Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Scanned 5/30/2026
Install to Claude Code
npx -y skills add a5c-ai/babysitter --skill writing-skills --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Writing Skills?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/a5c-ai-writing-skills)More formats (shields.io, HTML) on the badges page.
---
name: writing-skills
description: Use when creating new skills, editing existing skills, or verifying skills work before deployment.
---
# Writing Skills
## Overview
Writing skills IS Test-Driven Development applied to process documentation. Write pressure tests, watch agents fail, write the skill, watch them pass, close loopholes.
**Core principle:** If you did not watch an agent fail without the skill, you do not know if the skill teaches the right thing.
## TDD for Skills
| TDD Concept | Skill Creation |
|-------------|----------------|
| Test case | Pressure scenario with subagent |
| Production code | Skill document (SKILL.md) |
| RED | Agent violates rule without skill |
| GREEN | Agent complies with skill present |
| REFACTOR | Close loopholes |
## Skill Structure
- YAML frontmatter: `name` and `description` only
- Description: "Use when..." (triggering conditions only, never summarize workflow)
- Flat namespace, separate files only for heavy reference or reusable tools
## Tool Use
Meta-skill for creating new skills within the methodology.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...