- Home
- Skills
- Technical Documentation
- ADR Architect
Works with the AI Agents you already use
ADR Architect
Standardize technical decision-making by generating professional Architecture Decision Records with clear trade-offs.
Free
ADR Architect
Example session with this skill installed
Write an ADR for switching from a self-hosted Redis instance to AWS ElastiCache. We are struggling with maintenance overhead and scaling during peak hours.
- Read your context and instructions
- Compiled the adr architect
I have drafted the Architecture Decision Record for the migration to AWS ElastiCache, focusing on reducing operational overhead and improving scalability.
[Architecture Decision Record]
ADR-005: Migrate Session Management to AWS ElastiCache
- Status: Proposed
- Date: 2023-10-27
- Decision Makers: Engineering Lead, DevOps Team
Context
Our current self-hosted Redis instance on EC2 is becoming a single point of failure and a significant maintenance burden. We are experiencing latency spikes during peak traffic hours, and manual scaling requires downtime. The team needs a managed solution that supports auto-scaling and high availability to meet our 99.9% SLA requirements.
Considered Alternatives
Vertical Scaling of EC2: Increase instance size for the current Redis setup. Rejected because it does not solve the maintenance overhead or provide true high availability.
2.
Redis Enterprise Cloud: A fully managed third-party service. Rejected due to existing AWS ecosystem integration requirements and higher latency compared to VPC-native ElastiCache.
Decision
We will migrate our session and caching layer to AWS ElastiCache for Redis. This decision allows us to utilize AWS Managed Services to handle patching, backups, and automatic failover, directly addressing our current maintenance bottlenecks.
Consequences
Positive: Reduced operational toil for the DevOps team, improved reliability through multi-AZ deployment, and simplified horizontal scaling.
Negative / Trade-offs: Increased monthly cloud spend compared to self-hosting, and potential vendor lock-in to AWS-specific Redis configurations.
Reconsideration Criteria
Revisit this decision if AWS ElastiCache costs exceed $2,000/month or if we decide to move to a multi-cloud architecture that requires a provider-agnostic caching layer.
[Self-Check]
- Context and forcing problem clearly described
- Alternatives (including rejected ones) documented with trade-offs
- Decision stated in clear, active voice
- Consequences and accepted trade-offs outlined
- Reconsideration triggers defined
Next steps
- Review the cost projections for the ElastiCache production cluster.
- Schedule a maintenance window for the initial data migration.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Engineering teams often suffer from architecture drift and tribal knowledge loss. Technical decisions are made in Slack or meetings, leaving future developers to guess why a specific database or framework was chosen.
What it does
- Standardizes technical documentation into professional Architecture Decision Records.
- Forces the evaluation of at least two alternatives to avoid tunnel vision.
- Documents honest trade-offs and technical debt accepted during the process.
- Defines specific triggers for when a decision should be revisited.
Why this beats prompting it yourself
General LLMs often provide vague, non-committal justifications. This skill enforces a strict structure that demands active-voice decisions, objective pros/cons for rejected alternatives, and measurable reconsideration criteria that standard prompts miss.
Use cases
- Choosing between SQL and NoSQL for a new microservice.
- Standardizing on a frontend framework like Next.js vs. Remix.
- Documenting the transition from a monolith to an event-driven architecture.
- Explaining why a specific third-party API or auth provider was selected.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.
Requires the user to provide the initial context and names of decision makers. Does not automatically scan codebases to infer past decisions without manual input.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 2 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected