skill-creator

Design, assemble, and iterate Claude-ready Skills with structured evaluation.

2|1|Updated Mar 18, 2026

Search Tags:#automation #workflow #evaluation #packaging #iteration #skill-creation #prompt-engineering

Ready to run

npx skills add https://github.com/harshitsinghbhandari/domain-expansion --skill skill-creator-harshitsinghbhandari

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/harshitsinghbhandari/domain-expansion/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/harshitsinghbhandari/domain-expansion --skill skill-creator-harshitsinghbhandari

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The Skill Creator helps teams define, build, and iterate Claude-ready skills—from initial drafts to evaluation loops—so learning to craft effective skills becomes fast, repeatable, and measurable.

Core Features & Use Cases

Draft new skills and refine existing ones using a structured process (interview, implement, evaluate, iterate).
Run automated eval loops that test trigger accuracy, stability, and usefulness across varied prompts.
Package and deploy skills as portable artifacts for sharing and reuse.

Quick Start

Start by drafting a new skill using the guidance in SKILL.md, then run the evaluation loop to iterate on its description, and finally package and deploy the skill.

Frequently Asked Questions about skill-creator

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

FAQPage Schema

How do I create and iterate Claude-ready skills with automated evaluation?▼

Skill creation involves drafting a description, running automated eval loops to test trigger accuracy, and iterating through feedback to converge on a robust workflow. This structured process ensures skills are measurable, repeatable, and effectively capture user intents.

What's the best way to package and deploy skills for reuse across teams?▼

Packaging skills as portable artifacts requires consistently structured frontmatter, a SKILL.md body, and optional bundles like scripts, references, and assets. Validating these components ensures the skill is ready for repeatable deployment and sharing across teams.

Do I need pyyaml to scaffold evaluation and run tests on skill descriptions?▼

Yes, pyyaml is required to parse and validate the skill frontmatter during the scaffolding and iteration process. It enables the automated evaluation loops that test trigger accuracy and stability across varied prompts.

How does prompt engineering improve trigger accuracy in skill workflows?▼

Prompt engineering improves trigger accuracy by applying evaluation loops that test the skill description against varied prompts. Iterating through feedback and benchmarks refines the description, ensuring the skill activates reliably and produces useful outputs.

Can I refine an existing skill description instead of building one from scratch?▼

Yes, you can refine existing skills by applying the interview, implement, evaluate, and iterate process. Running automated eval loops on the current description identifies trigger accuracy gaps and tracks improvements through targeted feedback.

When should I bundle scripts and references into my skill packaging?▼

Bundle scripts, references, and assets when the skill workflow requires external logic or supporting data to process user intents. These optional components are validated alongside the frontmatter and SKILL.md to ensure consistent, repeatable deployment.