skills.rest
hachej
hachejCOMMUNITY
Explore all skills by this author →
GitHub

writing-great-skills

Design and edit AI agent skills with structured vocabulary and pruning discipline.

45|2|Updated Apr 24, 2026
Search Tags:#documentation#prompt-engineering#ai-agents#skill-design#agent-harness#predictability
One-click install
npx skills add https://github.com/hachej/boring-ui --skill writing-great-skills-hachej
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-great-skills
Source: https://github.com/hachej/boring-ui/tree/main/.agents/skill-references/skill-management/matt-pocock-writing-great-skills
Command: npx skills add https://github.com/hachej/boring-ui --skill writing-great-skills-hachej

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill addresses the challenge of agent unpredictability by providing a structured vocabulary and set of principles to design, refine, and maintain high-quality, deterministic AI skills.

Core Features & Use Cases

  • Predictability Framework: Learn to use leading words and completion criteria to ensure agents follow consistent processes.
  • Information Hierarchy: Implement progressive disclosure to keep skill instructions lean and relevant.
  • Use Case: Use this reference when you are building a new agent skill and need to decide whether to use model-invocation or user-invocation, or when you need to diagnose why an agent is rushing through steps.

Quick Start

Use the writing-great-skills skill to review my current skill definition and suggest improvements for better predictability.

Frequently Asked Questions about writing-great-skills

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

FAQPage Schema
How do I design AI agent skills for predictable behavior?▼

Design predictable AI agent skills by applying a structured vocabulary, using leading words, defining completion criteria, and implementing progressive disclosure to keep instructions lean and relevant.

Why does my AI agent rush through steps during task execution?▼

AI agents rush through steps when lacking clear completion criteria. You can diagnose this by reviewing your skill definition for missing leading words and pruning unnecessary context load.

What is progressive disclosure in prompt engineering for AI agents?▼

Progressive disclosure in prompt engineering is an information hierarchy principle that keeps skill instructions lean by revealing relevant context only when needed, reducing cognitive overhead and agent unpredictability.

When should I use model-invocation versus user-invocation for agent skills?▼

Choose model-invocation versus user-invocation based on whether the AI agent needs autonomous task reliability or explicit user control, using a predictability framework to evaluate instruction clarity and process consistency.

How do I review an existing skill definition to improve agent predictability?▼

Review existing skill definitions by checking for a standardized vocabulary, verifying leading words, ensuring clear completion criteria, and pruning instructions to manage context load and optimize agent harness performance.

Related Skills

Explore More Software Engineering Skills→
otrebuotrebu
4

prompting

Improve AI agent prompts using context engineering and signal-to-noise optimization.

Community
Advanced
mobster570mobster570

agent-development

Generate and validate autonomous agent configurations for Claude Code plugins.

Community
Advanced
nkabbarankabbara

writing-great-skills

Guide skill developers in constructing predictable skills with invocation types and pruning strategies.

Community
Advanced
axiomanticaxiomantic
8

optimizing-instructions

Compress long instruction files while preserving capabilities and safety constraints.

Official
Advanced