Skip to content
Back to skills

Writing Skills

ASecurity

Use when creating, editing, or testing agent skills

  • 2 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added September 10, 2026
ai-agentsgotestingdocumentation

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 10, 2026

npx -y skills add LoopyLuci/Skills --skill writing-skills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Writing Skills?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Writing Skills
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/loopyluci-writing-skills/badge)](https://www.skillsdirectory.com/skills/loopyluci-writing-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: writing-skills
description: Use when creating, editing, or testing agent skills
tags: [skills, authoring, testing, documentation]
related_skills: [test-driven-development, skill-discovery, skill-factory-system]
---

# Writing Skills

## Overview

**Writing skills is Test-Driven Development applied to process documentation.** You write test cases (pressure scenarios), watch them fail (baseline behavior), write the skill, watch tests pass, and refactor (close loopholes).

**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.

## TDD Mapping for Skills

| TDD Concept | Skill Creation |
|-------------|----------------|
| Test case | Pressure scenario with subagent |
| Production code | Skill document (SKILL.md) |
| Test fails (RED) | Agent violates rule without skill |
| Test passes (GREEN) | Agent complies with skill present |
| Refactor | Close loopholes while maintaining compliance |

## When to Create a Skill

- Technique wasn't intuitively obvious to you
- You'd reference this again across projects
- Pattern applies broadly (not project-specific)

**Don't create for:** One-off solutions, standard practices well-documented elsewhere, project-specific conventions.

## SKILL.md Structure

```markdown
---
name: skill-name-with-hyphens
description: Use when [specific triggering conditions and symptoms]
---

# Skill Name

## Overview
What is this? Core principle in 1-2 sentences.

## Core Pattern
Before/after code comparison

## Common Pitfalls
What goes wrong + fixes

## Verification Checklist
Actionable items to confirm the skill was followed
```

## Important Notes

**Description = When to Use, NOT What the Skill Does.** The description should only describe triggering conditions. Do NOT summarize the skill's process or workflow in the description.

**Name by what you DO:** Use active voice, verb-first (e.g., `creating-skills` not `skill-creation`).

## Common Pitfalls

| Pitfall | Solution |
|---------|----------|
| Writing skill before testing | Test first, watch it fail, then write the skill |
| Describing workflow in description | Only describe triggering conditions |
| One-off solutions made into skills | Skills must be broadly applicable |
| Skipping real-world testing | Test with real pressure scenarios |
| Vague verification steps | Make checklist items actionable and measurable |

## Verification Checklist

- [ ] Skill addresses a real, recurring problem
- [ ] Description is ≤60 chars, starts with "Use when"
- [ ] Skill tested with pressure scenario before writing
- [ ] Common Pitfalls section included
- [ ] Verification Checklist section included
- [ ] Code examples provided where applicable
- [ ] Related skills cross-referenced

Files in this skill

  • SKILL.md2.7 KB
  • examples/CLAUDE_MD_TESTING.md5.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.