brainstorming — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited brainstorming (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Part of Agent Skills™ by googleadsagent.ai™
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.
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.
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| Platform | Support | Notes |
|---|---|---|
| Cursor | Full | Native SKILL.md activation |
| VS Code | Full | Via Copilot agent mode |
| Windsurf | Full | Via Cascade rules |
| Claude Code | Full | Via AGENTS.md |
| Cline | Full | Via .clinerules |
| aider | Partial | Via conventions file |
brainstorming socratic-method design-refinement requirements-gathering before-coding alternative-exploration constraint-discovery specification
© 2026 googleadsagent.ai™ | Agent Skills™ | MIT License
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.