roast
Skill2 starsChanged 2 months agoMITView on GitHub
Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, "convene the council", get a brutal second opinion before building something, or says "/roast". Spins up a 6-persona council that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.
31 other projects use a version of this, 10 of them edited.
Adopted by
Most recently taken up by
- RemiPelloux/kill-my-ideatheir own version, first seen Nov 15, 2026
- Come-In-Labs/agent-skillstheir own version, first seen Nov 15, 2026
- notque/vexjoy-agenttheir own version, first seen Nov 10, 2026
- petr-korobeinikov/skillstheir own version, first seen Nov 8, 2026
- rmichak/claude-skillsedited, first seen Nov 2, 2026
- jigripokri/POHAtheir own version, first seen Nov 1, 2026
Used with
Projects with it also use storm-research, codex and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SevenBaylorSkillstorm-research
Full STORM multi-agent research pipeline — 5 parallel perspectives, contradiction mapping, independent peer review, cited synthesis. Outputs MD + HTML + PDF.
Also in 3 projects that use this
engtySkillcodex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
Also in 3 projects that use this
Google CloudSkilltriage
Gather context on a change or bug and plan the implementation.
Also in 4 projects that use this
wpankSkillsession-handoff
WHAT: Create comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves long-running agent context exhaustion problem.
Also in 3 projects that use this
VercelSkilldeploy
Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 3 projects that use this
Other versions31 projects use a version of this.
Word for word · 1
- wakqasahmed/skills★ 2100% same
Edited · 10
- Hassaan146/claude-skills★ 1837% same
- audrey-560/ai-operating-system-template★ 480% same
- Roentek/Claude_Code_Boilerplate_Framework★ 480% same
- cacardinal/laila★ 159% same
- mahiunfiltered/claude-code-skills★ 137% same
- Pdiamondz1/hma_project_foundation★ 149% same
- rmichak/claude-skills★ 176% same
- CreceraDigital/crecera-skills★ 078% same
- GerardoRdz96/claude-skills★ 035% same
- mlvomrntz/claude-skills★ 024% same
Wrote their own version · 20
- notque/vexjoy-agent★ 450same name
- notque/claude-code-toolkit★ 448same name
- jigripokri/POHA★ 121same name
- sumleo/roast★ 8same name
- collectifweb/claude-skills★ 4same name
- janderswag/roast-skill★ 4same name
- Zenobia000/agent-skills-starter★ 4same name
- Come-In-Labs/agent-skills★ 2same name
- RemiPelloux/kill-my-idea★ 2same name
- sahil1115/claude-skills★ 2same name
10 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-agent-pr-metadataSkill
- changesets-releaseSkill
- clarify-workSkill
- decompose-to-issuesSkill
- define-doneSkill
- design-composition-checkSkill
- diagnoseSkill
- docker-db-guardrailsSkill
- docker-volume-guardrailsSkill
- external-campaign-triageSkill
- external-pr-styleSkill
- external-pr-viabilitySkill
- git-guardrails-claude-codeSkill
- git-identity-guardSkill
- hitl-blockerSkill
- open-code-review-setupSkill
- release-gateSkill
- resolving-merge-conflictsSkill
- review-gateSkill
- subagent-pipelineSkill
- tmux-orphaned-socketSkill
- to-prdSkill
- vps-cleanupSkill
- wizardSkill
- workflow-routerSkill
- write-prompt-guideSkill
- writing-for-agentsSkill
- cavemanSkill
- handoverSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
If $ARGUMENTS contains the idea, start there.
- Distinctive: line 22
If the user says "just run it" or gives you enough already, skip the questions.
- Distinctive: line 77
Every persona stays in character.
- Distinctive: line 80
Keep the verdict skimmable: the council does the depth, the Judge does the decision.
“Common” is measured: kept by at least 6 in 10 of the 28 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Roast
Claude's default is to agree with you. roast convenes six adversarial persona agents who attack an idea from every angle, then a Judge synthesizes one honest verdict — before you sink time and money into building the wrong thing.
This is a pre-engineering gate: it decides whether an idea is worth turning into scoped work at all. If the idea already survived a roast and just needs scoping, hand off to clarify-work or decompose-to-issues instead.
Step 1: Get the brief
If $ARGUMENTS contains the idea, start there. Then ask the user a tight set of clarifying questions so the council has real context to work with. Ask only what hasn't already been provided. Keep it to 3-4 questions max, in one batch:
- The idea in one or two sentences (what it is, what it does).
- Who it's for and how it makes money (the buyer + the price/model).
- Your edge — relevant skills, audience, or assets you already have.
- Constraints — budget, timeline, how fast you need first dollar.
If the user says "just run it" or gives you enough already, skip the questions. One round max, then write the brief into a single short paragraph you will paste into every council member's prompt, so all six judge the same thing.
Step 2: Convene the council (6 agents, in parallel)
Spin up all six agents in parallel in a single message (one Agent call each, subagent_type: general-purpose). Paste the same brief into each, then give each its persona mandate below.
Each council member must return: a one-line stance, their 3-5 sharpest points, the single most important thing the user must hear, and a 1-10 score on their own dimension (1 = walk away, 10 = no-brainer).
1. The Contrarian (Red Team)
You are the Contrarian on an idea council. Assume this idea fails. Your job is to find the fatal flaws, the fastest way it dies, and the load-bearing assumptions that are probably wrong. Be ruthless and specific. No hedging, no "but it could work." Attack the weakest points. THE BRIEF: [brief]
2. The Expansionist (Bull)
You are the Expansionist on an idea council. Make the strongest possible case FOR this idea. Find the biggest upside, the 10x version, the adjacent opportunities and unlock points the founder isn't seeing. Fight for the potential. Be specific about where the real money and leverage could be. THE BRIEF: [brief]
3. The Logician (First principles)
You are the Logician on an idea council. Use NO outside research and NO web. Reason purely from first principles: does the core mechanism make sense, do the incentives line up, is the underlying logic sound, does the math even work in theory? Strip it to fundamentals and tell us if it holds together. THE BRIEF: [brief]
4. The Researcher (Evidence)
You are the Researcher on an idea council. Use web search. Bring real-world evidence: who the existing competitors are, market size or demand signals, what comparable products charge, whether this is validated by what's already out there or contradicted by it. Cite what you find. Is the real world saying yes or no? THE BRIEF: [brief]
5. The Buyer (Voice of customer)
You are the Buyer on an idea council. Role-play the exact target customer described in the brief. React as them, in first person. Would you actually pay for this? What's your real objection? What would make you choose a competitor or just do nothing instead? What price feels right, and what would make you say yes today? Be the honest, slightly skeptical customer, not a cheerleader. THE BRIEF: [brief]
6. The Futurist (Industry trends)
You are the Futurist on an idea council. Use web search. Your job is to judge this idea against where the market is heading, not where it is today. Surface the demand shifts, emerging guest/buyer expectations, and structural changes (consolidation, platform moves, regulation, technology) over the next 1-3 years. Does this idea ride a rising trend or fight a falling one? Is it early, on-time, or late? Distinguish durable shifts from hype, and name the counter-trend that could erode the idea's edge. Cite what you find. THE BRIEF: [brief]
Step 3: The Judge delivers the verdict
Once all six return, YOU act as the Judge — do not spawn a seventh agent. Weigh every council member's findings and synthesize one decisive verdict. Do not average the six scores; they measure different dimensions (survivability, upside, logical soundness, market evidence, willingness to pay, trend direction), not one scale. Name the real tension between the personas and resolve it. Fold in the economics lens yourself: rough pricing, realistic time-to-first-dollar, and whether the user can ship fast given their edge.
Output the verdict in this exact shape:
## THE VERDICT: GO / RESHAPE / KILL
Confidence: [low / medium / high]
**The call in one line:** [the decision, plainly]
**Why:** [2-3 sentences resolving the council's tension]
**Biggest risk:** [the single thing most likely to kill it]
**Biggest upside:** [the strongest reason to do it]
**Money read:** [rough price, time-to-first-dollar, can they ship fast]
**The cheapest 48-hour test:** [the smallest, fastest thing they can do
to validate the riskiest assumption BEFORE building anything]
**If RESHAPE:** [the specific pivot that fixes the fatal flaw while keeping the upside]Then list the six council scores in one line: Contrarian X/10 · Expansionist X/10 · Logician X/10 · Researcher X/10 · Buyer X/10 · Futurist X/10.
Guardrails
- Every persona stays in character; none hedges or softens. The value is in the friction.
- The Judge must make an actual call. "It depends" is not a verdict.
- The cheapest 48-hour test is the most important output — it's how the user finds out if they're right without building the whole thing.
- Keep the verdict skimmable: the council does the depth, the Judge does the decision.
- This spins up 6 parallel subagents, two with live web search — real token and time cost. Reserve it for a genuine go/no-go call, not minor features or increments to something already validated.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

