skills.rest
mkazimoto
mkazimotoCOMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Orchestrate end-to-end Claude skill creation, evaluation, and packaging into .skill files.

Updated Nov 5, 2025
Search Tags:#workflow#evaluation#iteration#benchmark#skill-creation#description-optimization
One-click install
npx skills add https://github.com/mkazimoto/AppMAUICopilot --skill skill-creator-mkazimoto
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/mkazimoto/AppMAUICopilot/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/mkazimoto/AppMAUICopilot --skill skill-creator-mkazimoto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) components.

What problem does it solve?

The Skill Creator guides users through building, evaluating, and refining Claude skills—from drafting to automated evals and benchmarking—so they can rapidly iterate toward robust capabilities.

Core Features & Use Cases

  • End-to-end skill workflow: capture intent, draft, run evals, iterate, and publish improved SKILL.md.
  • Evaluation and benchmarking orchestration: run trigger evaluations, collect results, and generate reviews with eval-viewer compatibility.
  • Description optimization: optionally improve trigger phrases using eval results and history, via scripts.
  • Packaging and deployment: ensure skills are validated and packaged as .skill files for distribution.

Quick Start

Draft a new skill, run the evaluation loop, review the results in the eval viewer, and iterate until you reach a stable description and strong trigger coverage.

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 on Claude skills with automated evaluation?▼

To create Claude skills, draft your initial SKILL.md and run an evaluation loop to test trigger phrases. Collect benchmarking results, review them in an eval viewer, and iterate on the description until trigger coverage is stable and robust.

What is the end-to-end workflow for building a distributable skill package?▼

The skill building workflow spans discovery, drafting, evaluation, and iteration. You capture intent, run trigger evaluations, optimize descriptions based on eval history, and package the validated output as a distributable .skill file.

Do I need PyYAML installed to run the skill creation and benchmarking scripts?▼

Yes, PyYAML is a required dependency for the skill creator scripts. You need a Python environment with PyYAML installed to orchestrate evaluations, run description optimization, and generate packaged .skill artifacts.

Can I optimize trigger phrases for a skill based on previous evaluation results?▼

Yes, you can optimize trigger phrases using evaluation results and history. The workflow includes optional scripts that analyze past benchmark data to refine and improve trigger coverage for your skill descriptions.

What's the best way to validate a skill before packaging it for distribution?▼

The best way to validate skills before packaging is to run the benchmarking and evaluation orchestration loop. Ensure your trigger evaluations pass and the eval-viewer review is stable, then package the validated SKILL.md into a .skill file.

Related Skills

Explore More Product & Management Skills→
ArrowsHQArrowsHQ
4

arrows-help

List all available Arrows skills and their trigger phrases.

Official
Basic
minhtungominhtungo

skill-creator

Create standardized Claude Skill Units with YAML frontmatter and packaging.

Community
Intermediate
pipixia-labspipixia-labs
38

skill-creator

Guide creation of SKILL.md files and coordinate evals, benchmarks, and iteration.

Official
Advanced
dariopalminiodariopalminio
1

skill-creator

Orchestrate Claude skill creation, evaluation, and packaging into .skill files.

Community
Advanced