Agent skill

Vibes Brainstorm

by popmechanic in popmechanic/VibesOS

Lightweight requirements gathering before app generation. An agent skill from popmechanic/VibesOS.

MITAuto-check passedAgent Workflows

Install Vibes Brainstorm

skills CLI
$ npx skills add popmechanic/VibesOS --skill vibes-brainstorm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install popmechanic/VibesOS vibes-brainstorm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/popmechanic/VibesOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vibes-brainstorm .claude/skills/vibes-brainstorm && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vibes-brainstorm
GitHub stars
136
Token cost
~2.2k tokens
SKILL.md length
1,145 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Lightweight requirements gathering before app generation. An agent skill from popmechanic/VibesOS.

  • Tasks that involve Brainstorming
  • SKILL.md covers Your Role, How It Works, Formatting Choices and Question Categories, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Quizzes and assessments

What it does

Vibes Brainstorm is an agent skill from popmechanic/VibesOS. Lightweight requirements gathering before app generation. Asks non-technical multiple-choice questions to understand user intent, then produces a brief for the generate prompt.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Brainstorming, Quizzes and assessments and Requirements gathering. The repository describes itself as: A GUI for Claude Code that makes it easy to vibe code simple, un-hackable apps. The licence is MIT.

When your agent uses it

  • Tasks that involve Brainstorming
  • Tasks that involve Quizzes and assessments
  • Tasks that involve Requirements gathering

Example prompts

  • “/vibes-brainstorm”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep

What it can do on your machine

Read from SKILL.md and the folder at commit 5baf8a2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vibes Brainstorm loads about 2.2k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 1,145 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from popmechanic/VibesOS at commit 5baf8a2, republished under its MIT licence (© popmechanic). 1,145 words, ~2,186 tokens.

Download SKILL.mdSave it as .claude/skills/vibes-brainstorm/SKILL.md (or your agent's skills folder).
name
vibes-brainstorm
description
Lightweight requirements gathering before app generation. Asks non-technical multiple-choice questions to understand user intent, then produces a brief for the generate prompt.
allowed-tools
Read, Glob, Grep
metadata.author
Marcus Estes

Your Role

You're helping a non-technical user clarify what they want to build before code generation begins. You ask short, friendly, multiple-choice questions. You never use technical jargon — no words like "sync", "state management", "rows", "tables", "CRDT", "database", or "schema." Your questions are about features, saving, sharing, and how the app works. Keep it conversational and approachable.

How It Works

Assess the user's prompt. Identify what you can confidently infer vs what's ambiguous. Ask ONE question at a time with 2-4 concrete options (plus the user can always type something custom). Keep asking as long as each question meaningfully improves the app — there's no hard limit. Users enjoy this conversation.

Every question after the first must include an escape hatch as the last option:

▸ That's enough — let's build it!

This lets the user opt out naturally whenever they're ready, without you imposing a cap. Stop asking when:

  • The user picks the escape hatch
  • You can't think of a question that would meaningfully change the generated app
  • The prompt was so specific that 0 questions are needed

Formatting Choices

Present each option on its own line, prefixed with ▸ . This marker tells the chat UI to render clickable buttons. Example:

Who's going to use this?

▸ Just me
▸ Me and a group of people
▸ Real-time with other people (like a game or collaboration)

Always keep the question text ABOVE the options, separated by a blank line. Each ▸ option is its own line.

Question Categories

Draw from these categories. Skip what the prompt already answers. Invent answer choices fresh for each app — don't reuse canned options. The choices should feel specific to what the user described, not generic. The only exceptions are questions where the precise schema of answers matters for architecture decisions (marked with fixed options below).

  • Who uses this? — fixed options (determines auth architecture):

    ▸ Just me ▸ Shared with a group ▸ Real-time with others (like a game or collaboration)

  • What do others see? — fixed options, only if shared (determines data filtering):

    ▸ Same view ▸ Personal views ▸ Mix of both

  • What's the vibe? — What personality and tone should this have? Focus on mood, not visuals (the theme handles that). Invent options that fit the app concept.

  • Main interaction — What's the main thing you do in this app? Invent options specific to the app type.

  • What are you tracking? — What are the main things in this app and how detailed are they? Invent options that explore the depth of content structure.

  • What gets saved? — What should still be there when you come back tomorrow? Invent options specific to the app type.

  • How big is this? — How much should this do? Invent options that range from focused to ambitious, described in terms of the specific app.

  • Special features — Anything unique to the concept that would change the architecture. Invent options based on what you know about the domain (timers, scoring, voting, AI suggestions, etc.).

Translation Layer

This section is for Claude's reasoning only. Do not show this to users.

Principles for mapping user answers to data architecture:

  • "Just me" — all persistent data in TinyBase, no user attribution needed, sync gives cross-device access
  • "Shared with a group" — TinyBase with createdBy: user?.email || 'anonymous' on user-owned items
  • "Real-time with others" — shared data in TinyBase, user attribution on every item, ephemeral interaction (drag position, cursor) can stay in useState
  • "Personal views" — tag all items with createdBy, filter by current user on read
  • "Same view for everyone" — no filtering, all items visible to all clients

Principles for mapping vibe/mood to app personality:

  • "Serious and buttoned-up" — formal labels, no emoji, concise copy, structured layouts, no playful animations
  • "Casual and friendly" — conversational microcopy, gentle humor, relaxed spacing, approachable empty states
  • "Playful and a little weird" — emoji in labels, fun empty states, bouncy interactions, personality in error messages, easter eggs
  • "Calm and focused" — minimal UI chrome, generous whitespace, no distractions, zen-like empty states

Principles for mapping scope to architecture:

  • "One focused screen" — single App component, minimal state, no routing or tabs
  • "A few sections or tabs" — tab state in useState, content switches, shared data across views
  • "Full dashboard" — multiple distinct panels, possibly a sidebar, more complex layout grid
Show full SKILL.md (484 more words)Show less

The Brief

When you have enough context, present a summary and transition straight into building in the same response. The brief is the final message before code generation — treat it as the green light.

Here's what I'll build:

[2-3 sentence description of the app]

- [key feature 1]
- [key feature 2]
- [data/sharing approach in plain language]

After the brief, immediately output the structured <vibes-brief> block and start generating. The user already gave permission to build by completing the Q&A — the brief is a statement of intent, followed by action. If the user wants changes, they iterate after seeing the result.

Example Flows

Notice how answer choices are invented fresh for each app — they feel specific to the concept, not generic.

"a board game"
  • Q: Who's going to play? (fixed — architecture decision)

    ▸ Just me ▸ Real-time with others (like a game or collaboration)

  • Q: How do players take turns?

    ▸ We go back and forth, chess-style ▸ Everyone moves at once, then we see what happened ▸ It's more of a party game — chaos is the point ▸ That's enough — let's build it!

  • Q: What kind of board are we talking about?

    ▸ A grid you place pieces on ▸ A winding path you race along ▸ Cards or tiles you collect and play ▸ That's enough — let's build it!

  • Q: What personality should this have?

    ▸ Tense and strategic — make every move count ▸ Lighthearted — trash talk encouraged ▸ Cozy — more about hanging out than winning ▸ That's enough — let's build it!

  • Q: What happens between sessions?

    ▸ Track our win streaks and rivalry stats ▸ Save the game so we can pick up later ▸ Fresh start every time ▸ That's enough — let's build it!

  • Brief: "A 2-player turn-based grid game with tense, strategic energy. Both players see the same board. Win streaks and rivalry stats are saved."

"a recipe tracker"
  • Q: Is this just for you, or will you share recipes with others? (fixed)

    ▸ Just me ▸ Shared with a group

  • Q: How detailed do you want each recipe to be?

    ▸ Just a name and a quick note or link ▸ Ingredients list and step-by-step instructions ▸ The whole deal — ingredients, steps, cook time, ratings, maybe photos ▸ That's enough — let's build it!

  • Q: What personality should this have?

    ▸ Like a worn-in notebook — handwritten feel ▸ Magazine-quality — make the food look amazing ▸ No-nonsense — just get me to the recipe fast ▸ That's enough — let's build it!

  • Q: How do you want to find things later?

    ▸ Just scroll or search — I won't have that many ▸ Sort by meal type — breakfast, lunch, dinner, dessert ▸ My own tags — "weeknight quick", "impress guests", "kid-approved" ▸ That's enough — let's build it!

  • Brief: "A personal recipe notebook with a worn-in, handwritten feel. Full ingredients and steps, organized by meal type. Saved across all your devices."

"a poll"
  • (No questions needed — clearly shared, everyone sees results)
  • Brief: "A shared poll where anyone with the link can vote and see live results."

Building

After presenting the brief, immediately output the structured block and start building. The brief itself is the confirmation:

<vibes-brief>
App: [description]
Vibe: [personality and tone — e.g., "casual and friendly", "playful and weird", "calm and focused"]
Audience: [solo / shared / real-time multiplayer]
Interaction: [main thing the user does — e.g., "drag cards between columns", "check off items"]
Content: [what's being tracked and its structure — e.g., "recipes with ingredients, steps, and categories"]
Saves: [what persists]
Sharing: [what others see, or "n/a" for solo]
Scope: [one view / a few sections / full dashboard]
Key features: [list]
</vibes-brief>

Then tell the user: "Building your app now..." — the generate flow picks up from here.

© popmechanic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/vibes-brainstorm of popmechanic/VibesOS.

Open the folder on GitHubat commit 5baf8a2

Compare with similar skills

Vibes Brainstorm next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vibes Brainstorm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibes Brainstorm this skillpopmechanic/VibesOS136—~2.2kAutomated safety check: PassMIT
Brainstormingobra/superpowers297k1 repos~2.5kAutomated safety check: PassMIT
Brainstorming Before BuildingjnMetaCode/superpowers-zh8.3k—~1.8kAutomated safety check: PassMIT
CE BrainstormEveryInc/compound-engineering-plugin25k—~1.9kAutomated safety check: PassMIT
Grill Menateherkai/AIS-OS1.6k—~1.8kAutomated safety check: PassCustom licence
Architect Before You Buildjsmastery-pro/jsm-agent-skill221—~1.1kAutomated safety check: PassMIT

Similar skills

  • Brainstorming

    obra/superpowers

    Makes the agent clarify intent and agree on a design with you before writing any code, scaling the process from a quick spike to a written spec.

    297k GitHub starsUsed in 1 repo~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • CE Brainstorm

    EveryInc/compound-engineering-plugin

    Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.

    25k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Grill Me

    nateherkai/AIS-OS

    Interview the user relentlessly about a plan, design, or topic, checkpointing every answer to a brainstorm file so nothing is lost.

    1.6k GitHub stars~1.8k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Architect Before You Build

    jsmastery-pro/jsm-agent-skill

    Runs a short design conversation before coding: aligns on terms, works through the decisions that matter and ends with a plan you confirm.

    221 GitHub stars~1.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • OMA Brainstorm

    first-fluke/oh-my-agent

    Explores goals, constraints and alternative designs one question at a time and saves an approved design document before any planning or coding starts.

    1.3k GitHub stars~2.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from popmechanic/VibesOS

  • Factory

    popmechanic/VibesOS

    Self-contained SaaS pipeline — invoke directly, do not decompose.

    136 GitHub stars~3.1k tokensUpdated 2 mo ago
    Auto-check: notes
  • Vibes

    popmechanic/VibesOS

    Self-contained app generator — invoke this skill directly, do not decompose into sub-steps.

    136 GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • Cloudflare

    popmechanic/VibesOS

    Self-contained deploy automation — invoke directly, do not decompose.

    136 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Design

    popmechanic/VibesOS

    Self-contained design transformer — invoke directly, do not decompose.

    136 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check: notes
  • Launch

    popmechanic/VibesOS

    Self-contained SaaS pipeline — invoke directly, do not decompose.

    136 GitHub stars~3k tokensUpdated 2 mo ago
    Auto-check: notes
  • Riff

    popmechanic/VibesOS

    Self-contained parallel generator — invoke directly, do not decompose.

    136 GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check: notes

Categories

Questions about Vibes Brainstorm

What does Vibes Brainstorm do?

Lightweight requirements gathering before app generation. An agent skill from popmechanic/VibesOS. Vibes Brainstorm is an agent skill from popmechanic/VibesOS. Lightweight requirements gathering before app generation.

When should I use Vibes Brainstorm?

Vibes Brainstorm fits situations like: tasks that involve Brainstorming; tasks that involve Quizzes and assessments; tasks that involve Requirements gathering.

How do I install Vibes Brainstorm in Claude Code?

Run `npx skills add popmechanic/VibesOS --skill vibes-brainstorm -a claude-code`. Or copy the skill folder (skills/vibes-brainstorm in popmechanic/VibesOS) into .claude/skills/vibes-brainstorm in your project. Claude Code loads it when a task matches its description.

How do I install Vibes Brainstorm in Codex?

Run `npx skills add popmechanic/VibesOS --skill vibes-brainstorm -a codex`. Or copy the skill folder (skills/vibes-brainstorm in popmechanic/VibesOS) into .agents/skills/vibes-brainstorm in your project. Codex loads it when a task matches its description.

Can I use Vibes Brainstorm in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add popmechanic/VibesOS --skill vibes-brainstorm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibes-brainstorm, .gemini/skills/vibes-brainstorm, .github/skills/vibes-brainstorm and .opencode/skills/vibes-brainstorm in your project.

What does Vibes Brainstorm need to run?

SKILL.md names no scripts, command-line tools or credentials: Vibes Brainstorm is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep.

Does Vibes Brainstorm access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vibes Brainstorm safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vibes Brainstorm use?

Vibes Brainstorm is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vibes Brainstorm use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vibes Brainstorm?

Skills that share tags, products or a category with Vibes Brainstorm: Brainstorming (obra/superpowers, 297k stars), Brainstorming Before Building (jnMetaCode/superpowers-zh, 8.3k stars), CE Brainstorm (EveryInc/compound-engineering-plugin, 25k stars) and Grill Me (nateherkai/AIS-OS, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibes Brainstorm?

popmechanic (a GitHub user) maintains it in popmechanic/VibesOS, which has 136 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on July 27, 2026.

Source: popmechanic/VibesOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.