skill-creator

Create, evaluate, and iteratively improve Claude skills with benchmarked test runs.

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill skill-creator-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-creator
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/skill-creator
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill skill-creator-cyrus-pinto

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Writing a skill that reliably triggers and produces good outputs is hard to do by intuition alone. This Skill guides the full lifecycle of skill development: drafting SKILL.md files, running test prompts with and without the skill, grading results against assertions, and optimizing the description for accurate triggering. ## Core Features & Use Cases - Guided Skill Authoring: Interviews the user about intent, trigger contexts, and output formats, then drafts a SKILL.md following progressive disclosure and writing-style best practices. - Evaluation & Benchmarking: Runs test prompts in parallel with-skill and baseline configurations, grades outputs against assertions, and aggregates pass rates, timing, and token usage into benchmark reports with an interactive HTML review viewer. - Description Optimization: Generates realistic should-trigger and should-not-trigger queries, then runs an automated train/test loop to iteratively improve the skill's description for better triggering accuracy. - Use Case: You want a skill that formats weekly sales spreadsheets. This Skill helps you draft it, creates test prompts, runs them with and without the skill, shows you side-by-side results in a browser viewer, and rewrites the skill based on your feedback until it performs well. ## Quick Start Help me create a new skill that converts meeting notes into structured action items, then test it with a few realistic prompts.

Frequently Asked Questions about skill-creator

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

FAQPage Schema
How do I create a new Claude skill from scratch?

Start by defining what the skill should do, when it should trigger, and its expected output format. Then write a SKILL.md with name and description frontmatter, draft 2-3 realistic test prompts, and iterate based on evaluation results.

How do I test whether my skill actually improves outputs?

Run each test prompt twice in parallel: once with the skill and once without as a baseline. Grade both against the same assertions, then aggregate pass rates, timing, and token usage into a benchmark for comparison.

How do I improve a skill description for better triggering?

Generate about 20 realistic queries split between should-trigger and should-not-trigger cases, then run the automated optimization loop. It evaluates description variants on a train split and selects the best by held-out test score.

What makes a good skill description for triggering?

A good description states both what the skill does and specific contexts when to use it, including phrases users actually type. Slightly pushy wording helps because Claude tends to undertrigger skills by default.

When should a skill include test cases and assertions?

Skills with objectively verifiable outputs like file transforms, data extraction, or code generation benefit from assertions. Skills with subjective outputs like writing style are better evaluated through qualitative human review.

Does skill evaluation work on Claude.ai without subagents?

Yes, but with limitations. Without subagents you run test prompts sequentially yourself, skip baseline comparisons and quantitative benchmarking, and present results inline in the conversation instead of the browser viewer.