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.
npx skills add product-on-purpose/pm-skills --skill develop-adr -a claude-codeWhat 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-code2Manually: put the files in place
~/.claude/skills/develop-adr/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/develop-adr/
1Skills CLI (Vercel)
npx skills add product-on-purpose/pm-skills --skill develop-adr -a codex2Manually: put the files in place
.agents/skills/develop-adr/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add product-on-purpose/pm-skills --skill develop-adr -a cursor2Manually: put the files in place
.cursor/skills/develop-adr/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install product-on-purpose/pm-skills develop-adr2Manually: put the files in place
.github/skills/develop-adr/SKILL.md1Skills CLI (Vercel)
npx skills add product-on-purpose/pm-skills --skill develop-adr -a gemini-cli2Platform CLI
gemini skills install https://github.com/product-on-purpose/pm-skills --path skills/develop-adrManually: put the files in place
.devin/skills/develop-adr/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add product-on-purpose/pm-skills --skill develop-adr -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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