prompt-generator

Generate GSD-compliant Claude Code command, skill, and agent files with type-specific validation.

1|Updated May 12, 2026
One-click install
npx skills add https://github.com/tcytan/tecton --skill prompt-generator-tcytan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-generator
Source: https://github.com/tcytan/tecton/tree/main/.claude/skills/prompt-generator
Command: npx skills add https://github.com/tcytan/tecton --skill prompt-generator-tcytan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you create and convert Claude Code prompt files reliably, ensuring they follow GSD-style structure, correct skill/command constraints, and basic quality gates.

Core Features & Use Cases

  • Command, Skill, and Agent authoring: Generate new orchestrators (commands), progressive-loading skills, and identity/domain role agents.
  • Style conversion without content loss: Restyle existing files into GSD conventions while preserving code, tables, and examples.
  • Type-aware validation: Detect artifact type from args/paths and apply skill-specific restrictions (notably: no @ refs and no required_reading).
  • Quality gate workflow: Enforce structural checks before writing the target artifact.

Quick Start

Run prompt-generator to create a new skill file at .claude/skills/my-skill/SKILL.md from your description.

Frequently Asked Questions about prompt-generator

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

FAQPage Schema
How do I generate Claude Code skill files with proper frontmatter and validation?

Generate Claude Code skill files by providing a description to prompt-generator, which produces GSD-compliant SKILL.md files with correct frontmatter, type-specific constraints enforcement, and deterministic quality-gate checks before writing.

Can I convert existing prompt markdown into GSD style without losing content?

Convert existing prompt markdown into GSD style without content loss by using prompt-generator to restyle files while preserving original code, tables, and examples into compliant command, skill, and agent definitions.

What are the constraints when authoring progressive inline skills for Claude Code?

Progressive inline skills enforce specific constraints: no @ references and no required_reading fields are allowed, optional phase loading must use Read("phases/..."), and correct frontmatter fields are required before writing.

Does prompt-generator support creating role-based agent definitions?

Role-based agent definitions are supported by generating identity and domain role agents that follow GSD-style structure, applying type-aware validation to ensure agent files meet deterministic quality-gate checks before output.

How does type-aware validation work for Claude Code prompt artifacts?

Type-aware validation detects artifact type from arguments and paths, then applies skill-specific restrictions like prohibiting @ references and required_reading fields, enforcing structural compliance before writing the target prompt artifact.

When do I need quality-gate checks for Claude Code command generation?

Quality-gate checks are required before writing any generated Claude Code command, skill, or agent file to ensure structural compliance, correct frontmatter fields, and enforcement of type-specific constraints like no @ references.