Skip to content

alirezarezvani/claude-skills / productivity/roast/skills/roast

Roast an idea: a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) attacks it, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it. Use whenever the user wants to pressure-test or validate a business idea, asks for a brutal second opinion before building, asks is this a good idea, says convene the panel, or runs /roast.

assets/roast_brief_worksheet.md

View on GitHub
# Roast Brief Worksheet

Fill this in before convening the panel. All five reviewers judge the *same* brief, so vagueness here
becomes noise in the verdict. Keep each answer tight — one or two sentences.

> Tip: run `scripts/brief_builder.py` with these fields to get a normalized paragraph + a check for
> anything still missing.

---

**1. The idea** — what it is and what it does, in one or two sentences.

>

**2. Who it's for** — the exact target buyer (be specific: "1-3 person nonprofits with no grant writer," not "nonprofits").

>

**3. How it makes money** — price + model (e.g. "$99/mo SaaS," "20% take rate," "one-time $499").

>

**4. Your edge** — the relevant skill, audience, or asset you already have that most people don't.

>

**5. Constraints** *(optional but recommended)* — budget, timeline, how fast you need first dollar.

>

---

## Assembled brief (paste into all five panelists)

> The idea: ____. Target buyer: ____. How it makes money: ____. The founder's edge: ____. Constraints: ____.

---

## The five seats (what each one will do to this brief)

| Seat | The question it answers |
|---|---|
| **The Critic** | "What kills this?" — fatal flaws, fastest way it dies |
| **The Champion** | "What's the 10x upside?" — biggest case for it |
| **The Analyst** | "Does the logic actually hold?" — first principles, no web |
| **The Investigator** | "What does the real market say?" — web evidence, competitors |
| **The Customer** | "Would I actually pay?" — first-person target buyer |
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall