AI Documentation Skill

Core Principles

Document Template

<rules>
1. [Rule]: `good` not `bad`
</rules>

<workflow>
1. {step with placeholder}
2. [Decision] {cond} → {action}
</workflow>

<tools>
tool = gotcha or constraint
</tools>

Writing Rules

Structure:    BAD "keep commits clear" → GOOD `{scope}: {msg}`
Positive:     BAD "Don't cd" → GOOD "Stay at repo root"
Concrete:     BAD "reasonably sized" → GOOD "~100 lines"
Observable:   BAD "mentally verify" → GOOD "output: Task, Constraints, Verify"
Decision:     [Decision] simple → exec | complex → breakdown

Followable Workflows

AI docs should include step-by-step workflows AI can mechanically follow.

• Numbered steps, single action each
• [Decision] {cond} → {action} for branches
• {placeholder} for fill-ins

example:

<workflow>
## Adding a NixOS Module
1. Create `modules/{home|nixos}/{name}/default.nix`
2. Add option: `my.{name}.enable = lib.mkEnableOption "{name}";`
3. [Decision] multiple configs → use collectFiles | single → inline
4. Import in parent default.nix
5. Verify: `nix flake check`
</workflow>

Anti-pattern: "Create appropriate module structure based on your judgment"

Content & Length

Include: conventions, constraints, decision templates, tool gotchas Exclude: generic best practices, tool docs, code explanations

Checklist

1. XML tags? 2. {placeholders}? 3. Positive framing? 4. [Decision] markers? 5. Examples? 6. Under limit?