Official agent skill

Brainstorming

by JetBrains in JetBrains/thinkrail

Use before implementation when a request requires choosing product scope, user-visible behavior, or architecture.

OfficialApache-2.0Auto-check passedAgent Workflows

Install Brainstorming

skills CLI
$ npx skills add JetBrains/thinkrail --skill brainstorming -a claude-code

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

GitHub CLI
$ gh skill install JetBrains/thinkrail brainstorming --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/JetBrains/thinkrail.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/pi-thinkrail-workflow/skills/brainstorming .claude/skills/brainstorming && 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
brainstorming
GitHub stars
513
Token cost
~913 tokens
SKILL.md length
472 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Use before implementation when a request requires choosing product scope, user-visible behavior, or architecture.

  • Works in 9 steps: Orient. Use the spec-graph skill to find… → Scope check. If the request bundles… → Open a task-spec. Once the decision to… → …
  • Tasks that involve Brainstorming
  • SKILL.md covers Brainstorm before you build, The workflow, What a good task-spec looks like and Ending
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Brainstorming is an agent skill from JetBrains/thinkrail, published by the product's own GitHub organization. Use before implementation when a request requires choosing product scope, user-visible behavior, or architecture. Not for fully specified fixes, mechanical refactors, documentation, or configuration-only changes.

Its SKILL.md is about 910 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 and Refactoring. The repository describes itself as: Vibe code with pi in a lightweight, real IDE that customises itself around the way you work — The Vibe You Need. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Brainstorming
  • Tasks that involve Refactoring

Example prompts

  • “/brainstorming”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Orient. Use the spec-graph skill to find relevant recorded boundaries, contracts, invariants,
  2. Scope check. If the request bundles independent product decisions or subsystems, separate them
  3. Open a task-spec. Once the decision to make is understood, spec_create a task-spec at
  4. Interview the open decisions. Ask via ask_user_question about every decision whose answer
  5. Draft the design. Record the request, recommended design, trade-offs that matter, and explicit
  6. Self-review. Remove placeholders, contradictions, accidental scope expansion, and ambiguous
  7. Review once. Present one cohesive design scaled to the decision. Ask for one approval only when
  8. Promote. Read the writing-specs concept skill, then move any settled boundary, contract, or
  9. Build. Implement directly against the accepted design. Before handoff, self-review the task

What it can do on your machine

Read from SKILL.md and the folder at commit 3f7e0d4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    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

Brainstorming loads about 913 tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 472 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~913

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 JetBrains/thinkrail at commit 3f7e0d4, republished under its Apache-2.0 licence (© JetBrains). 472 words, ~913 tokens.

Download SKILL.mdSave it as .claude/skills/brainstorming/SKILL.md (or your agent's skills folder).
name
brainstorming
description
Use before implementation when a request requires choosing product scope, user-visible behavior, or architecture. Not for fully specified fixes, mechanical refactors, documentation, or configuration-only changes.

Brainstorming

Brainstorm before you build

  • Run this workflow only when implementation depends on an unresolved product or design choice.
  • The aim is a validated design, recorded as a spec-graph task-spec, not a speculative implementation.
  • Do not implement until the design is accepted. Acceptance criteria or an explicit design already supplied by the user count as approval; do not ask them to approve the same decision again.

The workflow

  1. Orient. Use the spec-graph skill to find relevant recorded boundaries, contracts, invariants, and decisions; read code second to confirm implementation details. Do not read unrelated specs.
  2. Scope check. If the request bundles independent product decisions or subsystems, separate them rather than blending unrelated decisions into one task-spec.
  3. Open a task-spec. Once the decision to make is understood, spec_create a task-spec at .thinkrail/context/TASK-<slug>.md (id, title, status: draft, parent: the nearest relevant module). This gitignored file is the one temporary design artifact; update it as decisions land.
  4. Interview the open decisions. Ask via ask_user_question about every decision whose answer changes observable behavior or scope and that the request or specs have not already settled; look facts up instead of asking them. Interview in rounds per the asking-user-questions concept skill until no such decision is left assumed. Skipped questions or a host with no UI are not blockers: record the best assumption as unconfirmed and continue.
  5. Draft the design. Record the request, recommended design, trade-offs that matter, and explicit deferrals. Compare alternatives only when more than one viable approach remains; do not invent options after the constraints already select one.
  6. Self-review. Remove placeholders, contradictions, accidental scope expansion, and ambiguous requirements before presenting the design.
  7. Review once. Present one cohesive design scaled to the decision. Ask for one approval only when the user has not already approved the same design through their request or acceptance criteria. Revise the task-spec if they adjust it.
  8. Promote. Read the writing-specs concept skill, then move any settled boundary, contract, or decision into the relevant durable SPEC.md; use spec_create for a new module, spec_update for frontmatter, and edit for prose. Run spec_validate after structural changes.
  9. Build. Implement directly against the accepted design. Before handoff, self-review the task diff: no silent lint/type suppressions, duplicated nontrivial derivations, rationale left as code comments, or remnants of a replaced pattern. Keep durable specs honest and retire the task-spec once the work itself is done.
Show full SKILL.md (74 more words)Show less

What a good task-spec looks like

  • Scoped to one decision-bearing piece of work.
  • States the request, chosen design and why, real alternatives considered, assumptions, and explicit deferrals.
  • Promotes settled decisions instead of copying them: durable rationale lives once in the owning spec.

Ending

Once the accepted design is implemented, verified, reflected in durable specs, and its task-spec is retired, this workflow ends with no successor. PR lifecycle work, if requested, then enters shipping-a-pr separately.

© JetBrains, 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 packages/pi-thinkrail-workflow/skills/brainstorming of JetBrains/thinkrail.

Open the folder on GitHubat commit 3f7e0d4

Compare with similar skills

Brainstorming 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.

Brainstorming compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Brainstorming this skillJetBrains/thinkrail513—~913Automated safety check: PassApache-2.0
Cc10x Routerromiluz13/cc10x164—~20kAutomated safety check: PassMIT
Ideation Firstccplugins/awesome-claude-code-plugins968—~926Automated safety check: PassApache-2.0
Odoo Workflowunclecatvn/agent-skills143—~4.7kAutomated safety check: PassMIT
Improvefossasia/eventyay-interpretation1.6k10 repos~3.7kAutomated safety check: WarnMIT
Plate Plugin Creatorudecode/plate17k—~2.3kAutomated safety check: PassCustom licence

Similar skills

  • Cc10x Router

    romiluz13/cc10x

    Routes build, debug, review, plan, QA, and triage requests through the cc10x workflows (task graphs, workflow artifacts, gates); it is the single entry point for cc10x code work.

    164 GitHub stars~20k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Ideation First

    ccplugins/awesome-claude-code-plugins

    Use before planning a new feature or greenfield refactor whose requirements aren't yet pinned down — clarifies intent through a few questions and ends with a short scope brief the planner can build…

    968 GitHub stars~926 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Odoo Workflow

    unclecatvn/agent-skills

    Mandatory pre-code gate and definition-of-done for ANY Odoo change (add field, override method, inherit view/xpath, OWL/JS patch, wizard, cron, controller, report, security, migration, bug fix…

    143 GitHub stars~4.7k tokensUpdated 14 days ago
    DevelopmentAuto-check passed
  • Improve

    fossasia/eventyay-interpretation

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

    1.6k GitHub starsUsed in 10 repos~3.7k tokens
    Agent WorkflowsAuto-check: warnings
  • Build new Plate plugins with Slate-first architecture, sane typing, and explicit React/Plate wrapper boundaries.

    17k GitHub stars~2.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Chatgpt App Builder

    alpic-ai/skybridge

    Guide developers through creating and updating ChatGPT plugins.

    2.1k GitHub stars~1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from JetBrains/thinkrail

All 11 skills in this repo
  • Importing A Codebase

    JetBrains/thinkrail

    Official

    A skill your agent uses when asked to create the initial spec graph for an existing codebase that has source code but no specs.

    513 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Starting A New Project

    JetBrains/thinkrail

    Official

    A skill your agent uses when the workspace is empty, has no code, and the user brings a raw project idea.

    513 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Asking User Questions

    JetBrains/thinkrail

    Official

    A skill your agent uses when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step.

    513 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Setting Up A Project

    JetBrains/thinkrail

    Official

    A skill your agent uses when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card.

    513 GitHub stars~500 tokensUpdated yesterday
    Auto-check passed
  • Shipping A PR

    JetBrains/thinkrail

    Official

    A skill your agent uses when finished work needs to ship as a pull request, or when creating, syncing, updating metadata, checking status, monitoring CI, or addressing review comments on a PR.

    513 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Spec Graph

    JetBrains/thinkrail

    Official

    A skill your agent uses when locating, reading, creating, updating, or validating project specs, or when work is governed by or may alter a documented boundary, contract, invariant, behavior, or…

    513 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Brainstorming

What does Brainstorming do?

Use before implementation when a request requires choosing product scope, user-visible behavior, or architecture. Brainstorming is an agent skill from JetBrains/thinkrail, published by the product's own GitHub organization. Use before implementation when a request requires choosing product scope, user-visible behavior, or architecture.

When should I use Brainstorming?

Brainstorming fits situations like: tasks that involve Brainstorming; tasks that involve Refactoring.

How do I install Brainstorming in Claude Code?

Run `npx skills add JetBrains/thinkrail --skill brainstorming -a claude-code`. Or copy the skill folder (packages/pi-thinkrail-workflow/skills/brainstorming in JetBrains/thinkrail) into .claude/skills/brainstorming in your project. Claude Code loads it when a task matches its description.

How do I install Brainstorming in Codex?

Run `npx skills add JetBrains/thinkrail --skill brainstorming -a codex`. Or copy the skill folder (packages/pi-thinkrail-workflow/skills/brainstorming in JetBrains/thinkrail) into .agents/skills/brainstorming in your project. Codex loads it when a task matches its description.

Can I use Brainstorming 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 JetBrains/thinkrail --skill brainstorming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/brainstorming, .gemini/skills/brainstorming, .github/skills/brainstorming and .opencode/skills/brainstorming in your project.

What does Brainstorming need to run?

SKILL.md names no scripts, command-line tools or credentials: Brainstorming is instructions for the agent only.

Does Brainstorming 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 Brainstorming 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 Brainstorming use?

Brainstorming 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 Brainstorming use?

About 913 tokens (SKILL.md is roughly 3.7k 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 Brainstorming?

Skills that share tags, products or a category with Brainstorming: Cc10x Router (romiluz13/cc10x, 164 stars), Ideation First (ccplugins/awesome-claude-code-plugins, 968 stars), Odoo Workflow (unclecatvn/agent-skills, 143 stars) and Improve (fossasia/eventyay-interpretation, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Brainstorming?

JetBrains (a GitHub organization, an official publisher) maintains it in JetBrains/thinkrail, which has 513 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

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