plan-tune

Tune per-question sensitivity and developer vibe profiling in gstack prompts.

1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/zhu637882-stack/jiaoyi --skill plan-tune-zhu637882-stack
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan-tune
Source: https://github.com/zhu637882-stack/jiaoyi/tree/main/qoder-config-backup/skills/gstack-plan-tune
Command: npx skills add https://github.com/zhu637882-stack/jiaoyi --skill plan-tune-zhu637882-stack

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plan-tune solves the friction of noisy prompting in gstack by enabling self-tuning of question sensitivity and developer vibe profiling. It allows adjusting per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspecting the dual-track profile (what you declared vs what your behavior suggests), and enabling or disabling question tuning across gstack skills.

Core Features & Use Cases

  • Per-question tuning: identify and apply user preferences to individual prompts to reduce interruption and improve conversational flow.
  • Profile alignment: surface misalignments between declared intents and observed behavior to drive calibration.
  • Proactive suggestions: propose tuning changes when the same questions recur or a user frequently overrides recommendations.
  • Plan-mode integration: treat the skill instructions as executable steps to steer plan-mode interactions and routing hints.

Quick Start

Ask me to tune questions to adjust per-question prompts and align the user profile with observed behavior.

Frequently Asked Questions about plan-tune

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

FAQPage Schema
How do I tune prompt sensitivity for recurring questions in gstack?

Tune prompt sensitivity for recurring questions in gstack by applying per-question preferences like never-ask, always-ask, or ask-only-for-one-way to reduce conversational friction and interruptions.

What is developer vibe profiling and how does it align with gstack prompts?

Developer vibe profiling tracks dual-track data to compare declared intents against observed behavior, driving calibration and intent alignment to optimize gstack prompts across skills.

How do I stop gstack from asking the same questions repeatedly?

Stop gstack from asking the same questions repeatedly by enabling question tuning, which proactively suggests preference changes when it detects recurring prompts or frequent recommendation overrides.

Does gstack question tuning work with telemetry and lake-management features?

Gstack question tuning works with optional telemetry and lake-management features, using collected data to drive intent alignment and ensure safe planning across skill routing.

Can I inspect misalignments between my declared intents and observed behavior?

You can inspect misalignments between declared intents and observed behavior by viewing the dual-track profile, which surfaces discrepancies to drive profile calibration and proactive suggestion accuracy.