gov-model-selection-governance

Assign canonical model profiles and provider mappings to package manifests.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/FernanSuoza/AIDD-project-bootstrap --skill gov-model-selection-governance
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gov-model-selection-governance
Source: https://github.com/FernanSuoza/AIDD-project-bootstrap/tree/main/templates/skills/gov-model-selection-governance
Command: npx skills add https://github.com/FernanSuoza/AIDD-project-bootstrap --skill gov-model-selection-governance

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provide a consistent, auditable way to select, document, and maintain model metadata so agent and skill packages use task-fit models and avoid broken integrations or unsafe model assumptions across providers.

Core Features & Use Cases

  • Canonical profile assignment: Choose one of the five repo-wide profiles (deep-reasoning, balanced-execution, guided-workflow, utility-ops, routing-inherit) to ensure consistent routing and cost/control tradeoffs.
  • Provider-safe mappings: Populate provider_models with preferred and availability-safe defaults, including recommended fields for cursor and vscode-copilot to avoid blank fallbacks.
  • Governance checks & tooling: Commands and audit checks to find missing model_profile entries, orphaned profile names, and to document rationale when non-obvious choices are made.
  • Use case: Onboarding a new skill package and assigning it a balanced-execution profile with mapped fallbacks for Claude Code, Codex, Cursor, Copilot, and ChatGPT.

Quick Start

Run the gov-model-selection-governance skill to assign a canonical model_profile and provider mappings to a package manifest and record the selection rationale.

Frequently Asked Questions about gov-model-selection-governance

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

FAQPage Schema
How do I assign model metadata profiles to new agent skill packages?

Assign model metadata profiles by selecting from five canonical options like deep-reasoning or balanced-execution, then populate the package manifest with provider mappings and selection rationale to ensure consistent routing and auditability.

What is model profile governance for provider mappings?

Model profile governance is the process of documenting preferred and availability-safe model defaults across providers, ensuring agents use task-fit models and avoid broken integrations during catalog maintenance and package onboarding.

How do I add provider-safe fallbacks for Claude Code, Cursor, and Copilot?

Populate the provider_models block in the package manifest with preferred defaults and availability-safe alternatives, including recommended fields for cursor and vscode-copilot to prevent blank fallbacks during integration.

Can I audit package manifests for missing model_profile entries?

Yes, you can audit package manifests using built-in governance commands and audit checks that identify missing model_profile entries, orphaned profile names, and undocumented rationale for non-obvious model selection choices.

When do I need to update model metadata and provider mappings?

Update model metadata and provider mappings during catalog maintenance, new package onboarding, model renames, and provider mapping updates to ensure task-fit model assignment and maintain consistent routing across providers.

What are the limitations of using canonical model profiles for routing?

Limitations include the need to document rationale for non-obvious choices, maintain provider-safe fallbacks to avoid blank integrations, and regularly run governance checks to prevent orphaned profile names and missing entries.