ck:predict

Analyze proposed changes with five expert personas and issue a GO, CAUTION, or STOP verdict.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/DatTran26/KienTruThiHanh --skill ck-predict-dattran26
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:predict
Source: https://github.com/DatTran26/KienTruThiHanh/tree/main/.agents/skills/ck-predict
Command: npx skills add https://github.com/DatTran26/KienTruThiHanh --skill ck-predict-dattran26

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Five expert personas independently analyze a proposed change, then debate conflicts to produce a consensus verdict before a single line of code is written.

Core Features & Use Cases

  • Cross-functional risk assessment by five personas (Architect, Security, Performance, UX, Devil's Advocate) to surface architecture, security, performance, and UX concerns.
  • Structured verdicts (GO / CAUTION / STOP) with actionable recommendations to guide design reviews.
  • Early risk detection for major features, refactors, or API changes, enabling safer delivery.

Quick Start

Provide a proposed change description and have ck:predict deliver a consensus GO/CAUTION/STOP verdict after five persona analyses.

Frequently Asked Questions about ck:predict

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

FAQPage Schema
How do I run a design review for risky architectural changes before implementation?

To run a design review, provide a proposed change description. Five expert personas independently analyze architectural, security, performance, and UX risks, then debate conflicts to produce a formal GO, CAUTION, or STOP consensus verdict.

What is multi-persona risk analysis and when do I need it for a refactor?

Multi-persona risk analysis is a structured debate protocol where five expert personas independently vet a proposed change. You need it for major features, refactors, or API changes to surface cross-functional risks before writing code.

Can I use this to evaluate API changes for security and performance risks?

Yes, you can evaluate API changes by providing the proposed change description. The Security and Performance personas independently analyze the API change to surface specific risks before delivering an actionable consensus verdict.

How do I get a GO or STOP verdict for a proposed feature?

You get a GO or STOP verdict by submitting your proposed feature description. The five personas analyze the feature and debate conflicts to produce a formal consensus verdict with actionable recommendations for your design review.

Does cross-functional risk assessment work for UX and architecture concerns simultaneously?

Cross-functional risk assessment works simultaneously by assigning independent expert personas to UX and architecture. They analyze the proposed change, debate any conflicts between their concerns, and produce a unified risk and recommendation summary.

What are the limitations of using persona-based debate for early risk detection?

The limitation of persona-based debate for early risk detection is that it relies entirely on the provided change description. It produces a formal verdict and summary suitable for design reviews, but does not execute or test the actual code.