skill-creator

Skill Creator

A skill for creating new skills and iteratively improving them using vakt's provider-agnostic approach.

Overview

At a high level, the process of creating a skill goes like this:

• Decide what you want the skill to do and roughly how it should do it
• Write a draft of the skill
• Create a few test prompts and run claude-with-access-to-the-skill on them
• Help the user evaluate the results both qualitatively and quantitatively
• Rewrite the skill based on feedback
• Repeat until satisfied
• Use vakt to install and sync the skill to all providers

Communicating with the User

The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. Pay attention to context cues to understand how to phrase your communication.

---

Creating a Skill

Step 1: Capture Intent

Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture.

1. What should this skill enable Claude to do?
2. When should this skill trigger? (what user phrases/contexts)
3. What's the expected output format?
4. Should we set up test cases to verify the skill works?

Step 2: Interview and Research

Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies.

Step 3: Create the Skill Directory

Create the skill in ~/.agents/skills/<skill-name>/:

mkdir -p ~/.agents/skills/<skill-name>

Step 4: Write the SKILL.md

Create ~/.agents/skills/<skill-name>/SKILL.md with:

---
name: skill-name
description: When to trigger, what it does. Be specific about trigger phrases.
---

# Skill Name

[Instructions for the skill...]

Key frontmatter fields:

• name: Skill identifier (required)
• description: When to trigger + what it does (required, this is the primary triggering mechanism)

Skill Writing Guide

Anatomy of a Skill

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter (name, description required)
│   └── Markdown instructions
└── Bundled Resources (optional)
    ├── scripts/    - Executable code for deterministic tasks
    ├── references/ - Docs loaded into context as needed
    └── assets/     - Files used in output (templates, etc.)