agentleFS
itmbastawiitmbastawi/product-skill-pack/solution-architect/SKILL.md

solution-architect

Skill7 starsChanged 4 months agoMITView on GitHub

Design the technical architecture, ERD, API design, security model, and tech stack for a product. Use as step 5 of the product pipeline, after UX design is complete. Requires `04-ux-design.md` and all prior outputs as input. Produces architecture documentation ready for implementation planning.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use security-engineer, data-scientist and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • belokonmSkill

    security-engineer

    Expert in infrastructure security, DevSecOps pipelines, and zero-trust architecture design.

    Also in 3 projects that use this

  • belokonmSkill

    data-scientist

    Expert in statistical analysis, predictive modeling, machine learning, and data storytelling to drive business insights.

    Also in 3 projects that use this

  • ClineSkill

    data-analyst

    Act as an interactive data analyst for ClickHouse-backed analytics. Use when the user asks questions about internal data, metrics, dashboards, telemetry, active users, revenue, funnels, trends, distributions, or wants an analyst-style conversation, ad hoc SQL, charts, or a data export against ClickHouse (local or ClickHouse Cloud).

    Also in 3 projects that use this

  • VercelSkill

    technical-writer

    Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read all prior outputs from @output_dir@/: 01-interview-brief.md through 04-ux-design.md

    line 19
  2. Distinctive:

    All entities with attributes

    line 54
  3. Distinctive:

    Keep it pragmatic — don't over-engineer for hypothetical scale

    line 145
  4. Distinctive:

    Consider the team's existing skills (from interview brief)

    line 146
  5. Distinctive:

    Consider cost implications of infrastructure choices

    line 149
  6. Distinctive:

    Ensure security is designed in, not bolted on

    line 150

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Solution Architect — Step 5 of Product Pipeline

Goal

Design a robust, scalable technical architecture that fulfills all product requirements.

Input

Read all prior outputs from @output_dir@/: 01-interview-brief.md through 04-ux-design.md

Output

Save to @output_dir@/05-architecture.md

Deliverables

1. System Architecture

  • High-level architecture diagram (Mermaid)
  • Component breakdown
  • Service boundaries
  • Communication patterns (sync/async)
  • Data flow
graph TB
    Client[Client App] --> API[API Gateway]
    API --> Service1[Service 1]
    API --> Service2[Service 2]
    Service1 --> DB[(Database)]
    Service2 --> Cache[Cache]

2. Tech Stack

For each layer, respect the user's stated technology preferences (captured in the interview brief and tech preferences checkpoint):

  • Frontend
  • Backend
  • Database
  • Infrastructure/Hosting
  • Third-party services
  • Development tools

Justify each choice with 1-2 sentences. If the user had no preference, recommend the most suitable option and explain why.

3. ERD — Entity Relationship Diagram

  • All entities with attributes
  • Relationships (1:1, 1:N, M:N)
  • Primary and foreign keys
  • Indexes for performance
erDiagram
    USER ||--o{ ORDER : places
    USER { string id PK string email }
    ORDER { string id PK string user_id FK }

4. API Design

  • RESTful or GraphQL approach
  • Base URL and versioning
  • Authentication method
  • Rate limiting
  • Key endpoints:
    • Method, path, description
    • Request/response schemas
    • Error codes

5. Security Model

  • Authentication (OAuth2, JWT, API keys, etc.)
  • Authorization (RBAC, ABAC)
  • Data encryption (at rest, in transit)
  • Input validation and sanitization
  • CORS policy
  • Secrets management

6. Non-Functional Architecture

  • Scaling strategy (horizontal/vertical)
  • Caching strategy
  • Database scaling (read replicas, sharding)
  • Monitoring and logging
  • Backup and disaster recovery
  • CI/CD pipeline overview

Output Template

# Architecture: [Project Name]

## System Architecture
[High-level description]
[Architecture diagram]

## Tech Stack
### Frontend
### Backend
### Database
### Infrastructure
### Third-Party Services
### Development Tools

## Data Model
### ERD
[Mermaid diagram]
### Entity Descriptions
[Details for each entity]

## API Design
### Overview
### Authentication
### Endpoints
#### GET /api/v1/resource
#### POST /api/v1/resource
...

## Security
### Authentication
### Authorization
### Data Protection
### Other Security Measures

## Infrastructure
### Deployment
### Scaling
### Monitoring
### Backup/Recovery

## Technical Decisions
[Key decisions and trade-offs]

## Risks and Mitigations
[Technical risks]

Rules

  • Architecture must satisfy ALL functional and non-functional requirements from the PRD
  • Keep it pragmatic — don't over-engineer for hypothetical scale
  • Consider the team's existing skills (from interview brief)
  • Flag any requirement that seems technically infeasible or extremely complex
  • Include specific technology versions where relevant
  • Consider cost implications of infrastructure choices
  • Ensure security is designed in, not bolted on

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.