Expert guidance for creating, writing, building, and refining GSD skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
<essential_principles>
Skills are modular, filesystem-based capabilities that provide domain expertise on demand. This skill teaches how to create effective skills.
All prompting best practices apply. Be clear, be direct, use XML structure. Assume Claude is smart - only add context Claude doesn't have.
When a skill is invoked, Claude reads SKILL.md. Use this guarantee:
skill-name/
├── SKILL.md # Router + principles
├── workflows/ # Step-by-step procedures (FOLLOW)
├── references/ # Domain knowledge (READ)
├── templates/ # Output structures (COPY + FILL)
└── scripts/ # Reusable code (EXECUTE)
SKILL.md asks "what do you want to do?" → routes to workflow → workflow specifies which references to read.
When to use each folder:
No markdown headings (#, ##, ###) in skill body. Use semantic XML tags:
<objective>...</objective>
<process>...</process>
<success_criteria>...</success_criteria>
Keep markdown formatting within content (bold, lists, code blocks).
SKILL.md under 500 lines. Split detailed content into reference files. Load only what's needed for the current workflow. </essential_principles>
Based on the user's message, route directly to the appropriate workflow:
Creating new skills:
create-domain-expertise skill instead (separate skill with batched subagent orchestration)Working with existing skills:
Need help deciding:
If user intent is unclear, ask minimal clarifying questions:
[User] markers or imagined answers).Then proceed directly to the workflow. </routing>
<quick_reference>
Skill directories:
~/.gsd/agent/skills/{skill-name}/.pi/agent/skills/{skill-name}/Simple skill (single file):
---