writing-skills

Validate AI skills using test-driven development and RED/GREEN/REFACTOR cycles.

7|1|Updated Oct 16, 2025
One-click install
npx skills add https://github.com/xloxn69/AgileFlow --skill writing-skills-xloxn69
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/xloxn69/AgileFlow/tree/main/packages/cli/src/core/skills/writing-skills
Command: npx skills add https://github.com/xloxn69/AgileFlow --skill writing-skills-xloxn69

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, test-driven approach to documenting and validating new skills. It ensures consistency, reusability, and quality by requiring explicit frontmatter, well-defined sections, and a cycle of failing tests before the skill is considered complete.

Core Features & Use Cases

  • Template-driven documentation: Enforces a consistent frontmatter and section layout for all skills.
  • TDD-style validation: Encourages writing pressure scenarios and observing agent behavior before deployment.
  • Reusable reference: Produces guidance that helps future Claude instances apply proven techniques across projects.

Quick Start

To get started, duplicate this folder for a new skill, update the frontmatter with the new name and description, fill in the sections as described, and run the TDD workflow: observe failures without the skill, implement the skill, then verify that scenarios pass with the skill active.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I validate AI skills using test-driven development?

Test-driven development for skills means writing pressure-scenario tests first, observing failures without the skill implemented, then building the skill to pass those tests. This RED/GREEN/REFACTOR cycle closes loopholes and ensures your skill meets functional requirements before deployment.

What structure should my skill documentation follow?

Skill documentation requires frontmatter with name and description, a structured SKILL.md with recommended sections, and optional cookbook, prompts, and tools components. This standardized layout ensures consistency, reusability, and Claude Search Optimization readiness across all skills.

Can I use TDD to catch edge cases in skill behavior before deployment?

Yes. Pressure-scenario tests with subagents expose edge cases and unexpected agent behaviors before live deployment. Running these tests during the RED/GREEN/REFACTOR cycle identifies and closes gaps that normal usage might miss.

How do I ensure my skill process documentation is deployment-ready?

Enforce frontmatter with explicit name and description, complete all SKILL.md sections, validate against the template structure, and run your full TDD workflow with subagents. This validation cycle confirms your skill satisfies functional requirements for deployment.

What's the fastest way to document a new skill consistently?

Duplicate the skill template folder, update frontmatter with your name and description, fill in structured sections, then follow the TDD workflow: observe failures without the skill, implement it, verify scenarios pass. Template-driven documentation eliminates inconsistency and rework.

Why should I test skill behavior with subagents before shipping?

Subagent pressure testing reveals how your skill performs under realistic agent reasoning and constraint scenarios. These tests surface behavioral gaps that unit-level checks miss, reducing post-deployment failures and ensuring the skill works as documented.