skill-improver

Audit agent and skill definitions and produce codified improvement recommendations.

2|Updated Sep 12, 2016
One-click install
npx skills add https://github.com/paulnsorensen/dotfiles --skill skill-improver-paulnsorensen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-improver
Source: https://github.com/paulnsorensen/dotfiles/tree/main/claude/skills/skill-improver
Command: npx skills add https://github.com/paulnsorensen/dotfiles --skill skill-improver-paulnsorensen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Audit and improve agent and skill definitions for better calibration, tool scoping, context management, activation quality, and output format.

Core Features & Use Cases

  • 4-step calibrated confidence scoring for improvement recommendations
  • Guidance on tool scoping, context budgets, and activation optimization
  • Structured prompt and output-format recommendations plus hook guidance

Quick Start

Provide a path to an agent definition (agents/.md) or skill definition (skills//SKILL.md) to audit.

Frequently Asked Questions about skill-improver

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

FAQPage Schema
How do I audit and improve agent skill definitions for better calibration?

Audit agent and skill definitions by providing a path to an agent or SKILL.md file, which generates actionable recommendations and concrete patches for frontmatter, prompt structure, context budgets, and output formatting.

What is tool scoping and how does it optimize skill activation quality?

Tool scoping restricts the allowed tools an agent or skill can access, optimizing activation quality by ensuring the agent only triggers relevant tools and stays within designated context budgets during execution.

How do I calibrate context management settings in SKILL.md frontmatter?

Calibrate context management by auditing SKILL.md frontmatter to evaluate context settings, producing codified recommendations and concrete patches that align context budgets with the skill's operational requirements.

Can I use this skill to generate a formal improvement report for prompt design?

Yes, auditing an agent or skill definition produces a formal Skill Improvement Report containing a 4-step calibrated confidence scoring mechanism and structured recommendations for prompt and output-format improvements.

What's the best way to fix poorly structured output formats in agent definitions?

Audit the agent definition file to receive structured prompt and output-format recommendations, delivering concrete patches to frontmatter and inline prompt design suitable for immediate implementation.

Does this skill work with agents and skills that have no dependencies?

Yes, the skill audits any agent or skill definition provided via a file path, requiring no external dependencies to evaluate triggers, allowed-tools, context settings, and reporting structures.