What file formats does this skill support?

It provides standardized Markdown templates for summary.md (init research), sources.md (source registry), and research.md (section-specific data).

Can this skill be invoked directly by the user?

No, this skill is designed to be used internally by other dokhak agents like the researcher or writer to ensure systematic file handling.

How does multi-tier resolution work?

It uses a four-step search algorithm that attempts to find files using exact canonical matches first, followed by increasingly flexible patterns to account for variations in naming.

What is the purpose of the Research Storage skill?

It defines a set of conventions and tools for storing research data, allowing AI agents to save, read, and reuse research results to avoid redundant work.

Why is chapter and section normalization important?

Normalization ensures that folders like '1' and '01' are treated consistently, preventing duplicate directories and making the research cache predictable for all tools.

Research Storage

Name: Research Storage
Author: BitYoungjae

byBitYoungjae

•

콘텐츠 관리

Standardizes research data storage and directory conventions to optimize caching and retrieval for AI agents.

소개

The Research Storage skill provides a specialized framework for dokhak agents to manage research data within the Claude Code environment. It implements a strict directory hierarchy and naming convention for chapter and section-based research, ensuring that data collected by researcher agents is easily accessible to writers and designers. By utilizing normalization functions and a sophisticated multi-tier resolution algorithm, the skill prevents redundant web searches and handles legacy naming inconsistencies, creating a reliable cache for high-quality content generation.

주요 기능

Canonical directory structure for organized research caching
Cross-agent compatibility for research-collector, researcher, and writer roles
Automated normalization for chapters, sections, and kebab-case slugs
Multi-tier path resolution to handle naming variations and legacy data
5 GitHub stars
Standardized Markdown templates for summaries, sources, and research logs

사용 사례

Enforcing consistent documentation structures across large-scale technical writing projects
Coordinating data sharing between multiple specialized AI agents in a research pipeline
Building a persistent research cache to reduce redundant web searches and API costs

소개

주요 기능

Canonical directory structure for organized research caching
Cross-agent compatibility for research-collector, researcher, and writer roles
Automated normalization for chapters, sections, and kebab-case slugs
Multi-tier path resolution to handle naming variations and legacy data
5 GitHub stars
Standardized Markdown templates for summaries, sources, and research logs

사용 사례

Enforcing consistent documentation structures across large-scale technical writing projects
Coordinating data sharing between multiple specialized AI agents in a research pipeline
Building a persistent research cache to reduce redundant web searches and API costs