New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Brainstorm

by softspark in softspark/ai-toolkit

Pre-artifact conversation that prices the zero option and can end in 'do not build this'.

Apache-2.0Auto-check: notesAgent Workflows

Install Brainstorm

skills CLI
$ npx skills add softspark/ai-toolkit --skill brainstorm -a claude-code

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

GitHub CLI
$ gh skill install softspark/ai-toolkit 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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/brainstorm .claude/skills/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
brainstorm
GitHub stars
179
Token cost
~2k tokens
SKILL.md length
938 words
Files
1
Skills in repo
112
Repo updated
First seen
Licence
Apache-2.0

At a glance

Pre-artifact conversation that prices the zero option and can end in 'do not build this'.

  • Works in 5 steps: Understand before proposing → Shape the options → Resolve the unknowns → …
  • Tasks that involve Brainstorming
  • SKILL.md covers The zero option is a real…, Steps, Rules and Gotchas, plus 2 more sections
  • Calls go

What it does

Brainstorm is an agent skill from softspark/ai-toolkit. Pre-artifact conversation that prices the zero option and can end in 'do not build this'. Triggers: brainstorm, should we build, is this worth it, explore idea, thinking out loud, half-formed idea.

Its SKILL.md is about 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. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Brainstorming

Example prompts

  • “do not build this”
  • “/brainstorm”

Requirements

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

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Understand before proposing
  2. Shape the options
  3. Resolve the unknowns
  4. Challenge the conclusion
  5. Take an exit ramp

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. 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
    • Grep
    • Glob
    • Bash
    • Agent

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go

    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

Brainstorm loads about 2k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 938 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Glob, Bash, Agent

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 softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 938 words, ~1,992 tokens.

Download SKILL.mdSave it as .claude/skills/brainstorm/SKILL.md (or your agent's skills folder).
name
brainstorm
description
Pre-artifact conversation that prices the zero option and can end in 'do not build this'. Triggers: brainstorm, should we build, is this worth it, explore idea, thinking out loud, half-formed idea.
allowed-tools
Read, Grep, Glob, Bash, Agent
user-invocable
true
effort
high
argument-hint
[the idea, problem, or half-formed thought]

Brainstorm

$ARGUMENTS

The conversation that happens before an artifact exists. Every other planning skill here produces something — a PRD, a plan, issues, a design. This one is allowed to produce nothing, and that is its point.

The zero option is a real candidate

Price "build nothing" against the proposal properly. Not as a strawman, not as a sentence acknowledged and moved past — as a genuine option with its own costs:

  • what breaks or stays broken if nobody does this
  • who currently absorbs that, and how much it costs them
  • how long the problem has existed without being fixed, and what that says about it
  • what the codebase carries forever once this exists: another surface, another migration path, another thing that has to keep working

If the zero option wins, say so and stop. Do not invent a deliverable to justify the conversation. A brainstorm that ends in "this is not worth building, and here is what it would have cost" has done its job.

Steps

Step 1: Understand before proposing

Explore the actual codebase before shaping anything. Read what exists, grep for prior attempts, check whether the problem is already solved somewhere.

Ask what the user is trying to achieve, not what they want built. The stated request is a proposed solution; the problem behind it is what matters. Keep asking until you can state the problem without naming the solution.

Step 2: Shape the options

Produce at least three genuinely different approaches, one of which is always "do nothing / do it manually / wait". Different means different in kind, not three variants of the same shape.

For each: what it costs, what it forecloses, what has to stay true for it to keep working.

Step 3: Resolve the unknowns

List what nobody in the conversation actually knows. For each, decide whether it can be resolved now (read the code, check the data, run something) or whether it stays open and becomes a risk the next stage inherits.

Resolve what is cheap to resolve. An unknown carried into a PRD becomes an Open Question; an unknown carried past a PRD becomes a bug.

Step 4: Challenge the conclusion

Before routing anywhere, spawn a separate agent to attack the conclusion. Not you re-reading your own reasoning — a different context that did not fall in love with the idea.

Use the Agent tool with subagent_type: general-purpose.

Your job is to break the conclusion below, not to improve it. Assume it is wrong
and find out where. If you cannot break it, say what specifically held.

Conclusion reached: <one paragraph>
Options rejected, with reasons: <list — the zero option is always one of them>
Unknowns still open: <list>

Work through these in order:

1. Restate the problem without naming any solution. If you cannot, the problem
   was never separated from the proposal and everything below is downstream of
   that.
2. Who pays for the problem today, how often, and how much? If nobody can be
   named, the cost is assumed rather than observed.
3. The problem has existed until now without this being built. What changed —
   or is the trigger just that someone thought of it?
4. Take the zero-option reasoning and argue the opposite side as well as you can.
   If that argument is stronger than the one that won, the zero option was
   dismissed rather than priced.
5. What does the codebase carry permanently once this exists? Count the surface,
   the migration path, the thing that must keep working.
6. Name the single assumption that, if false, wastes the most work — and the
   cheapest thing that would prove it false today.
7. Hand the brief to someone who was not here. What do they ask first?

Report as: BLOCKER (the conclusion or the chosen next step does not survive),
CONCERN (holds, but on an assumption worth naming), HOLDS (what you tried to
break and could not).

Write plainly and skip the closing summary. Do not soften findings to be
agreeable — agreement you did not test is worth nothing here. A first pass over
a fresh idea that produces no BLOCKER and no CONCERN almost always means the
attack was shallow; go back to question 4.

Any BLOCKER goes back to Step 2 or Step 3. Do not route past one.

Step 5: Take an exit ramp

Pick exactly one and say which, in the user's words, before invoking anything.

#WhenNext
1Nothing worth building, or the question is answeredstop — no artifact, no handoff
2Worth doing, not nowwrite a brief to kb/planning/, stop
3Feature, unknowns resolved/write-a-prd
4Feature, user wants to co-design/design-an-interface, then /write-a-prd
5Small and obvious, no spec needed/tdd or /fix directly
6Already tracked somewherepoint at the existing issue or task, stop

Ramp 1 and ramp 6 are the two most likely to be correct and the two most likely to be skipped. Check both before considering the others.

Show full SKILL.md (427 more words)Show less

Rules

  • MUST price the zero option explicitly and state why it lost, before any ramp other than 1 is taken
  • MUST spawn the challenger as a separate agent — self-review at Step 4 does not count and is the failure mode this skill exists to prevent
  • NEVER invoke a downstream skill without naming the ramp and the reason first
  • NEVER produce a PRD, plan, or issue from inside this skill — it routes, it does not build
  • CRITICAL: ending at ramp 1 is a success, and is reported as one, not as an apology
  • MANDATORY: at least one of the three options in Step 2 is always the zero option

Gotchas

  • The challenger only works from a separate context. Re-reading your own reasoning in the same conversation reproduces the same blind spots and returns OK on everything, which reads as validation and is nothing of the kind.
  • A challenger that never returns BLOCKER or CONCERN is broken, not agreeable. If several runs come back clean, check that the conclusion, the rejected options and the open unknowns are actually being passed in — an attacker given nothing to attack reports that everything holds.
  • "The user asked for it" is not the problem statement. Users arrive with a solution already chosen; Step 1 is not finished until the problem stands without it.
  • Sunk conversation is not evidence. Forty minutes of good discussion does not make the idea worth building, and the pull toward a handoff gets stronger the longer the conversation ran. That pull is exactly what ramp 1 resists.
  • Ramp 6 loses to novelty. Searching the tracker feels like admitting the conversation was wasted, so it gets skipped — do it early, in Step 1.
  • This skill costs roughly double a plain planning session, because of the challenger. That is only worth paying if ramp 1 or ramp 6 sometimes wins. If every run of this skill routes to /write-a-prd, stop using it — it has become ceremony.

When NOT to Use

  • The decision is already made and you want it executed — use /plan or /write-a-prd
  • A concrete plan exists and needs stress-testing — use /grill-me
  • An architectural choice needs several expert perspectives — use /council
  • A bug needs a root cause — use /debug or /triage-issue
  • The change is one obvious line — just make it; a brainstorm about a typo is the same waste as a PRD about one
  • Chose to build it? → /write-a-prd for the requirements, then /prd-to-plan
  • Need to compare interface shapes first? → /design-an-interface
  • Want the plan attacked instead of the idea? → /grill-me
  • Want four expert lenses on a decision? → /council

© softspark, Apache-2.0. 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 app/skills/brainstorm of softspark/ai-toolkit.

Open the folder on GitHubat commit d64db2b

Compare with similar skills

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.

Brainstorm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Brainstorm this skillsoftspark/ai-toolkit179—~2kAutomated safety check: NotesApache-2.0
Brainstormingxpinjection/test-driven-spring-boot11254 repos~2.6kAutomated safety check: PassMIT
LLM Councilgcpdev/llm-council-skill4611 repos~1kAutomated safety check: NotesMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT
Trellis StartROYIANS/foliq-print-template-designer1356 repos~646Automated safety check: PassMIT

Similar skills

  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 54 repos~2.6k tokens
    Agent WorkflowsAuto-check passed

  • LLM Council

    gcpdev/llm-council-skill

    Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

    461 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes

  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed

  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Trellis Start

    ROYIANS/foliq-print-template-designer

    Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

    135 GitHub starsUsed in 6 repos~646 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 4 days ago
    Agent WorkflowsAuto-check passed

More from softspark/ai-toolkit

All 112 skills in this repo

  • Prepare Test Env

    softspark/ai-toolkit

    Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.

    179 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check: notes

  • A11y Validate

    softspark/ai-toolkit

    Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~3.8k tokensUpdated yesterday
    Auto-check: notes

  • Analyze

    softspark/ai-toolkit

    Analyzes code quality, complexity, patterns across codebase.

    179 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • Autonomous Dev

    softspark/ai-toolkit

    Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.

    179 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check: notes

  • Brand Voice

    softspark/ai-toolkit

    Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed

  • CI

    softspark/ai-toolkit

    Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).

    179 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

Categories

Questions about Brainstorm

What does Brainstorm do?

Pre-artifact conversation that prices the zero option and can end in 'do not build this'. Brainstorm is an agent skill from softspark/ai-toolkit. Pre-artifact conversation that prices the zero option and can end in 'do not build this'.

When should I use Brainstorm?

Brainstorm fits situations like: tasks that involve Brainstorming.

How do I install Brainstorm in Claude Code?

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

How do I install Brainstorm in Codex?

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

Can I use 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 softspark/ai-toolkit --skill 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/brainstorm, .gemini/skills/brainstorm, .github/skills/brainstorm and .opencode/skills/brainstorm in your project.

What does Brainstorm need to run?

Going by SKILL.md and its folder, Brainstorm needs the command-line tools its instructions call (go). Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash, Agent.

Does 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 Brainstorm safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Brainstorm use?

Brainstorm is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Brainstorm use?

About 2k tokens (SKILL.md is roughly 8k 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 Brainstorm?

Skills that share tags, products or a category with Brainstorm: Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), LLM Council (gcpdev/llm-council-skill, 461 stars), Typesafe AI (OpenAgentsInc/openagents, 455 stars) and Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Brainstorm?

softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.

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