skills.rest
anilveersingh1308
anilveersingh1308COMMUNITY
Explore all skills by this author →
GitHub

skill-creator

Convert user intent into validated SKILL.md files with an evaluation loop.

Updated May 19, 2026
Search Tags:#skill creation#benchmarking#iterative improvement#instruction design#evals#LLM tooling#trigger optimization
One-click install
npx skills add https://github.com/anilveersingh1308/copilot-skills --skill skill-creator-anilveersingh1308
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/anilveersingh1308/copilot-skills/tree/main/.github/skills/skill-creator
Command: npx skills add https://github.com/anilveersingh1308/copilot-skills --skill skill-creator-anilveersingh1308

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude, python3, pyyaml, lsof, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the challenge of creating reliable GitHub Copilot skills by guiding you through drafting instructions, running evaluation prompts, and iterating with measurable results until triggering and behavior are accurate.

Core Features & Use Cases

  • Skill drafting from intent: Turn a user goal into a structured SKILL.md with clear “when to trigger” description and actionable body instructions.
  • Evaluation-driven iteration loop: Generate realistic test prompts, run them, compare with a baseline, and grade outcomes to quantify improvement.
  • Trigger description optimization: Use eval sets to iteratively refine the SKILL.md frontmatter description so Claude invokes the skill at the right times.

Quick Start

Use the skill when you want to create a new skill for “do X”, or when you already have a draft and want to measure and improve triggering accuracy.

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 test a SKILL.md file for GitHub Copilot?▼

To create a SKILL.md file, you draft structured instructions from user intent, generate evaluation prompts, run parallel test executions, and grade outcomes to iteratively improve behavior and triggering accuracy.

What is trigger description optimization for Claude skills?▼

Trigger description optimization iteratively refines the SKILL.md frontmatter description using evaluation sets, ensuring Claude invokes the skill at the right times based on measurable benchmarking results.

How do I benchmark LLM tooling to measure skill behavior improvements?▼

You benchmark LLM tooling by generating realistic test prompts, running them against a baseline, and grading outcomes with aggregated evidence to quantify iterative improvements in skill behavior and trigger reliability.

Do I need Python and Claude to run iterative improvement evals?▼

Yes, you need python3, pyyaml, and Claude to execute the evaluation loop, process YAML configurations, and grade the parallel test executions required for iterative improvement of skills.

What is the best way to fix a Copilot skill that does not trigger reliably?▼

The best way to fix unreliable triggering is to use an evaluation-driven iteration loop that tests realistic prompts, grades outcomes against a baseline, and optimizes the description within size constraints.

Related Skills

Explore More Software Engineering Skills→
Fudan-SMI-labFudan-SMI-lab
39

torch-npu-pyyaml-preinstall

Preinstall PyYAML before torch-npu to prevent transitive dependency failures.

Official
Intermediate
niduran-orionniduran-orion

skill-creator

Create, evaluate, and refine Claude skills with SKILL.md and trigger evaluations.

Community
Advanced
NodeJSmithNodeJSmith
1

mine.skill-eval

Automate evaluation and comparison of AI skill variants via structured grading and statistical analysis.

Community
Advanced
LudwigAJLudwigAJ

prompt-engineering-expert

Refine vague prompts into clear instructions for AI agents.

Community
Advanced