Skip to main content
ClaudeWave
Skill856 repo starsupdated 11d ago

vc:predict

vc:predict runs a proposed code change through five independent expert personas (architect, security, performance, UX, and devil's advocate) who debate and reach consensus before implementation begins. Use this skill before major features, risky changes, significant refactors, or when evaluating competing technical approaches to catch architectural, security, performance, and user experience issues early.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit /tmp/vc-predict && cp -r /tmp/vc-predict/.claude/skills/vc-predict ~/.claude/skills/vc-predict
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# vc: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 `debugger` for bugs, `generate-plan` / `plan-agent` for already-decided tasks)
- Already-approved work with no open design questions
- Pure dependency upgrades with no API changes

---

## The 5 Personas

| Persona | Focus | Core Questions |
|---------|-------|----------------|
| **Architect** | System design, scalability, coupling | Does this fit the architecture? Will it scale? What new coupling does it introduce? |
| **Security** | Attack surface, data protection, auth | What can be abused? Where is data exposed? Are auth boundaries respected? |
| **Performance** | Latency, memory, queries, bundle size | What is the latency impact? N+1 queries? Memory leaks? Bundle bloat? |
| **UX** | User experience, accessibility, error states | Is this intuitive? What does the error state look like? Accessible on mobile? |
| **Devil's Advocate** | Hidden assumptions, simpler alternatives | Why 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

| Verdict | Meaning |
|---------|---------|
| **GO** | All personas aligned, no critical risks, proceed with confidence |
| **CAUTION** | Concerns exist but are manageable — mitigations identified, proceed carefully |
| **STOP** | Critical 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 Step | Skill | How |
|---------------|-------|-----|
| Deepen risk scenarios | `vc:scenario` | Feed Risk Summary rows as feature description |
| Create implementation plan | `generate-plan` / `plan-agent` | Attach Recommendations as constraints to the canonical planning path |
| High-risk feature implementation | `execute-agent` | Reference CAUTION/STOP items as acceptance gates |

---

## Example Invocations

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

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

code-simplifierSubagent

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

debuggerSubagent

Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying bottlenecks, analyzing failed deployments, investigating test failures, and creating diagnostic reports. Examples:\n\n<example>\nContext: The user needs to investigate why an API endpoint is returning 500 errors.\nuser: "The /api/users endpoint is throwing 500 errors"\nassistant: "I''ll use the debugger agent to investigate this issue"\n<commentary>\nSince this involves investigating an issue, use the Task tool to launch the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to analyze why the CI/CD pipeline is failing.\nuser: "The GitHub Actions workflow keeps failing on the test step"\nassistant: "Let me use the debugger agent to analyze the CI/CD pipeline logs and identify the issue"\n<commentary>\nThis requires analyzing CI/CD logs and test failures, so use the debugger agent.\n</commentary>\n</example>\n\n<example>\nContext: The user notices performance degradation in the application.\nuser: "The application response times have increased by 300% since yesterday"\nassistant: "I''ll launch the debugger agent to analyze system behavior and identify performance bottlenecks"\n<commentary>\nPerformance analysis and bottleneck identification requires the debugger agent.\n</commentary>\n</example>

execute-agentSubagent

EXECUTE MODE - Implementing EXACTLY what was planned. Full tool access. Can only be invoked after explicit user confirmation. Use after plan is approved.

fast-mode-agentSubagent

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + INNOVATE + PLAN) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

git-managerSubagent

Stage, commit, and push code changes with conventional commits. Use when user says "commit", "push", or finishes a feature/fix.

innovate-agentSubagent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

plan-agentSubagent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features/*/active/ only. Use after approach is decided.