Cheatcode_
Feedback

Catalog / Productivity / Thinkrail

Agent skills · 11 skills

Thinkrail

Listed by its author as thinkrail

Vibe code with pi in a lightweight, real IDE, The Vibe You Need

DoesCoding and refactoringProduct and strategyPlanning and specsTasks and ticketsGit and GitHubArchitecture and system designWriting and docsNews and social feeds

Source on GitHub ↗
curl -fsSL https://api.cheatcodehq.com/install.sh | sh -s -- thinkrail --to all

Copies 11 skills into each app's skills folder (Claude Code: ~/.claude/skills), after checking every file against JetBrains/thinkrail at commit 0def253. Nothing else on your computer changes. To undo it, run the terminal command with --uninstall at the end; that also removes what the app added.

Then start a new session in your AI app and ask for the work in plain words; it picks the skill from its description. In Claude Code you can also type /thinkrail:asking-user-questions.

See it in use

One real session, replayed step by step: the request, each step at the moment it happened, and the answer, unedited. Long waits are shown faster, with the real time in the corner. Sample notes invented for this example: Rosewood Bakery and its Pantry Pal app idea are fictional, and so is every number.
The result
goal-and-requirements.mdWhat the session produced: goal-and-requirements.md, the file the session saved.

A short requirements document with a version 1 list, what waits for later and why, and the questions still open.

goal-and-requirements.md, the file the session saved.

Open the whole result
Try it

After installing, start a new session and say: My app idea is in idea-notes.md. Turn it into a requirements document I can hand to a developer, keep version 1 small, and save it as goal-and-requirements.md.

What else it can do, and its limits
  • Turns a raw idea into one goal and requirements document, keeping version 1 small
  • Drafts a first set of specs for an existing codebase from its code
  • Weighs product and design choices before building and records the decision
  • Plans multi step work as a shared to do list, and guides a finished change through a pull request
  • Made for the Thinkrail coding app: its question cards, spec tools and pull request steps rely on that app and a terminal; elsewhere the AI writes the files and marks its guesses as unconfirmed, as in this run
  • Drafts for you to review: specs stay marked draft until you approve them

Sample input Recorded Oct 24, 2026 in Claude Code 2.1.308 with Sonnet 5.5. The video replays that session; nothing in it was acted or edited.

What's inside 11 skills

  • asking-user-questionsUse when composing an ask_user_question round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.

    Use when composing an ask_user_question round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.

  • brainstormingUse 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.

    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.

  • choosing-a-workflowUse at the start of new project onboarding, PR lifecycle work including PR checks, or changes that require choosing product scope, user-visible behavior, or architecture. Not for continuing work already routed to a workflow, non-PR questions, checks, explanations, or localized fully specified work.

    Use at the start of new project onboarding, PR lifecycle work including PR checks, or changes that require choosing product scope, user-visible behavior, or architecture. Not for continuing work already routed to a workflow, non-PR questions, checks, explanations, or localized fully specified work.

  • importing-a-codebaseUse when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project.

    Use when asked to create the initial spec graph for an existing codebase that has source code but no specs. Normally reached via setting-up-a-project.

  • setting-up-a-projectUse 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. Not for ordinary work in an already-specced project.

    Use 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. Not for ordinary work in an already-specced project.

  • shipping-a-prUse 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. Not for reviewing a PR you are not shipping.

    Use 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. Not for reviewing a PR you are not shipping.

  • spec-graphUse 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 architecture decision.

    Use 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 architecture decision.

  • starting-a-new-projectUse when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing project.

    Use when the workspace is empty, has no code, and the user brings a raw project idea. Normally reached via setting-up-a-project; not for an existing project.

Show all 11 skills
  • todosUse when the user asks for a shared plan, a task needs at least three substantive execution steps, or a user-origin TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.

    Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a user-origin TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.

  • writing-specsUse when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

    Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

  • writing-workflow-skillsUse when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

    Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

About

Where this comes from. The public repository JetBrains/thinkrail at commit 0def253, under its Apache-2.0 license, copied without changes. JetBrains is not affiliated with Cheatcode and has not claimed this listing yet. New releases are repackaged after review, never synced automatically. If this is your project, write to admin@cheatcodehq.com to claim or remove it.

Something wrong with this listing, or it did not install? Tell us

Versions

v0.0.0-g0def253Listed from JetBrains/thinkrail at 0def253 · 2026-09-28