agentleFS
pitimonpitimon/claude-governance/skills/create-adr/SKILL.md

create-adr

Skill4 starsChanged 6 months agoMITView on GitHub

Create an Architecture Decision Record (ADR) to document a technical decision with governance classification and fitness function.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-plan.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JetBrainsSkill

    create-plan

    Research the codebase and create an implementation plan with architecture notes, design document, and track decomposition. Use when starting a new feature or large change.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use /create-adr to document significant technical decisions — architecture choices, technology selections, API design patterns, or …

    line 15
  2. Distinctive:

    Not needed for trivial implementation choices.

    line 17
  3. Very specific:

    Check docs/adr/ for existing ADRs.

    line 23
  4. Distinctive:

    Ask the user (using AskUserQuestion) for:

    line 31
  5. Very specific:

    Write the ADR file to docs/adr/ADR-NNN-<kebab-case-title>.md using this template:

    line 48

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create Architecture Decision Record

Generate an ADR for the given decision title.

Scope and When to Use

Use /create-adr to document significant technical decisions — architecture choices, technology selections, API design patterns, or governance policy changes. ADRs create an audit trail so future developers understand WHY decisions were made.

Not needed for trivial implementation choices. If unsure whether a decision warrants an ADR, ask: "Would a new team member need to know why we chose this?"

Workflow

1. Determine ADR Number

Check docs/adr/ for existing ADRs. Find the highest numbered ADR and increment by 1. If the directory doesn't exist, create it and start at ADR-001.

ls docs/adr/ADR-*.md 2>/dev/null | sort -t- -k2 -n | tail -1

2. Gather Context

Ask the user (using AskUserQuestion) for:

Question 1: Context "What problem or situation motivated this decision?"

Question 2: Decision "What did you decide? Describe the chosen approach."

Question 3: Governance Loop Options:

  • "Out-of-Loop — AI can implement autonomously (formatting, simple fixes)"
  • "On-the-Loop — AI proposes, human approves (features, API changes)"
  • "In-the-Loop — Human decides, AI assists (architecture, security, breaking changes)"

3. Generate ADR

Write the ADR file to docs/adr/ADR-NNN-<kebab-case-title>.md using this template:

# ADR-NNN: <Title>

## Status

Accepted

## Date

<today's date in YYYY-MM-DD>

## Context

<user's context answer>

## Decision

<user's decision answer>

## Consequences

### Positive

- <infer 2-3 positive consequences from the decision>

### Negative

- <infer 1-2 trade-offs or downsides>

### Risks

- <infer 1-2 risks>

## Governance

- **Decision Loop**: <selected loop>
- **Fitness Function**: <suggest an automated check to verify this decision is upheld>
- **Review Trigger**: <when should this decision be revisited>

4. Confirm

Show the user the generated ADR path and a summary. Suggest they review and adjust the consequences section.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.