Multi-persona risk analysis and debate tool for proposed architectural changes.

Install

mkdir -p .claude/skills/ck-predict && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12353" && unzip -o skill.zip -d .claude/skills/ck-predict && rm skill.zip

Installs to .claude/skills/ck-predict

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.
175 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Analyze proposed changes from multiple expert perspectives
  • Identify architectural risks before implementation
  • Evaluate security vulnerabilities in design proposals
  • Assess performance impacts of new features
  • Debate conflicts and produce a consensus verdict

How it works

Five expert personas independently analyze a proposed change, then debate conflicts to produce a consensus verdict.

Inputs & outputs

You give it
Feature description or change proposal, optionally with file paths
You get back
A prediction report with a verdict (GO, CAUTION, STOP), agreements, conflicts, risk summary, and recommendations

When to use ck:predict

  • Predict architectural risks
  • Analyze high-risk feature plans
  • Validate design changes

About this skill

ck:predict — Multi-Persona Pre-Analysis

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

When to Use

  • Before implementing a major or high-risk feature
  • Before a significant refactor or architecture change
  • Evaluating competing technical approaches
  • Stress-testing assumptions in a proposed design

When NOT to Use

  • Trivial or low-risk changes (use ck:debug for bugs, ck:plan for already-decided tasks)
  • Already-approved work with no open design questions
  • Pure dependency upgrades with no API changes

The 5 Personas

PersonaFocusCore Questions
ArchitectSystem design, scalability, couplingDoes this fit the architecture? Will it scale? What new coupling does it introduce?
SecurityAttack surface, data protection, authWhat can be abused? Where is data exposed? Are auth boundaries respected?
PerformanceLatency, memory, queries, bundle sizeWhat is the latency impact? N+1 queries? Memory leaks? Bundle bloat?
UXUser experience, accessibility, error statesIs this intuitive? What does the error state look like? Accessible on mobile?
Devil's AdvocateHidden assumptions, simpler alternativesWhy not do nothing? What is the simplest alternative? Which assumption could be wrong?

Debate Protocol

  1. Read the proposed change/feature description from the argument
  2. Read relevant code if file paths are provided (grep for affected areas)
  3. Each persona analyzes independently — do not let personas influence each other during this phase
  4. Identify agreements — points where all (or 4+) personas align
  5. Identify conflicts — points where personas meaningfully disagree
  6. Weigh tradeoffs — for each conflict, evaluate which concern has higher impact
  7. Produce verdict — GO / CAUTION / STOP with actionable recommendations

Output Format

## Prediction Report: [proposal title]

## Verdict: GO | CAUTION | STOP

### Agreements (all personas align)
- [Point 1 — what they all agree on]
- [Point 2]

### Conflicts & Resolutions

| Topic | Architect | Security | Performance | UX | Devil's Advocate | Resolution |
|-------|-----------|----------|-------------|-----|-----------------|------------|
| [Issue] | [View] | [View] | [View] | [View] | [View] | [Recommendation] |

### Risk Summary

| Risk | Severity | Mitigation |
|------|----------|------------|
| [Risk description] | Critical/High/Medium/Low | [Concrete action] |

### Recommendations
1. [Action item — rationale]
2. [Action item — rationale]
3. [Action item — rationale]

Verdict Levels

VerdictMeaning
GOAll personas aligned, no critical risks, proceed with confidence
CAUTIONConcerns exist but are manageable — mitigations identified, proceed carefully
STOPCritical unresolved issue found — needs redesign or more information before proceeding

STOP Triggers (any one is sufficient)

  • Security persona identifies auth bypass or data exposure with no viable mitigation
  • Architect identifies fundamental design incompatibility requiring significant rework
  • Performance persona identifies unacceptable latency or query explosion with no workaround
  • Devil's Advocate exposes a false assumption that invalidates the entire approach

Integration with Other Skills

Workflow StepSkillHow
Deepen risk scenariosck:scenarioFeed Risk Summary rows as feature description
Create implementation planck:planAttach Recommendations as constraints to planner
High-risk feature implementationck:cookReference CAUTION/STOP items as acceptance gates

Example Invocations

/ck:predict "Add WebSocket support for real-time notifications"
/ck:predict "Migrate authentication from JWT to session cookies"
/ck:predict "Add multi-tenancy to the database layer"
/ck:predict "Replace REST API with GraphQL" --files src/api/**/*.ts

When not to use it

  • For trivial or low-risk changes
  • For already-approved work with no open design questions
  • For pure dependency upgrades with no API changes

Limitations

  • Not suitable for minor changes
  • Requires a clear feature description or change proposal as input
  • Verdict can be STOP if critical unresolved issues are found

How it compares

This structured debate process identifies potential issues and provides actionable recommendations before coding, unlike a single-person review.

Compared to similar skills

ck:predict side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ck:predict (this skill)03moNo flagsIntermediate
ai-spec-review02moReviewAdvanced
agent-v3-security-architect36moReviewAdvanced
pair-capability-verify-adoption05moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry