One-click install
npx skills add https://github.com/rdleclerc/agentic-uber-skills --skill uber-skill-creator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uber-skill-creator
Source: https://github.com/rdleclerc/agentic-uber-skills/tree/main/uber-skill-creator
Command: npx skills add https://github.com/rdleclerc/agentic-uber-skills --skill uber-skill-creator

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill resolves the difficulty of authoring and maintaining portable SKILL.md packages for agent runners by providing a single, eval-driven workflow for creating, updating, migrating, and deprecating Uber-style skills.

Core Features & Use Cases

  • Portable skill authoring: Create and update runtime-neutral SKILL.md instructions for Codex, Claude, and compatible coding agents.
  • Legacy alias migration: Migrate or purge legacy local skill-creator and skill-creator-pro aliases using a safe deprecation-shim pattern.
  • Quality and eval iteration: Use read-only quality evaluation and an eval-driven extension to tune triggers, compare with-skill vs without-skill behavior, and produce evidence-backed HTML review reports.
  • Compression without behavior change: Estimate lossless compression opportunities and preserve router-sensitive trigger phrasing.

Quick Start

Use $uber-skill-creator when you want to create a new portable SKILL.md skill directory for general Uber-family agent workflows.

Frequently Asked Questions about uber-skill-creator

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

FAQPage Schema
How do I create portable SKILL.md packages for agentic coding workflows?

Create portable SKILL.md packages by authoring runtime-neutral skill directories with YAML frontmatter, trigger-focused descriptions, and optional scripts or references for deterministic validation and eval reporting across compatible coding agents.

What is eval-driven skill iteration and how does it improve trigger tuning?

Eval-driven iteration compares with-skill versus without-skill behavior to tune triggers and generate evidence-backed HTML review reports, ensuring stable discovery and safe activation without altering existing router-sensitive trigger phrasing.

Can I use SKILL.md instructions with both Codex and Claude agents?

SKILL.md instructions are runtime-neutral and designed for Codex, Claude, and compatible coding agents, allowing portable workflows while preserving trigger boundaries to ensure stable discovery across different agent runners.

How do I migrate legacy skill aliases safely without breaking existing workflows?

Migrate legacy skill-creator and skill-creator-pro aliases using a safe deprecation-shim pattern that purges or redirects old references while maintaining trigger boundaries for stable discovery and safe activation.

What's the best way to validate SKILL.md skill packages before deployment?

Validate SKILL.md packages using deterministic validation scripts that check YAML frontmatter, trigger-focused descriptions, and quality reporting to ensure portable skill guidance meets agentic coding workflow standards.

Does SKILL.md compression affect trigger boundaries or agent routing behavior?

Lossless compression estimates preserve router-sensitive trigger phrasing and trigger boundaries, ensuring stable discovery and safe activation without causing behavior changes in compatible coding agents.