mmaideveloper/aiarchitecttoolkit / skills/generate-adr
generate-adr
VerifiedCreate, update, review, reject, deprecate, or supersede source-backed Architecture Decision Records (ADRs), compare viable options, and connect decisions to use cases, ADDs, C4 views, risks, compliance evidence, and implementation. Use for any significant architecture choice or ADR reference; use the separate conformance-review skill when comparing code with accepted decisions.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.1 KB |
| agents/openai.yaml | config | 217 B |
| assets/adr-template.md | markdown | 1.7 KB |
| references/adr-quality.md | markdown | 640 B |
assets/adr-template.md
View on GitHub# ADR-<NNN>: <Decision outcome>
## Record
- Status: Proposed
- Date: <YYYY-MM-DD>
- Decision owner: <role or Unknown>
- Decision source: <board/ticket/meeting record or Not yet decided>
- Supersedes: <ADR link or None>
- Superseded by: None
- Related artifacts: <UC, ADD, C4, task links>
## Context
<Problem, why a decision is needed now, and evidence-backed current state.>
## Scope and Non-goals
- In scope: <items>
- Out of scope: <items>
## Decision Drivers
| Driver | Priority | Source/confidence |
|---|---|---|
| <driver> | <priority> | <source and Confirmed/etc.> |
## Options Considered
### Option A: <name>
- Description: <viable option>
- Advantages: <items>
- Disadvantages/risks: <items>
- Driver assessment: <assessment>
### Option B: <name>
- Description: <viable option>
- Advantages: <items>
- Disadvantages/risks: <items>
- Driver assessment: <assessment>
## Decision
<Specific selected option and boundaries, or “Not yet decided” while Proposed.>
## Consequences
### Positive
- <consequence>
### Negative and trade-offs
- <consequence>
## Security, Privacy, Safety, and Compliance
- Security/trust impact: <assessment>
- Privacy/data-lifecycle impact: <assessment and applicable framework>
- AI/automation/human-oversight impact: <assessment and applicable framework>
- Clinical/legal-risk impact: <assessment>
- Required review/approval: <source or To obtain>
## Validation and Follow-up
| Action or validation | Owner | Due date | Tracking link |
|---|---|---|---|
| <action> | <owner/Unknown> | <date/Unknown> | <link> |
## Evidence and Uncertainty
| Claim/question | Source | State |
|---|---|---|
| <item> | <source> | <Confirmed/Assumption/To verify/Unknown> |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |