
Advanced
mattwoodcomattwoodco
3

ai-rag-vectors

Create a pgvector embedding layer for semantic search with recursive text chunking.

Community
Advanced
0xBigBoss0xBigBoss
53

web-fetch

Fetches web pages and converts main content into clean markdown using CSS selectors.

Community
Intermediate