create-advisory-brief

Generates a self-contained markdown advisory brief for external AI evaluation of architecture and vendor decisions.

3|Updated Feb 15, 2025
One-click install
npx skills add https://github.com/mark-torres10/ai_tools --skill create-advisory-brief-mark-torres10
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-advisory-brief
Source: https://github.com/mark-torres10/ai_tools/tree/main/skills/create-advisory-brief
Command: npx skills add https://github.com/mark-torres10/ai_tools --skill create-advisory-brief-mark-torres10

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When you want an external AI (like ChatGPT or Claude web) to evaluate architecture, vendor, or stack options, that AI has no access to your codebase. This Skill mines your repository and conversation for decision-relevant facts and distills them into a copy-paste markdown brief the external agent can reason from without asking for code. ## Core Features & Use Cases - Repo Discovery: Systematically extracts shipped vs stub vs planned state, behavioral contracts, constraints, and candidate options from plans, architecture docs, interfaces, and config. - Structured Brief Template: Produces a complete brief with product context, critical distinctions, constraints, options, deliverables, assumptions, and anti-patterns. - Sufficiency Quality Gate: Validates the brief against a checklist ensuring the external agent never needs to ask for repository access. - Use Case: You are deciding between PostgreSQL and SQLite for your app database. The Skill scans your repo, identifies fixed vs open stack choices, and outputs a paste-ready prompt asking the external AI for a comparison matrix, migration plan, and recommendation. ## Quick Start Ask the AI to create an advisory brief comparing database options for external evaluation, and it will mine the repo and output a copy-paste markdown prompt.

Frequently Asked Questions about create-advisory-brief

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

FAQPage Schema
How do I get an external AI to evaluate my architecture options?

Create an advisory brief that distills your repository's decision-relevant facts into prose the external AI can reason from. The brief includes product context, constraints, options, and deliverables so the external agent never needs codebase access.

What should a decision evaluation prompt for ChatGPT include?

It should include product context, current architecture as behavioral description, critical distinctions, technical constraints, options to evaluate, explicit deliverables, assumptions, and anti-patterns. It must open by stating the AI has no codebase access.

When should I use an advisory brief instead of an implementation plan?

Use an advisory brief when comparing options before committing, such as vendors, databases, or patterns. Once the path is chosen, switch to an implementation plan; advisory briefs are for evaluation, not execution.

Can the external AI ask for my code after receiving the brief?

No, a valid brief passes a sufficiency checklist confirming the external agent can proceed without requesting files. Context is described as behavior and contracts, never as file paths or README dumps.

What are the limitations of external AI architecture evaluation?

The external AI only knows what the brief contains, so incomplete repo discovery leads to generic recommendations. The skill mitigates this with a mandatory extraction checklist covering shipped versus stub state and engineering contracts.