progressive-disclosure

Refactors large Skill instructions into linked reference files, preserving meaning and guardrails.

24|22|Updated Dec 14, 2025

Search Tags:#context management #agent skills #progressive disclosure #YAML frontmatter #instruction integrity #documentation refactor #ACP definitions

Ready to run

npx skills add https://github.com/datarobot-oss/datarobot-agent-skills --skill progressive-disclosure-datarobot-oss

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: progressive-disclosure
Source: https://github.com/datarobot-oss/datarobot-agent-skills/tree/main/.skills/progressive-disclosure
Command: npx skills add https://github.com/datarobot-oss/datarobot-agent-skills --skill progressive-disclosure-datarobot-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams refactor overly large skill instructions into smaller, linked reference files so agents can use the right context without hitting context-window limits.

Core Features & Use Cases

Progressive disclosure refactoring: Split verbose sections into directly linked reference documents while preserving the original guidance and meaning.
Safety-first editing guardrails: Prevent rewrites that change intent, remove prerequisites, alter SDK/command guidance, or introduce unrelated repo changes.
Workflow and validation steps: Provide a structured process for inspecting the target skill, moving content minimally, and validating with integration and lint tasks.

Quick Start

Use progressive-disclosure to refactor a target skill by moving detailed sections into directly linked reference files while keeping the SKILL.md entry guidance intact.

Frequently Asked Questions about progressive-disclosure

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

FAQPage Schema

How do I reduce context-window issues when refactoring large agent skills?▼

To reduce context-window issues, progressively disclose large agent skills by splitting verbose instruction sections into smaller, directly linked reference files while preserving the original guidance and meaning.

What is progressive disclosure for YAML frontmatter and ACP definitions?▼

Progressive disclosure for YAML frontmatter and ACP definitions is a refactoring technique that moves detailed skill instructions into linked reference documents, allowing agents to load context dynamically without exceeding token limits.

How do I split DataRobot skill instructions without changing meaning or removing prerequisites?▼

Split DataRobot skill instructions by applying safety-first editing guardrails that move content minimally into reference files, strictly preventing rewrites that alter intent, remove critical prerequisites, or change SDK command guidance.

When do I need to chunk skill instructions into separate reference files?▼

You need to chunk skill instructions into separate reference files when a skill triggers context warnings, suffers from context-window limits, or benefits from progressive disclosure during agent execution.

What are the limitations of progressive disclosure refactoring for skill instructions?▼

Limitations include the strict requirement to keep links one level deep from SKILL.md to references, and the absolute necessity of running validation and lint tasks to ensure no semantic changes occurred during the documentation refactor.

Does progressive disclosure work with any agent skill or only DataRobot skills?▼

Progressive disclosure works with any agent skill that triggers context warnings, needs chunking, or benefits from progressive disclosure during agent execution, although it is specifically designed to refactor DataRobot skill instructions.