Clarify intent, requirements, and solution direction before any creative implementation work.
The material indicates this is essentially an open-source prompt-only brainstorming/workflow skill with no required secrets and no declared remote endpoints, so overall risk is low. The README does instruct checking project files, writing a design doc, and committing changes, but these appear to be workflow directions rather than standalone execution capability, which warrants only limited caution.
The material explicitly states that no keys or environment variables are required, and there is no visible request to collect or store tokens, API keys, or other credentials, leaving minimal credential exposure.
No remote endpoints or external service calls are declared; based on the provided material, there is no indication that user data is sent to third-party network destinations.
The system flags it as prompt-only, and the material itself is a set of workflow constraints and dialogue instructions; although it mentions later invoking other skills and committing a design doc, it does not show that this skill itself can spawn local processes or execute code.
The README instructs users to 'check files, docs, recent commits' and save a design under `docs/superpowers/specs/...`, indicating an expected workflow that reads project context and writes repository files; this is a typical skill data-access pattern with no clear signs of over-privileged access.
It comes from an open-source GitHub repository, which is a clear risk-reducing factor due to auditability; however, the license is unspecified, stars are 0, and maintenance status is unknown, so community validation and upkeep evidence are weak, warranting some supply-chain caution.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "brainstorming" skill from askskill: 1. Download https://raw.githubusercontent.com/obra/superpowers/main/skills/brainstorming/SKILL.md 2. Save it as ~/.claude/skills/brainstorming/SKILL.md 3. Reload skills and tell me it's ready
I need to add a bulk refund feature to an e-commerce admin panel. Do not write code yet. First, brainstorm the user goals, key scenarios, edge cases, risks, and possible UX and technical approaches.
A structured requirement and solution outline covering goals, scenarios, constraints, risks, and implementation directions.
I want to design a reusable date filter component. First, brainstorm usage scenarios, user interaction patterns, state design, accessibility requirements, and API options, then recommend an approach.
A comparison of multiple design options and a recommended component approach suitable for implementation.
I want to change the sending logic of an existing notification system. Before making changes, brainstorm the possible impacts on user experience, business rules, failure cases, rollback strategy, and testing priorities.
A change impact assessment and pre-implementation checklist to help make the update safely.
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
<HARD-GATE> Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity. </HARD-GATE>Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
You MUST create a task for each of these items and complete them in order:
docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md and commitdigraph brainstorming {
"Explore project context" [shape=box];
"Visual questions ahead?" [shape=diamond];
"Offer Visual Companion\n(own message, no other content)" [shape=box];
"Ask clarifying questions" [shape=box];
"Propose 2-3 approaches" [shape=box];
"Present design sections" [shape=box];
"User approves design?" [shape=diamond];
"Write design doc" [shape=box];
"Spec self-review\n(fix inline)" [shape=box];
"User reviews spec?" [shape=diamond];
"Invoke writing-plans skill" [shape=doublecircle];
"Explore project context" -> "Visual questions ahead?";
"Visual questions ahead?" -> "Offer Visual Companion\n(own message, no other content)" [label="yes"];
"Visual questions ahead?" -> "Ask clarifying questions" [label="no"];
"Offer Visual Companion\n(own message, no other content)" -> "Ask clarifying questions";
"Ask clarifying questions" -> "Propose 2-3 approaches";
"Propose 2-3 approaches" -> "Present design sections";
"Present design sections" -> "User approves design?";
"User approves design?" -> "Present design sections" [label="no, revise"];
"User approves design?" -> "Write design doc" [label="yes"];
"Write design doc" -> "Spec self-review\n(fix inline)";
"Spec self-review\n(fix inline)" -> "User reviews spec?";
"User reviews spec?" -> "Write design doc" [label="changes requested"];
"User reviews spec?" -> "Invoke writing-plans skill" [label="approved"];
}
The terminal state is invoking writing-plans. Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.
Understanding the idea:
…
Turn requirements into a clear step-by-step execution plan before implementation.
Set conversation rules to discover and invoke skills before replying.
Systematically investigate bugs, test failures, and unexpected behavior before fixing.
Helps decide merge, PR, or cleanup steps after branch work is complete.
Execute implementation plans by splitting and advancing independent tasks in-session.
Verify results before claiming work is complete, fixed, or passing.
Turn rough ideas into actionable designs through structured questioning and validation.
Brainstorm product ideas, explore problems, and challenge assumptions with an AI partner.
Plan with pseudocode first, refine approaches, then translate into working code.
Build and refine UI/UX with design exploration, frontend setup, and integration.
Compare 2-3 approaches before execution to choose a stronger solution.
Implement features and fixes by writing tests before production code.