Skip to content

mmaideveloper/aiarchitecttoolkit / skills/generate-add

generate-add

Verified

Create, update, and review a source-backed Architecture Design Document (ADD) from reviewed use cases, applicable Business Decision Records, repository evidence, constraints, quality attributes, C4 views, and ADRs. Use when a change needs an overall technical design, an ADD reference must be revised, or implementation readiness must be assessed without writing code.

FileKindSize
SKILL.mdskill md2.0 KB
agents/openai.yamlconfig233 B
assets/add-template.mdmarkdown3.3 KB
references/add-quality.mdmarkdown687 B

assets/add-template.md

View on GitHub
# ADD-<NNN>: <Architecture design title>

## Record

- Status: Draft
- State described: <Current/Transition/Target/Conceptual>
- Owner: <owner or Unknown>
- Date: <YYYY-MM-DD>
- Related use cases: <UC links>
- Related business decisions: <BDR links or Not applicable with reason>
- Related diagrams: <C4 links or To create>
- Related decisions: <ADR links or None>

## Executive Summary

<Problem, architectural response, intended outcome, and material uncertainty.>

## Scope and Non-goals

### In scope

- <item>

### Non-goals

- <item>

## Architecture Drivers and Constraints

| Driver/constraint | Priority | Source | Confidence |
|---|---|---|---|
| <item> | <Must/Should/Could> | <source> | <Confirmed/etc.> |

## Current-State Context

<Relevant existing behavior, boundaries, pain points, and evidence.>

## Target Architecture

### Responsibilities and boundaries

| Element | Responsibility | Owner | Trust/data boundary | Evidence |
|---|---|---|---|---|
| <element> | <responsibility> | <owner/Unknown> | <boundary> | <source/confidence> |

### Interfaces and integrations

| Source | Destination | Purpose/data | Interface/protocol | Failure behavior |
|---|---|---|---|---|
| <source> | <destination> | <flow> | <known or To verify> | <behavior> |

### Data architecture

| Data category | System of record | Processing purpose | Residency/retention/deletion | Access/audit |
|---|---|---|---|---|
| <category> | <system> | <purpose> | <controls> | <controls> |

### C4 views

- <link and stakeholder question answered>

## Quality Attribute Scenarios

| Attribute | Stimulus and environment | Expected measurable response | Validation |
|---|---|---|---|
| <attribute> | <scenario> | <response> | <test/evidence> |

## Security, Privacy, Safety, and Compliance

- Threat/trust boundaries: <assessment>
- GDPR safeguards: <minimization, lawful basis/consent, rights, retention/deletion>
- EU AI Act safeguards: <classification, transparency, logs, oversight, limitations>
- Clinical/legal-risk safeguards: <human authority, escalation, fail-safe behavior>
- Compliance blockers: <None or list>

## Deployment and Operations

- Environments/topology: <description or diagram link>
- Observability and privacy-safe logging: <signals and exclusions>
- Availability, recovery, and continuity: <targets or To verify>
- Operational ownership and support: <roles or Unknown>

## Delivery, Migration, and Rollback

1. <increment>

- Compatibility/data migration: <plan>
- Rollback trigger and procedure: <plan>

## Decisions and Alternatives

| Decision topic | ADR | Status | Design impact |
|---|---|---|---|
| <topic> | <link/To create> | <Proposed/Accepted> | <impact> |

## Risks, Assumptions, and Open Questions

| Item | Type/state | Impact | Mitigation/owner |
|---|---|---|---|
| <item> | <Risk/Assumption/To verify/Unknown> | <impact> | <action> |

## Verification and Implementation Readiness

- [ ] Reviewed use cases and acceptance criteria are linked.
- [ ] Required C4 views are linked and evidence-backed.
- [ ] Binding decisions are accepted and reconciled.
- [ ] Compliance blockers are closed.
- [ ] Test, migration, observability, rollback, and documentation work are defined.

Readiness: Not ready

## Evidence

| Claim | Source | Confidence |
|---|---|---|
| <claim> | <source> | <Confirmed/etc.> |
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall