- Home
- Skills
- Product Management
- Foundational Companion
Foundational Companion
Foundational Companion turns a PRD and constraints into a versioned architecture decision record pack and Mermaid diagrams before any product code is written.
$29
Works with the AI Agents you already use
Foundational Companion
Example session with this skill installed
Start from this PRD. Three TypeScript-fluent engineers, a 4-month deadline, about 10k users in year one, no hard real-time, SOC2 later. Produce the architecture ADR pack.
- Read your context and instructions
- Compiled the foundational companion
Proposed ADRs 0000-0010: modular monolith, one repo with vertical slices, hybrid paradigm, PostgreSQL, HTTPS JSON REST and OpenAPI, managed Postgres plus one PaaS service, GitHub Actions trunk-based CI. Mermaid C4 and deployment diagrams. Microservices, Kubernetes, and a second datastore are vetoed.
Connects securely to your tools. The creator never sees your data.
About this skill
Foundational Companion turns a PRD and constraints into a versioned architecture decision record pack and Mermaid diagrams before any product code is written.
It is for founders and small teams starting a new product. The agent runs ten decisions in order: system decomposition, repository layout, architecture patterns, programming paradigm, code patterns, data structures, backend stack, API design with a mandatory security baseline, infrastructure, and CI/CD. Each decision records the choice, the PRD signals, rejected options, assumptions, and a YAGNI veto. Default bets stay small: modular monolith, one repo, hybrid paradigm, PostgreSQL, HTTPS JSON REST and OpenAPI, managed hosting, GitHub Actions. Extra services need a reason from the PRD.
A second skill, Gen AI Companion, runs only after that architecture exists, and only when the product needs models, RAG, agents, tools, or MCP. It writes nine more ADRs and refuses an agent mesh, a separate vector database, or an MCP server unless a named constraint requires it.
The agent writes the ADR pack and diagrams into the product repository. A person accepts or sends them back. It does not implement the product.
Works with agents that load SKILL.md through Agensi, including Cursor, Claude Code, and Copilot.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
Does not implement the product. ADRs stay proposed until a person accepts them. Language and cloud follow the PRD. Confirm current stable versions before locking a stack ADR. The Gen AI pass does not run unless the product needs models, RAG, agents, tools, or MCP.
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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
Requires
Nothing to install.
Permissions
File Scopes
Writes proposed ADRs and Mermaid diagrams into the product repo. Does not copy the skill pack into the repo and does not implement the product.