Skip to main content
skill CX Codex

develop-adr — Claude Code skill: ADRs in Nygard format

A skill that writes Architecture Decision Records: the context, the choice, and what it costs you later. Useful when the team picks a database, framework or pattern.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add product-on-purpose/pm-skills --skill develop-adr -a claude-code
Open on GitHub

What develop-adr does

The skill turns a technical decision into a document following Michael Nygard's lightweight ADR format. It walks through the parts in order: a number and a short noun-phrase title, status, context, the decision itself, consequences. Decisions are written in active voice, and the consequences section lists what gets easier and what gets harder.

There is a separate subsection for model choices, and it only appears when the decision selects a model or commits the system to one. Then the record covers what is now coupled to that choice — prompts, evaluation sets, output schemas, latency budgets — the operating cost you accept, and the real cost of reversing it. It also names the observation that would reopen the ADR.

The structure comes from references/TEMPLATE.md, with a finished example in references/EXAMPLE.md. Every template section gets filled, alternatives considered and references included. Product and UX decisions belong to develop-design-rationale instead, and pitching a solution to stakeholders is a different job — an ADR records a decision, it does not sell one.

What it helps with

  • document why the team picked one database over another
  • explain to a new hire why the codebase looks the way it does
  • record the reversal cost of committing to a model
  • keep architecture decisions out of UX rationale docs
  • collect the rejected alternatives in one place

Example prompts for the agent

  • Create an ADR for using PostgreSQL for order data
  • Write up the switch to React as an ADR in Nygard format
  • Draft an ADR for our model choice, include coupling and reversal cost

How to install develop-adr

1Skills CLI (Vercel)

npx skills add product-on-purpose/pm-skills --skill develop-adr -a claude-code

2Manually: put the files in place

~/.claude/skills/develop-adr/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/develop-adr/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about develop-adr

How do I install develop-adr in Claude?

Run npx skills add product-on-purpose/pm-skills --skill develop-adr -a claude-code. The skill file lands at ~/.claude/skills/develop-adr/SKILL.md.

What does develop-adr do?

It creates an Architecture Decision Record covering the context of a technical decision, the decision itself and its consequences. The format follows Michael Nygard's lightweight template.

How is it different from develop-design-rationale?

develop-adr handles architecture and technology choices; product and UX decisions go to develop-design-rationale. If you are still checking whether an approach works at all, run develop-spike-summary first.

Source text

SKILL.md · Apache-2.0
---
name: develop-adr
description: Creates an Architecture Decision Record following the Nygard format to document significant technical decisions, their context, and consequences. Use when making technical choices that affect system architecture, technology selection, or development patterns.
license: Apache-2.0
metadata:
  phase: develop
  version: "3.0.0"
  updated: 2026-08-21
  category: specification
  frameworks: [triple-diamond, lean-startup, design-thinking]
  author: product-on-purpose
---
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
# Architecture Decision Record (ADR)

An Architecture Decision Record documents a significant technical decision along with its context and consequences. ADRs capture the "why" behind architectural choices so future team members understand the reasoning - especially important when they question why something was done a particular way. This skill follows Michael Nygard's lightweight ADR format.

## When to Use

- Making significant technical decisions that affect system architecture
- Choosing between technology options (frameworks, databases, services)
- Establishing patterns that future development should follow
- Documenting the rationale for constraints or non-obvious approaches
- Preserving institutional knowledge about past decisions

## When NOT to Use

- The decision is a product or UX design choice, not architecture or technology -> use `develop-design-rationale`
- You are still exploring whether an approach is feasible -> time-box the exploration and record it with `develop-spike-summary` first
- You need to pitch a solution to stakeholders -> use `develop-solution-brief`; an ADR records a decision, it does not sell one
- Nothing is actually being decided (the status quo continues unchanged): an ADR without a decision is noise; wait until there is one

## Instructions

When asked to create an ADR, follow these steps:

1. **Assign a Number and Title**
   ADRs are numbered sequentially (ADR-001, ADR-002, etc.) for easy reference. The title should be a short noun phrase describing the decision, like "Use PostgreSQL for order data" or "Adopt React for frontend."

2. **Set the Status**
   New ADRs start as "Proposed." After team review, they become "Accepted," "Deprecated," or "Superseded by ADR-XXX." Status changes should be tracked.

3. **Describe the Context**
   Explain the circumstances that led to this decision. What problem are you solving? What forces are at play (technical constraints, team expertise, timeline, cost)? This section should help a reader who wasn't there understand why this decision was needed.

4. **State the Decision**
   Clearly articulate what you decided. Use active voice: "We will use..." rather than "It was decided..." Be specific about what is and isn't included in the decision.

5. **Document the Consequences**
   List the outcomes of this decision - positive, negative, and neutral. Good ADRs are honest about trade-offs. What becomes easier? What becomes harder? What new constraints or options does this create?

6. **Record the Model-Choice Consequences** *(only when the decision selects a model or commits the system to one)*
   Skip this step entirely otherwise; it is a subsection inside Consequences, not a seventh heading. A model choice differs from an ordinary dependency choice in one way that matters for an ADR: the thing you evaluated will be replaced, often inside the life of this decision. So record what the choice costs to undo, not just which option won. Name whether you are building, buying, or prompting a general model and what ruled the other two out; what is now coupled to the choice (prompts, evaluation sets, output schemas, latency budgets); the operating cost accepted and the volume at which it stops being acceptable; the real reversal cost given that coupling; and the observation that would reopen this ADR, which is a trigger rather than a review date.

## Output Format

Use the template in `references/TEMPLATE.md` to structure the output. A complete ADR fills every template section: Status; Context; Decision; Consequences; Alternatives Considered; and References.

## Quality Checklist

Before finalizing, verify:

- [ ] Title is a short, descriptive noun phrase
- [ ] Status is clearly indicated (Proposed/Accepted/Deprecated/Superseded)
- [ ] Context explains why this decision was needed
- [ ] Decision is stated clearly in active voice
- [ ] Consequences include both positive and negative outcomes
- [ ] ADR can stand alone without requiring other documents
- [ ] If the decision selects or commits to a model: coupling, operating cost, reversal cost, and the observation that would reopen the decision are all recorded

## Examples

See `references/EXAMPLE.md` for a completed example.

© product-on-purpose · Apache-2.0 · product-on-purpose/pm-skills

Similar skills

Everything for Writing and docs →

From the same set68

deliver-edge-cases Catalogs edge cases, error states, race conditions, and recovery paths for a feature. It maps failure modes during specification or QA test planning. CX Codex +1 873installs discover-competitive-analysis Builds a structured teardown of 3–5 direct and indirect competitors: features, pricing, positioning, a 2x2 map and strategic calls. CX Codex +1 832installs define-problem-statement Builds a problem framing document: who feels the pain, what it costs the business, and which metrics will show success. CX Codex +1 816installs define-hypothesis Turns an assumption about user behavior into a falsifiable statement with success metrics and a validation plan, before you design any experiment. CX Codex +1 806installs deliver-launch-checklist Builds a cross-functional pre-launch checklist: engineering, design, marketing, support, legal, operations. For launches that span several teams. CX Codex +1 786installs define-opportunity-tree Turns a measurable outcome into a tree of customer opportunities, candidate solutions and assumption tests. Useful when feature ideas pile up without structure. CX Codex +1 774installs develop-solution-brief Turns a problem into a one-page brief: proposed approach, key features, trade-offs and risks. Useful before you write the full spec. CX Codex +1 772installs discover-interview-synthesis This skill turns interview notes and transcripts into themes, quotes, insights and recommendations. Useful after a round of user research when the team needs to see what you heard. CX Codex +1 770installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor