Superpowers Brainstorming

Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method

What task is this skill designed for?

Clarify a synthetic appointment-reminder feature where timing, audience and delivery channel are initially unspecified.

What input and output should you expect?

Input: The initial request, existing application constraints, intended users and known operational limits. Use fictional contact data and do not send reminders.

Output: An agreed problem statement, compared approaches and a proportionate design document that separates user decisions from proposed assumptions.

What does it need to run?

A conversational coding agent with access to the relevant project context. An optional visual companion has separate helper files and a local server; it is not required for a text-only design discussion.

Publisher README documents Claude Code, Codex and Cursor installation paths, among other harnesses. Tool availability and behavior depend on the host; this is publisher-declared support, not a cross-platform test result.

How should you approach installation?

1. Review the pinned folder and its referenced files before enabling the workflow. The folder belongs to the broader Superpowers plugin, not an independently verified standalone installer.
2. Follow the publisher README for your chosen coding-agent platform. The publisher documents several harnesses; use the instructions for your installed version and review plugin hooks and permissions.
3. Try the suggested task in a disposable repository with synthetic inputs. Check the acceptance list before applying the workflow to shared work.

Installation guide: discovery, dependencies and runtime checks

What files, accounts or data can it access?

Reads project material and writes design documents. Optional visual assistance can start a server and load an external branding resource; the repository README describes telemetry opt-out controls. Review those files before enabling the visual mode.

What does the skill cost?

No separate skill purchase is specified in the MIT-licensed source. Coding-agent subscriptions, model tokens, test compute and any external services have their own charges. Review or repeated execution can increase model usage.

What are its limits and alternatives?

The process can be excessive for a fully specified small edit. The current source includes an opt-out route and a fast path for clear tasks. Asking questions is only useful when the answers change the design; an approved-looking document cannot substitute for actual user agreement.

Use Writing Plans when the design is already agreed. Use a short written assumption list for a small reversible change where a separate discovery discussion adds little value.

What could you ask in a small trial?

Try this with a small sample:

Clarify this fictional reminder feature before implementation. Identify which missing decision changes the design most, compare feasible approaches and produce a short design with assumptions clearly attributed. Do not send messages or start a server.

How would you verify the result?

1. The design identifies who receives reminders, when and through which channel.
2. User decisions and proposed assumptions are distinguishable.
3. No implementation, external messages or optional server is started during the text-only trial.

Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.

Which source and license were checked?

Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder

Repository and current publisher guidance

Checked: 2026-10-27

MIT — repository LICENSE at the reviewed commit. Dependencies and external services retain their own terms. License evidence

Report an error, license concern or request a new review.