writing-skills

Convert recurring agent patterns into structured oh-my-colab skill units.

2|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/iadr-dev/colab --skill writing-skills-iadr-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/iadr-dev/colab/tree/main/skills/writing-skills
Command: npx skills add https://github.com/iadr-dev/colab --skill writing-skills-iadr-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you convert recurring agent behavior into a reusable oh-my-colab skill while keeping structure, frontmatter quality, and token-efficient instructions consistent.

Core Features & Use Cases

  • Skill Folder Structure Enforcement: Ensures new skills follow the expected skills/{skill-name}/ layout with SKILL.md at the root.
  • Frontmatter + Discovery Quality: Guides writing a searchable SKILL.md description that is reliably load-triggered.
  • 200-Line Discipline: Prevents SKILL.md from growing too large by moving detail into references/ for on-demand loading.
  • Promotion Workflow: Supports a draft-to-promoted process so skills evolve safely from informal templates to official folder skills.

Quick Start

Use the writing-skills skill when RETRO identifies a reusable pattern and ask it to scaffold a new skill in the correct folder format and produce a SKILL.md description that is specific about triggers and outputs.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I create a reusable skill from recurring agent patterns?

To create a reusable skill from recurring agent patterns, you scaffold a new skill folder using a structured format. This process converts identified behaviors into properly structured skill units with discovery metadata for reliable loading and reuse across projects.

How do I keep skill instructions token-efficient when authoring large workflows?

To keep skill instructions token-efficient, you enforce a 200-line limit on the main SKILL.md file. You move detailed instructions and references into a separate directory for on-demand loading, preventing operational bloat.

What is the promotion workflow for scaffolding new skills?

The promotion workflow for scaffolding new skills uses a draft-to-promoted process. This allows skills to evolve safely from informal templates into official folder skills within the directory structure as patterns prove reusable.

When should I not use a large SKILL.md file for skill authoring?

You should not use a large SKILL.md file for skill authoring when details exceed 200 lines. Exceeding this limit reduces token efficiency, so you must offload excess content into references to maintain operational performance.