agentleFS
Sign inStart free
RemiPellouxRemiPelloux/kill-my-idea/skills/roast/SKILL.md

roast

Skill2 starsChanged 6 days agoMITView on GitHub

Roast a startup or business idea. It is funny and savage, but every burn is backed by a real, sourced fact, and it ends with the kill-my-idea verdict card. Use when the user says "roast my idea", "roast my startup", "roast <company>", or wants a shareable, funny verdict. Also works on famous companies (for example Juicero or Quibi).

31 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use storm-research, to-prd and 7 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.
  • SevenBaylorSkill

    storm-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

  • GoogleSkill

    to-prd

    Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 3 projects that use this

  • AWSSkill

    wizard

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Also in 3 projects that use this

  • engtySkill

    codex

    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 CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • wpankSkill

    session-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

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never post anything on the user's behalf.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 29 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Roast My Idea

A roast is the kill-my-idea verdict told as stand-up. It is shareable on purpose.

Steps

  1. Research and score exactly as in ${CLAUDE_PLUGIN_ROOT}/skills/kill/SKILL.md, sections 0–5: the safety rules, the brief, the kill-shot checklist, the source rules (minimum 10 sources from 6 domains for a roast), the metrics, the rubric, the formula and the fixed rules. Famous companies need no questions; use public, well-documented facts.
  2. Write the data files so compare can rank the idea: idea.json and verdict.json (mode: "roast") in ideas/<YYYY-MM>-<slug>/, following the kill skill's schemas. The HTML report is optional for a roast; write it (kill skill §6) if the user asks. For a famous company, the roast may use hindsight (that's the joke), but if the user asks "would it have worked?", score it as of its launch date (as_of, kill skill §3) and keep the hindsight in the roast lines only.
  3. Write the roast to roast.md in the same folder, in this order:
    • the verdict card (kill skill §6), then the badge;
    • 5 burns: one line each, one fact each, one source link each. Funny comes from the fact itself (numbers, quotes, irony), not from insults. Order them from the biggest kill shot down;
    • "The one thing that's actually good": one honest line (the steelman, kill skill §5);
    • The fix: the cheapest test or best rescue path that could save it, in at most 2 lines, with its projected score;
    • one closing tagline, at most 12 words.
  4. Self-check with python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check-idea.py" ideas/<folder> when Bash is available (it accepts a folder without report data).
  5. Answer in chat with the full roast. It must fit in one screenshot: no extra sections, no preamble.

Rules

  • Roast the idea, never the person: no looks, identity or private life.
  • Facts only. Every burn has a source, and opinions are labelled as opinions. This keeps it funny and fair, and stops it from becoming defamatory.
  • Real companies and public figures: only public, documented facts.
  • Quotes must be verbatim from the linked source. If you can't confirm the exact words, paraphrase without quotation marks.
  • Same language as the user.
  • Never post anything on the user's behalf.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free