skill-creator

Installation
Summary

Scaffold new skills with validated directory structure, frontmatter, and progressive disclosure patterns.

  • Generates skill directories with SKILL.md frontmatter, optional scripts/, references/, and assets/ subdirectories based on your needs
  • Enforces lean SKILL.md bodies (under 500 lines) by routing detailed docs to references/ and executable code to scripts/ for context efficiency
  • Provides validation script to catch frontmatter errors, missing fields, and structural issues before skill activation
  • Includes init script with customizable resource directories and example file generation for rapid skill prototyping
SKILL.md

Core Principles

Concise is key. The context window is a shared resource between the system prompt, skills, conversation history, and your reasoning. Every line in a SKILL.md competes with everything else. Only add what you don't already know — don't document tool parameters visible in the system prompt, don't prescribe step-by-step workflows for things you can figure out. Focus on domain knowledge, interpretation guides, decision frameworks, and gotchas.

Progressive disclosure. Skills load in three levels:

  1. Always in context — name, emoji, and description appear in <available_skills> in every conversation. This is how you decide which skill to activate. The description must be a strong trigger.
  2. On activation — the full SKILL.md body is loaded via read_file when you decide the skill is relevant. This is where workflow, guidelines, and decision trees live.
  3. On demand — scripts/, references/, and assets/ are only loaded when explicitly needed. Heavy content goes here, not in the body.

This means: keep the SKILL.md body lean (< 500 lines). Put detailed API docs in references/. Put automation in scripts/. The body should be what you need to start working, not an encyclopedia.

Degrees of freedom. Match instruction specificity to task fragility:

  • High freedom (text guidance) — When multiple approaches are valid. Write natural language explaining WHAT and WHY, not step-by-step HOW. Example: "Check funding rates and social sentiment to gauge market mood."
  • Medium freedom (pseudocode + params) — When a preferred pattern exists but details can vary. Describe the approach with key parameters. Example: "Use RSI with period 14, buy below 30, sell above 70."
  • Low freedom (scripts in scripts/) — When operations are fragile, require exact syntax, or are repetitive boilerplate. Put the code in standalone scripts that get executed, not loaded into context. Example: Chart rendering with exact color codes and API calls.

Default assumption: you are already smart. Only add context you don't already have.

Anatomy of a Skill

Related skills
Installs
5.6K
GitHub Stars
13
First Seen
Mar 13, 2026