ak-skill-creator

name	ak:skill-creator
description	Create or update Claude skills. Use for new skills, skill scripts, references, packaging, metadata validation, and extending Claude's capabilities.
user-invocable	true
when_to_use	Invoke when creating or refining Claude skills.
category	dev-tools
keywords	["skills","authoring","eval","testing","templates"]
license	Apache-2.0 and MIT; see LICENSE.txt and LICENSE-MIT.txt
argument-hint	[skill-name or description]
metadata	{"author":"agentkit","version":"4.0.0"}

Skill Creator

Create effective Claude skills using progressive disclosure, focused references, and human-in-the-loop iteration.

Core Principles

• Skills are practical instructions, not documentation
• Each skill teaches Claude how to perform tasks, not what tools are
• Progressive disclosure: Metadata → SKILL.md → Bundled resources
• Validation-driven iteration: Create → Validate → Package → Improve from feedback

Quick Reference

Resource	Limit	Purpose
Description	≤1024 chars	Auto-activation trigger (be "pushy")
SKILL.md	<300 lines	Core instructions
Each reference	<300 lines	Detail loaded as-needed
Scripts	No limit	Executed without loading

Skill Structure

New skills MUST be created in the current project scope unless the user explicitly asks for user-scope skill authoring.

skill-name/
├── SKILL.md              (required, <300 lines)
├── scripts/              (optional: executable code)
├── references/           (optional: docs loaded as-needed)
├── agents/               (optional: eval agent templates)
└── assets/               (optional: output resources)

Full anatomy: references/skill-anatomy-and-requirements.md

Creation Workflow

Follow the process in references/skill-creation-workflow.md:

1. Capture Intent — What should skill do? When trigger? What output? (ask_user capability)
2. Research — Activate /ak:docs-seeker, the engineer research skill for best practices
3. Plan — Identify reusable scripts, references, assets
4. Initialize — scripts/init_skill.py <name> --path <dir>
5. Write — Implement resources, write SKILL.md, optimize for benchmarks
6. Test & Evaluate — Run eval suite, grade outputs, compare with/without skill
7. Optimize Description — AI-powered trigger accuracy optimization
8. —