skills.rest
Leap0920
Leap0920COMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-creator

Draft SKILL.md content, generate eval queries, and run trigger/evaluation loops.

1|Updated Mar 30, 2026
Search Tags:#skill creation#benchmarking#evaluation#Claude Code#iterative development#SKILL.md#trigger optimization
One-click install
npx skills add https://github.com/Leap0920/Clean-Portfolio --skill skill-creator-leap0920
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/Leap0920/Clean-Portfolio/tree/main/%25USERPROFILE%25/.openclaude/plugins/marketplaces/claude-plugins-official/plugins/skill-creator/skills/skill-creator
Command: npx skills add https://github.com/Leap0920/Clean-Portfolio --skill skill-creator-leap0920

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Skill-creator helps turn an idea for a Claude skill into a working, reliably triggered skill by guiding the full loop: draft the skill, create evaluation cases, run tests, and iteratively improve both behavior and triggering accuracy.

Core Features & Use Cases

  • Skill drafting from intent: Capture what you want the skill to do, when it should trigger, and what output format to expect.
  • Eval-driven iteration: Generate a test set, run trigger/evaluation experiments, and revise the skill based on quantitative and qualitative feedback.
  • Benchmarking and analysis: Aggregate results and review pass-rate and variance patterns to reduce flakiness and improve reliability.
  • Description optimization: Optimize the description frontmatter so Claude invokes the skill more accurately (fewer misses and fewer false triggers).

Quick Start

Tell the skill-creator what you want the new skill to do, when you want it to trigger, and what files or example inputs it should produce outputs for.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I optimize Claude skill triggers to prevent false positives and missed invocations?▼

To optimize Claude skill triggers, iteratively revise the YAML frontmatter description and run evaluation loops. This process analyzes pass-rate and variance patterns to reduce false triggers and ensure accurate skill invocation.

What is the best way to benchmark Claude skill performance using quantitative metrics?▼

The best way to benchmark Claude skill performance is to run packaged scripts that aggregate evaluation results. This analyzes pass-rates and variance to reduce flakiness and provide objective, verifiable success criteria.

How do I create a new Claude skill from an initial intent description?▼

To create a new Claude skill, provide the desired functionality, trigger conditions, and expected output format. The system then iteratively drafts the SKILL.md content and generates realistic eval queries to refine it.

How does eval-driven iterative development improve SKILL.md definitions?▼

Eval-driven iterative development improves SKILL.md definitions by generating a test set, running trigger and evaluation experiments, and applying quantitative feedback. This loop refines both skill behavior and triggering accuracy.

Do I need YAML frontmatter to test Claude skill definitions?▼

Yes, a YAML frontmatter name and description are required to test Claude skill definitions. These fields are essential for benchmarking workflows and optimizing how Claude invokes the skill.

Why does my Claude skill fail to trigger correctly in Claude Code?▼

A Claude skill may fail to trigger correctly due to an unoptimized description frontmatter. By generating test cases and running trigger loops, you can revise the description to prevent missed or false triggers.

Related Skills

Explore More Software Engineering Skills→
coreyjacoreyja
12

skill-writer

Draft SKILL.md frontmatter and structure guidance for Claude Code skills.

Community
Basic
xiaoyuge886xiaoyuge886
196

skill-creator

Draft, evaluate, and optimize AI skills with Python-based benchmarks.

Community
Advanced
dlt-hubdlt-hub
53

create-eval

Scaffold trigger evaluation setups for toolkit skills with test workspaces and queries.

Official
Intermediate
zhbonerzhboner

skill-creator

Draft SKILL.md files and refine them through prompt-based test evaluations.

Community
Advanced