gsd-config

Configure GSD settings via interactive prompts and flag-routed workflows.

1|Updated May 24, 2026
One-click install
npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill gsd-config-tinner-deinno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd-config
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/gsd/gsd-config
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill gsd-config-tinner-deinno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Setting up and changing GSD runtime behavior often requires remembering many flags, toggles, and profiles; this Skill centralizes that configuration into an interactive, flag-routed workflow.

Core Features & Use Cases

  • Common-case interactive setup: Answers a 5-question prompt to configure typical toggles like model, research, plan_check, verifier, and branching.
  • Advanced power-user tuning: Applies planning, execution, discussion, cross-AI behavior, git/runtime options, and other advanced knobs via a dedicated advanced workflow.
  • Integrations and credentials/config routing: Manages third-party API key configuration and agent-skill injection using an integrations-specific workflow.
  • Model profile switching: Updates the active GSD model profile directly with a non-interactive command, supporting quality|balanced|budget|inherit (or an inheritable custom profile).

Use case example: You want to run the same agent workflow but switch from a balanced model to a budget profile for faster iterations, while keeping your usual common-case settings.

Quick Start

Run gsd-config with the desired mode, for example: "gsd-config --profile budget" to switch the model profile without answering prompts.

Frequently Asked Questions about gsd-config

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

FAQPage Schema
How do I configure runtime settings and model profiles for command line workflows?

Runtime settings and model profiles are configured via interactive prompts or flag-routed workflows, allowing you to toggle models, research, plan checks, and verifiers. You can use command flags to select default, advanced, or integrations workflows for specific configuration tasks.

What's the best way to switch model profiles without answering interactive prompts?

To switch model profiles non-interactively, run the configuration command with the profile flag, such as specifying 'budget' or 'quality'. This executes a safe, PATH-checked SDK operation that directly updates your active model profile without stepping through the interactive setup questions.

How do I manage third-party API keys and agent integrations for workflow routing?

Third-party API keys and agent-skill injection are managed using an integrations-specific workflow. You route to this workflow by selecting the integrations mode, which configures credentials and injects API-dependent review or agent routing into your runtime.

Can I tune advanced execution and planning behaviors for power-user workflows?

Yes, advanced execution and planning behaviors are tuned via a dedicated advanced workflow. This mode applies specific settings for planning, execution, discussion, cross-AI behavior, and git/runtime options beyond the common-case interactive setup.

What are the available model profiles I can select for faster iterations?

Available model profiles include quality, balanced, budget, and inherit. You can also use an inheritable custom profile, allowing you to switch to a budget profile for faster iterations while keeping your usual common-case settings.