adr-generator

SkillDev tools

Formats Architecture Decision Records (ADRs) capturing problem context, considered alternatives, and consequences.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the adr-generator skill

What this skill tells your AI

The instructions your AI receives, as published by codebygarv/ai-skills in skills/documentation/adr-generator/SKILL.md and read by ahel’s review.

Purpose

Document significant architectural choices in a lightweight, immutable Architecture Decision Record (ADR) following the Michael Nygard format to maintain long-term technical context.

When to Use

Committing to a new framework, language, database, or major pattern.
Changing an existing architectural standard or deprecating a system.
Preserving the "why" behind non-obvious engineering decisions for future hires.

What to Analyze

Title & Status: [Number] [Title] (e.g. ADR-0012 Use ClickHouse for Event Analytics) with status (Proposed, Accepted, Superseded, Rejected).
Context: What problem are we solving, and what business/technical constraints force a decision?
Decision: The clear, active-voice statement of what is being adopted.
Alternatives Considered: What other options were evaluated and why were they declined?
Consequences: Positive effects, negative tradeoffs, and operational risks accepted.

Output Format

Standard Markdown ADR template with YAML frontmatter.
Clear, objective, concise sections without fluff.

Avoid

Writing ADRs as post-hoc justifications with no alternatives mentioned.
Omitting negative consequences and maintenance burdens.

Signals

GitHub stars: 26
Forks: 1
Last commit: Aug 2026

Others that do the same job

adr-generator
Skill · a5c-ai

Advanced

Item type: skill
Key: adr-generator-codebygarv
Source: github.com/codebygarv/ai-skills

github.com/codebygarv/ai-skills