skills.rest
greglamb
greglambCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

writing-skills

Create and test SKILL.md files with YAML frontmatter and RED-GREEN-REFACTOR verification.

1|Updated Mar 20, 2026
Search Tags:#workflow design#tdd#documentation#prompt engineering#skill authoring#agent evaluation
One-click install
npx skills add https://github.com/greglamb/macos-name-tag-app --skill writing-skills-greglamb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/greglamb/macos-name-tag-app/tree/main/.claude/skills/writing-skills
Command: npx skills add https://github.com/greglamb/macos-name-tag-app --skill writing-skills-greglamb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents AI skills from becoming vague, undiscoverable, untested, or unreliable by applying test-driven development principles to process documentation.

Core Features & Use Cases

  • Skill Authoring: Create concise, searchable SKILL.md files with valid frontmatter, clear triggers, and efficient instructions.
  • Evaluation-Driven Testing: Design pressure scenarios, establish failure baselines, and verify that agents follow the skill under realistic conditions.
  • Reliability Hardening: Identify rationalizations, close procedural loopholes, improve progressive disclosure, and refine skills before deployment.
  • Use Case: Apply this Skill when creating or editing a reusable workflow guide, especially one that must enforce disciplined behavior despite time pressure or competing priorities.

Quick Start

Use the writing-skills skill to create and test a new SKILL.md for the reusable workflow you want to document.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I create reliable AI skills that agents consistently follow?▼

To create reliable AI skills, document reusable workflow patterns in a SKILL.md file with valid YAML frontmatter, clear activation triggers, and concise instructions. Apply test-driven development principles to establish failure baselines before authoring.

What is evaluation-driven testing for prompt engineering workflows?▼

Evaluation-driven testing for prompt engineering is the process of designing pressure scenarios and establishing failure baselines to verify that agents follow instructions under realistic conditions. It ensures AI skills remain reliable despite competing priorities.

How do I write a SKILL.md file with valid frontmatter and triggers?▼

Writing a SKILL.md file requires adding YAML frontmatter with name and description fields, defining clear activation triggers, and providing concise instructions. Use progressive disclosure to layer guidance efficiently and ensure discoverability.

What's the best way to test agent compliance under pressure before deployment?▼

The best way to test agent compliance under pressure is applying RED-GREEN-REFACTOR verification before deployment. This reliability hardening process identifies rationalizations, closes procedural loopholes, and refines skills under realistic conditions.

Why do my AI skills become vague or undiscoverable during execution?▼

AI skills become vague or undiscoverable when they lack valid YAML frontmatter, clear activation triggers, or concise instructions. Without baseline pressure testing and progressive disclosure, agents fail to follow workflow documentation reliably under competing priorities.

Related Skills

Explore More Software Engineering Skills→
mahoushoujyo-eeemahoushoujyo-eee
15

writing-skills

Create and validate SKILL.md files with YAML frontmatter and evaluation scenarios.

Community
Advanced
ZJUxjyZJUxjy

writing-skills

Enforce Test-Driven Development cycles for creating and modifying AI skills.

Community
Advanced
tannishmangotannishmango

skill-authoring

A structured framework for designing, implementing, and validating Agent Skills.

Community
Intermediate
abcnutsabcnuts
60

mcp-connector-tester

Automate MCP connector testing and generate templated Markdown documentation.

Community
Advanced