skill-creator

Design, test, and optimize Claude skills through an eval-and-improve workflow.

5|1|Updated May 9, 2026

Search Tags:#automation #workflow #evaluation #packaging #skill #claude-code

Ready to run

npx skills add https://github.com/ql-link/LinkRag --skill skill-creator-ql-link

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/ql-link/LinkRag/tree/main/.ai/skills/skill-creator
Command: npx skills add https://github.com/ql-link/LinkRag --skill skill-creator-ql-link

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates the end-to-end lifecycle of building, evaluating, and refining Claude skills, empowering teams to move from concept to measurable performance with structured feedback loops.

Core Features & Use Cases

End-to-end Skill Lifecycle: Draft, test, evaluate, and iteratively improve skills from scratch or by enhancing existing ones.
Evaluation & Benchmarking: Run standardized evals, aggregate results, generate reports, and compare configurations (with/without skill, or baselines) to drive improvements.
Description Optimization: Use an improvement loop to refine triggering descriptions and reduce under- or over-triggering.
Packaging & Validation: Validate skills and package them into deployable bundles for distribution and reuse across projects.

Quick Start

Provide an initial SKILL.md, then kick off the evaluation loop to test and refine it.

Frequently Asked Questions about skill-creator

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

FAQPage Schema

How do I automate the end-to-end lifecycle of building and evaluating Claude skills?▼

You can automate the lifecycle of building and evaluating Claude skills by orchestrating prompts, train/test splits, and benchmarking through an integrated eval-and-improve workflow. This process moves concepts to measurable performance with structured feedback loops.

What is the best way to optimize triggering descriptions and reduce over-triggering in Claude skills?▼

The best way to optimize triggering descriptions and reduce over-triggering is to use a description improvement loop. This refines triggers by running standardized evaluations, aggregating results, and generating reports to drive iterative improvements.

How do I package validated Claude skills into distributable bundles for reuse?▼

You package validated Claude skills into distributable bundles by using the included tooling for packaging and validation. This produces deployable skill bundles that can be distributed and reused across multiple projects.

Does the skill evaluation workflow support train and test splits for benchmarking?▼

Yes, the skill evaluation workflow supports train and test splits for benchmarking. It orchestrates these splits alongside standardized evaluations to compare configurations, such as baselines versus active skills, and generate performance reports.

Can I use pyyaml to configure the evaluation and improvement workflow for Claude skills?▼

You can use pyyaml to configure the evaluation and improvement workflow, as it is a required dependency. It supports the underlying scripts that orchestrate prompts, benchmarking, and description optimization for your skills.

Why should I use an integrated workflow for skill development instead of manual testing?▼

An integrated workflow for skill development automates end-to-end lifecycle management from drafting to refinement, providing structured feedback loops and standardized benchmarking. This approach ensures robust, trigger-friendly skills compared to manual testing.