plan-tune

Tune AskUserQuestion prompts and per-question preferences within gstack workflows.

Updated May 11, 2026
One-click install
npx skills add https://github.com/wodeh/gstack-kimi --skill plan-tune-wodeh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan-tune
Source: https://github.com/wodeh/gstack-kimi/tree/main/plan-tune
Command: npx skills add https://github.com/wodeh/gstack-kimi --skill plan-tune-wodeh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plan-tune addresses the challenge of inconsistent question pacing and misaligned prompts during AI-assisted planning by providing per-question preferences, profile-aware tuning, and proactive guidance to keep interactions efficient and relevant.

Core Features & Use Cases

  • Per-question preferences (never-ask / always-ask / ask-only-for-one-way) to tailor prompts.
  • Dual-track profile inspection to align declared vs inferred user behavior and expectations.
  • Proactive tuning, model overlays, and telemetry prompts to optimize conversations across plan-mode workflows.

Quick Start

Run plan-tune to begin tuning questions by applying per-question preferences across your gstack plan workflow.

Frequently Asked Questions about plan-tune

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

FAQPage Schema
How do I tune AskUserQuestion prompts for plan-mode workflows?

You can tune AskUserQuestion prompts by applying per-question preferences like never-ask, always-ask, or ask-only-for-one-way to align interactions with your plan-mode workflow.

What is proactive prompt tuning for AI-assisted planning?

Proactive prompt tuning optimizes question pacing and alignment during AI-assisted planning by using profile-aware adjustments and telemetry prompts to keep interactions relevant.

How do I align inferred user behavior with declared profiles when prompting?

Dual-track profile inspection aligns inferred user behavior with declared expectations, enabling dynamic adjustments to prompts and proactive suggestions based on project context.

Can I configure telemetry prompts and model overlays within gstack?

Yes, you can enable or disable telemetry prompts and model overlays within gstack by scoping tuning across various triggers and integrating with project workflow configurations.

Why are my AI planning questions inconsistent or misaligned with user context?

Inconsistent question pacing occurs when prompts lack per-question preferences; applying a structured decision framework and profile-aware tuning resolves these misalignments.

Does plan-tune require external dependencies to optimize question strategies?

No, plan-tune operates without external dependencies, relying entirely on the internal gstack config and project workflow to record decisions for continuous improvement.