roast

v2.10.3

Pressure-test a business idea before you build it. Convenes a 5-angle adversarial panel — The Critic (what kills this?), The Champion (the 10x upside?), The Analyst (does the logic hold?), The Investigator (what does the market say?), and The Customer (would I actually pay?) — fired in parallel as independent reviewers, then a Judge synthesizes one GO / RESHAPE / KILL verdict with explicit confidence and the cheapest 48-hour test to de-risk it. Never averages the scores: a weighted synthesizer with demand/fatal-flaw/logic veto gates produces the call, backed by deterministic stdlib tools. The opposite of Claude's default agreeableness.

Claude Code1 skill

by Alireza RezvaniMIT24.2kupdated 10 hours ago

Source

$ git clone https://github.com/alirezarezvani/claude-skills

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is productivity/roast/ inside the repository.

Layout

productivity/roast/

├── .claude-plugin/plugin.json
└── skills/roast/SKILL.md

Skills1

roastskills/roast/SKILL.md

Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, "convene the panel", get a brutal second opinion before building something, or says "/roast". Spins up a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.

Manifests1

productivity/roast/.claude-plugin/plugin.json

{
  "name": "roast",
  "description": "Pressure-test a business idea before you build it. Convenes a 5-angle adversarial panel — The Critic (what kills this?), The Champion (the 10x upside?), The Analyst (does the logic hold?), The Investigator (what does the market say?), and The Customer (would I actually pay?) — fired in parallel as independent reviewers, then a Judge synthesizes one GO / RESHAPE / KILL verdict with explicit confidence and the cheapest 48-hour test to de-risk it. Never averages the scores: a weighted synthesizer with demand/fatal-flaw/logic veto gates produces the call, backed by deterministic stdlib tools. The opposite of Claude's default agreeableness.",
  "version": "2.10.3",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/productivity/roast",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills/roast"
  ],
  "source": {
    "build_pattern": "Path-B persona skill — adversarial panel prompt preserved + deterministic verdict/brief/test tooling added",
    "distinct_from": "productivity/andreessen (single market-first lens, not a 5-angle panel); c-level-advisor boardroom /cs:boardroom (enterprise C-suite pipeline requiring company-context.md onboarding, outputs a board memo); engineering/grill-me (interrogates a plan, issues no GO/KILL verdict)"
  }
}