Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
itallstartedwithaidea avatar

Brainstorming

  • 56 installs
  • 31 repo stars
  • Updated April 12, 2026
  • itallstartedwithaidea/agent-skills

Brainstorming is an agent skill that turns vague requirements into an approved design brief through Socratic questioning—usable whenever a solo builder needs to map a problem before committing to code.

About

Brainstorming from Agent Skills™ is a journey-wide planning ritual for solo builders who otherwise let the agent start coding on half-formed requests. The skill positions the agent as a senior engineer who probes requirements: it asks about constraints, alternatives, and what you are explicitly not building, then outputs a shared design brief rather than a pull request. That brief becomes the measurable contract for every later phase—whether you are scoping an MVP landing page, choosing between monolith and services, or deciding what to defer past v1. Because it refuses to write code until questioning completes, it prevents expensive mid-sprint reversals when edge cases appear on day three. It pairs naturally with downstream planning skills once the human approves the brief. Prism catalogs it as methodology, not a one-off validator: use it at Idea when the opportunity is still fuzzy, at Validate when specs are thin, at Build when a feature spike needs reframing, and anytime you feel pressure to “just implement” without alignment.

  • Activates before any code is written and blocks implementation until the problem space is mapped
  • Uses targeted questions on edge cases, scalability, UX, and architectural trade-offs
  • Explores multiple viable approaches instead of jumping to the first solution
  • Produces a crystallized design brief that acts as the contract for later implementation
  • Enforces a deliberate pause between “I want X” and shipping code for X

Brainstorming by the numbers

  • 56 all-time installs (skills.sh)
  • +4 installs in the week ending Aug 2, 2026 (Skillselion tracking)
  • Ranked #1,583 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/itallstartedwithaidea/agent-skills --skill brainstorming

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs56
repo stars31
Security audit3 / 3 scanners passed
Last updatedApril 12, 2026
Repositoryitallstartedwithaidea/agent-skills

What it does

Run structured Socratic questioning before coding so vague feature ideas become an agreed design brief with explicit trade-offs and deferred scope.

Who is it for?

Best when you're facing ambiguous feature requests, multiple architectural paths, or hidden requirements that only show up under questioning.

Skip if: Runs where the design brief is already written, reviewed, and frozen—you should proceed to implementation or planning skills instead.

When should I use this skill?

A user presents a feature request without detailed specifications, or the problem has multiple viable architectural approaches.

What you get

You get a crystallized design brief with chosen approaches and deferred items, ready to hand off to implementation or a dedicated writing-plans skill once you approve it.

  • Crystallized design brief
  • Documented trade-offs and deferred scope
  • Shared human–agent implementation contract

Files

SKILL.mdMarkdownGitHub ↗

Brainstorming

Part of Agent Skills™ by googleadsagent.ai™

Description

Brainstorming is a Socratic design refinement skill that activates before any code is written. It transforms vague requirements and rough ideas into well-defined implementation plans through structured questioning, constraint discovery, and alternative exploration. The agent refuses to write code until the problem space is sufficiently mapped.

This skill enforces a deliberate pause between "I want X" and "here's the code for X." By asking targeted questions about edge cases, scalability concerns, user experience implications, and architectural trade-offs, the agent surfaces hidden requirements that would otherwise become expensive mid-implementation discoveries. The process mirrors how senior engineers naturally probe requirements before committing to an approach.

The output is a crystallized design brief: a shared understanding between human and agent of what will be built, why specific approaches were chosen, and what was explicitly deferred. This artifact becomes the contract against which all subsequent implementation is measured.

Use When

  • A user presents a feature request without detailed specifications
  • The problem has multiple viable architectural approaches with meaningful trade-offs
  • Requirements contain ambiguous terms that could be interpreted differently
  • The scope of work is unclear or potentially unbounded
  • You detect assumptions that need validation before implementation begins
  • The task involves integrating with unfamiliar systems or APIs

How It Works

graph TD
    A[Receive Rough Idea] --> B[Extract Core Intent]
    B --> C[Ask Clarifying Questions]
    C --> D{Ambiguities Resolved?}
    D -->|No| E[Explore Alternatives]
    E --> F[Present Trade-offs]
    F --> C
    D -->|Yes| G[Synthesize Design Brief]
    G --> H[Confirm with User]
    H -->|Rejected| C
    H -->|Accepted| I[Output Implementation-Ready Spec]

The brainstorming flow begins by extracting the core intent from the user's request, stripping away implementation assumptions. The agent then enters a questioning loop, probing constraints, exploring alternatives, and presenting trade-offs until all critical ambiguities are resolved. Only when the user confirms the synthesized design brief does the agent produce an implementation-ready specification.

Implementation

activation:
  trigger: "before_code_generation"
  conditions:
    - task_complexity > "trivial"
    - specification_completeness < 0.7

brainstorming_phases:
  - name: "Intent Extraction"
    actions:
      - parse_user_request
      - identify_nouns_as_entities
      - identify_verbs_as_operations
      - flag_ambiguous_terms

  - name: "Constraint Discovery"
    questions:
      - "What does success look like for this feature?"
      - "Who are the users and what are their primary workflows?"
      - "What are the hard constraints (budget, timeline, platform)?"
      - "What existing systems must this integrate with?"

  - name: "Alternative Exploration"
    actions:
      - generate_minimum_3_approaches
      - score_each_on: [complexity, maintainability, performance, time_to_ship]
      - present_comparison_table

  - name: "Design Brief Synthesis"
    output:
      - problem_statement
      - chosen_approach_with_rationale
      - explicit_non_goals
      - acceptance_criteria
      - estimated_task_breakdown

Best Practices

  • Never skip brainstorming for tasks rated above trivial complexity
  • Limit brainstorming rounds to 3-5 exchanges to avoid analysis paralysis
  • Always generate at least three alternative approaches before recommending one
  • Document what was explicitly excluded from scope as non-goals
  • Use concrete examples and scenarios rather than abstract descriptions
  • End every brainstorming session with a written design brief the user confirms

Platform Compatibility

PlatformSupportNotes
CursorFullNative SKILL.md activation
VS CodeFullVia Copilot agent mode
WindsurfFullVia Cascade rules
Claude CodeFullVia AGENTS.md
ClineFullVia .clinerules
aiderPartialVia conventions file

Related Skills

  • Writing Plans - Converts brainstorming design briefs into step-by-step implementation plans with verification commands
  • Executing Plans - Drives the approved plan through batch execution with checkpoints and rollback
  • Code Review - Quality gate that validates the implementation matches the brainstormed design brief

Keywords

brainstorming socratic-method design-refinement requirements-gathering before-coding alternative-exploration constraint-discovery specification

---

© 2026 googleadsagent.ai™ | Agent Skills™ | MIT License

Related skills

How it compares

Use instead of jumping straight from chat prompts to code generation when you still need shared intent and explicit deferrals.

FAQ

Who is brainstorming for?

Developers using Claude Code, Cursor, or similar agents who want a disciplined requirements pass before any implementation tokens are spent.

When should I use brainstorming?

Use it in Idea (research) when the opportunity is vague, Validate (scope) when specs are incomplete, Build (pm) before large features, and Ship (launch prep) when launch scope still has open architectural questions—any time code would be premature.

Is brainstorming safe to install?

It is conversational planning without built-in shell access by default; confirm what your agent runtime allows and review the Security Audits panel on this Prism page before enabling broader permissions.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.