create-skill
Create Skill
Skill File Structure
Directory Layout
Skills are stored as directories containing a SKILL.md file:
skill-name/
├── SKILL.md # Required - main instructions
├── reference.md # Optional - detailed documentation
├── examples.md # Optional - usage examples
└── scripts/ # Optional - utility scripts
├── validate.py
└── helper.sh
Core Authoring Principles
1. Concise is Key
The context window is shared with conversation history, other skills, and requests. Every token competes for space.
Default assumption: The agent is already very smart. Only add context it doesn't already have.
Challenge each piece of information:
- "Does the agent really need this explanation?"
- "Can I assume the agent knows this?"
- "Does this paragraph justify its token cost?"
More from jasonharmongit/jh-skills
doctor
Runs pre-PR formatting, checking and testing.
30organize-elixir-functions
Organize functions in a file or across a branch.
30walkthrough-process
Writes a deep markdown walkthrough for code understanding - how a function, module, or process fits into the system. Also supports branch-change walkthroughs when the user explicitly asks about PR/branch diffs.
24solutionize
Plan-only workflow with a human partner; no implementation while this skill governs the turn
22implement-next-phase
Prepare to implement the next pending todo phase from a solutionize sketch plan (frontmatter todos); implementation only after explicit user approval.
8approach-problem
Produce named strategic options with file/line estimates and pros/cons
7