# Vc Scenario

Generate comprehensive edge cases and test scenarios by decomposing features across 12...

- Repository: https://github.com/withkynam/vibecode-pro-max-kit (1164 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-06-21
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scenario -g -a claude-code -y`
Codex: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scenario -g -a codex -y`
Cursor: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scenario -g -a cursor -y`
Gemini CLI: `npx skills add withkynam/vibecode-pro-max-kit --skill vc-scenario -g -a gemini-cli -y`

## Description

Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use before implementation or testing to catch issues early.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# vc-scenario, Edge Case & Scenario Explorer

> **Output style:** Follow `process/development-protocols/communication-standards.md`, answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Decompose any feature or code path across 12 dimensions to surface edge cases, risks, and test targets before implementation begins.

## Mode Selection

Choose a mode before generating scenarios. Default is Simple unless a trigger condition applies.

### Simple Mode (default)

Generates edge cases from the plan description, checklist item, or approach text provided in the prompt. No subagent spawned.

**Use when:**
- The checklist item is self-contained and clearly described
- Blast radius is narrow (1, 2 files, single package)
- No auth, billing, schema, or external API surface is touched
- Speed matters and hypothetical coverage is sufficient

### Deep Mode

Spawns a research subagent to read the actual source before generating scenarios. Scenarios reference real variable names, real function signatures, and real failure modes visible in the code rather than hypothetical ones.

**Trigger conditions (any one):**
- Checklist item modifies an auth, billing, schema, or external API surface
- Blast radius spans 3+ files or 2+ packages
- The plan marks the item as `HIGH_RISK`
- Caller explicitly requests deep mode

**Deep mode subagent steps:**
1. Reads the actual source files being modified (from plan Touchpoints)
2. Locates and reads existing test files for those files (via grep for import paths or describe blocks)
3. Reads any Public Contracts affected (from plan's Public Contracts section)
4. Returns: real function signatures, actual data shapes, existing test coverage gaps, real failure modes visible in the code

The orchestrator then generates scenarios using the research output.

### Output quality difference

The rest: https://github.com/withkynam/vibecode-pro-max-kit/blob/HEAD/.claude/skills/vc-scenario/SKILL.md