mmaideveloper/aiarchitecttoolkit / skills/generate-adr
generate-adr
UnverifiedCreate, 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.
Generate ADR
Workflow
- Read
AGENTS.md, existing decisions, linked use cases/ADDs/C4 views, supplied evidence, and relevant code. - Determine whether to create, update, review, reject, deprecate, or supersede an ADR.
- For a new record, select the next unused
ADR-NNNunderarchitecture/decisions/and copy assets/adr-template.md. - Apply references/adr-quality.md. Compare viable options using the same decision drivers; do not invent weak alternatives.
- Record the decision, positive and negative consequences, risks, compliance effects, follow-ups, and reciprocal artifact links.
- Use
Proposeduntil an authoritative decision source supports another state. - Treat accepted ADR content as immutable history. Create a new ADR to change the decision and update reciprocal supersession links.
- Save as
architecture/decisions/ADR-NNN-<slug>.mdunless an established layout exists.
Rules
- Keep one primary, independently changeable decision per ADR.
- Phrase the title as the decision outcome.
- Never claim approval without evidence.
- Use
To classifyrather than inferring personal/health-data or AI-risk classification. - Exclude personal/health records, credentials, secrets, connection strings, and sensitive endpoints.
- Update affected target-state C4/ADD artifacts after acceptance; proposed decisions may be shown only as proposals.
- When asked to review code, use
$review-architecture-conformanceand report deviations without rewriting accepted history.
Output
Return path, lifecycle action/status, selected option, unresolved questions, evidence/approval gaps, affected artifacts, and required follow-ups.
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: 464k | Updated | Claude CodeCodex | Verified | 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: 464k | 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: 318k | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |