create-adr

Create Architecture Decision Records in the Cortex Database via PostgREST.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill create-adr-hugoalmeidamoreira
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-adr
Source: https://github.com/HugoAlmeidaMoreira/zeus-agent/tree/main/skills/create-adr
Command: npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill create-adr-hugoalmeidamoreira

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Architecture decisions are often scattered and hard to enforce; this skill provides a standardized workflow to create ADRs directly in the Cortex Database via PostgREST, avoiding local markdown ADRs.

Core Features & Use Cases

  • Standardized ADR templates and workflow for capturing architectural decisions.
  • Direct Cortex integration: ADRs are stored in ontology.adrs and submitted through the PostgREST API.
  • Governance and traceability: Enables versioned decisions and auditable records without manual file management.

Quick Start

Submit a new ADR using the provided template and the Cortex PostgREST API.

Frequently Asked Questions about create-adr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create Architecture Decision Records directly in the Cortex Database?

To create Architecture Decision Records in Cortex, submit a templated payload to the ontology.adrs table via the PostgREST API, using a Python script to ensure safe submission and avoid shell escaping issues.

What is the best way to manage ADR governance without relying on local markdown files?

Managing ADR governance without local markdown files requires storing decisions directly in a centralized database. This skill submits ADRs through the PostgREST API into Cortex, ensuring versioned and auditable architectural records.

How does the PostgREST API handle ID incrementation for new ADRs?

The PostgREST API handles ID incrementation for new ADRs automatically when the templated payload is submitted. This ensures sequential tracking within the ontology.adrs table without manual ID management.

Why should I use a Python script for submitting ADRs via PostgREST?

You should use a Python script or equivalent to submit ADRs via PostgREST to avoid shell escaping issues. It ensures the templated payload is safely transmitted to the Cortex Database without formatting errors.

Can I use standard ADR templates for capturing architectural decisions in Cortex?

Yes, you can use standardized ADR templates for capturing architectural decisions in Cortex. The skill applies these templates to format the payload before submitting it through the PostgREST API to the ontology.adrs table.