plan-tune

Tune per-question AskUserQuestion prompts during plan-mode.

Updated May 6, 2026
One-click install
npx skills add https://github.com/stayconnectquick/gstack --skill plan-tune-stayconnectquick
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan-tune
Source: https://github.com/stayconnectquick/gstack/tree/main/plan-tune
Command: npx skills add https://github.com/stayconnectquick/gstack --skill plan-tune-stayconnectquick

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plan-tune reduces question fatigue and prompts fatigue by tuning per-question prompts and developer profiles across gstack skills, enabling smoother interactions during plan-mode.

Core Features & Use Cases

  • Per-question tuning: set never-ask / always-ask / ask-only-for-one-way preferences for each AskUserQuestion invocation used by skills.
  • Dual-track profile inspection: compare declared vs inferred user behavior to adapt prompts and avoid repetitive questions.
  • Proactive prompts and configurability: enable/disable telemetry, lake intro, routing injection, and proactive suggestions to improve workflow.

Quick Start

Run plan-tune to tune questions for your gstack session by answering prompts and adjusting per-question preferences.

Frequently Asked Questions about plan-tune

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

FAQPage Schema
How do I reduce unnecessary AI prompt questions during plan-mode?

To reduce unnecessary AI prompt questions during plan-mode, you can tune per-question preferences using plan-tune. It analyzes declared preferences and observed behavior to adjust which questions fire, minimizing repetitive AskUserQuestion occurrences and smoothing workflow interactions.

What is per-question prompt tuning for developer profiles?

Per-question prompt tuning adjusts which prompts fire by comparing declared user preferences against inferred behavior. This dual-track inspection adapts developer profiles to avoid repetitive questions and reduce prompt fatigue across gstack skill sessions.

Can I configure guardrails and telemetry for AI prompt tuning?

Yes, you can configure guardrails and telemetry for AI prompt tuning. You can enable or disable telemetry, routing injection, lake intro, and proactive suggestions to enforce specific workflow rules and improve overall interaction quality.

How do I set ask-only-for-one-way preferences for AskUserQuestion invocations?

You can set ask-only-for-one-way preferences by running the tuning process and answering configuration prompts. This adjusts each AskUserQuestion invocation used by skills to fire only under specific conditions, reducing unnecessary interruptions.

Why does my AI assistant keep asking repetitive questions in plan-mode?

Your AI assistant keeps asking repetitive questions because per-question prompts lack tuned preferences. By analyzing inferred user behavior and applying dual-track profile inspection, you can adjust prompts to stop repetitive questions and reduce fatigue.