brainstorming
You MUST use this before any creative work — creating features, building components, drafting documents, designing workflows, or modifying behavior. Explores your human partner's intent, requirements, and design before any implementation begins.
Surogate Agent (adapted from obra/superpowers) · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add invergent-ai/surogates --skill brainstormingAbout this skill
name: brainstorming description: "You MUST use this before any creative work — creating features, building components, drafting documents, designing workflows, or modifying behavior. Explores your human partner's intent, requirements, and design before any implementation begins." version: 1.0.0 author: Surogate Agent (adapted from obra/superpowers) license: MIT tags: [process, design, brainstorming]
Brainstorming Ideas Into Designs
Help turn your human partner's idea into a fully formed design 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 is being built, present the design and get approval before any implementation skill is invoked.
Anti-Pattern: "This Is Too Simple To Need A Design"
Every task goes through this process. A todo list, a single-function utility, a config change, a short report — 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 work), but you MUST present it and get approval.
Checklist
You MUST create a todo for each of these items and complete them in order:
- Explore project context — check files, docs, recent activity
- Offer visual support (if upcoming questions will involve visual content) — see Visuals section. This is its own message, not combined with a clarifying question.
- Ask clarifying questions — one at a time, understand purpose / constraints / success criteria
- Propose 2-3 approaches — with trade-offs and your recommendation
- Present design — in sections scaled to their complexity, get approval after each section
- Write design doc — save to
.surogate/specs/YYYY-MM-DD-<topic>.md - Spec self-review — inline check for placeholders, contradictions, ambiguity, scope (see below)
- Partner reviews written spec — ask your human partner to review the spec file before proceeding
- Transition to implementation — invoke
writing-plansviaskill_viewto create the implementation plan
Process Flow
digraph brainstorming {
"Explore project context" [shape=box];
"Visual questions ahead?" [shape=diamond];
"Offer visual support\n(own message, no other content)" [shape=box];
"Ask clarifying questions" [shape=box];
"Propose 2-3 approaches" [shape=box];
"Present design sections" [shape=box];
"Partner approves design?" [shape=diamond];
"Write design doc" [shape=box];
"Spec self-review\n(fix inline)" [shape=box];
"Partner approves spec?" [shape=diamond];
"Invoke writing-plans skill" [shape=doublecircle];
"Explore project context" -> "Visual questions ahead?";
"Visual questions ahead?" -> "Offer visual support\n(own message, no other content)" [label="yes"];
"Visual questions ahead?" -> "Ask clarifying questions" [label="no"];
"Offer visual support\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" -> "Partner approves design?";
"Partner approves design?" -> "Present design sections" [label="no, revise"];
"Partner approves design?" -> "Write design doc" [label="yes"];
"Write design doc" -> "Spec self-review\n(fix inline)";
"Spec self-review\n(fix inline)" -> "Partner approves spec?";
"Partner approves spec?" -> "Write design doc" [label="changes requested"];
"Partner approves spec?" -> "Invoke writing-plans skill" [label="approved"];
}
The terminal state is invoking writing-plans. Do NOT invoke any other implementation-shaped skill after brainstorming. The ONLY skill you invoke next is writing-plans.
The Process
Understanding the idea:
- Check out the current project state first (files, docs, recent activity).
- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of work that needs to be decomposed first.
- If the work is too large for a single spec, help your human partner decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
- For appropriately-scoped work, ask questions one at a time to refine the idea.
- Prefer multiple-choice questions via
ask_user_questionwhen feasible (faster to answer). Open-ended is fine too. - Only one question per message — if a topic needs more exploration, break it into multiple questions.
- Focus on understanding: purpose, constraints, success criteria.
Exploring approaches:
- Propose 2-3 different approaches with trade-offs.
- Present options conversationally with your recommendation and reasoning.
- Lead with your recommended option and explain why.
Presenting the design:
- Once you believe you understand what is being built, present the design.
- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced.
- Ask after each section whether it looks right so far.
- For software work, cover: architecture, components, data flow, error handling, testing. For other work, cover the analogous structure (e.g., document outline, section ownership, source material, review path).
- Be ready to go back and clarify if something doesn't make sense.
**Design
Read the complete source ↗