New to Claude Skills? Learn how to install them β†’

vudovn on GitHub

Brainstorming Protocol

Free

Enhance clarity and communication for complex requests.

by vudovn8.1k stars on vudovn/ag-kit
1 views
Updated Jul 30, 2026
Get this skill

Free Β· Opens the source repo

What Brainstorming Protocol does

The Brainstorming Protocol is designed to facilitate effective communication and clarity when dealing with complex or vague requests in software development. It employs a Socratic questioning technique to ensure that all necessary details are gathered before any coding begins. This is particularly useful for teams that frequently encounter unclear requirements or are tasked with developing new features. By adhering to this protocol, developers can minimize misunderstandings and ensure that they are addressing the right problems from the outset.

At the core of this skill is the Socratic Gate, which mandates that developers ask a minimum of three questions before proceeding with implementation. These questions focus on the purpose of the request, the intended users, and the scope of the project. This structured approach helps to clarify the objectives and constraints of a request, ensuring that all stakeholders have a shared understanding of the task at hand. The protocol also emphasizes the importance of checking past context in memory to avoid redundant questioning and to build upon prior knowledge.

In addition to its questioning framework, the Brainstorming Protocol includes guidelines for dynamic question generation, progress reporting, and error handling. This ensures that communication remains transparent and actionable throughout the development process. By maintaining a status board and employing clear error response strategies, developers can effectively manage their tasks and address issues as they arise. This skill is particularly beneficial for teams working in agile environments where adaptability and clear communication are key.

Overall, the Brainstorming Protocol is an essential tool for developers and designers who want to enhance their collaborative processes and ensure that complex requests are handled with clarity and precision. It fosters a culture of inquiry and transparency, ultimately leading to more successful project outcomes.

When to use it

Use this protocol when faced with vague requirements, new feature requests, or updates that lack clarity.

When not to use it

Avoid using this skill for straightforward tasks where requirements are clear and well-defined.

What you can build with it

Clarifying a New Feature Request

When a stakeholder requests a new feature without sufficient details, use the protocol to ask targeted questions that clarify the purpose, users, and scope.

Handling Vague Requirements

In scenarios where requirements are unclear, the protocol helps ensure that all necessary information is gathered before implementation begins.

Managing Progress on Complex Tasks

Utilize the progress reporting aspect of the protocol to keep stakeholders informed about the status of complex projects.

How to install Brainstorming Protocol

View source

1. Install with the skills CLI

npx skills add vudovn/ag-kit/brainstorming --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by vudovn

Brainstorming & Communication Protocol

MANDATORY: Use for complex/vague requests, new features, updates.


πŸ›‘ SOCRATIC GATE (ENFORCEMENT)

When to Trigger

PatternAction
"Build/Create/Make [thing]" without detailsπŸ›‘ ASK 3 questions
Complex feature or architectureπŸ›‘ Clarify before implementing
Update/change requestπŸ›‘ Confirm scope
Vague requirementsπŸ›‘ Ask purpose, users, constraints

🧠 Memory Check (2026.5.13 β€” Before Questioning)

Before asking questions, check if past context exists:

0. CHECK MEMORY β€” Does .agents/memory/MEMORY.md exist?
   β†’ YES: Read index. Apply relevant past decisions silently.
          Skip questions already answered in memory.
   β†’ NO: Proceed with standard Socratic Gate.

🚫 MANDATORY: 3 Questions Before Implementation

  1. STOP - Do NOT start coding
  2. CHECK - Read .agents/memory/ for past context on this topic
  3. ASK - Minimum 3 questions (skip any already answered via memory):
    • 🎯 Purpose: What problem are you solving?
    • πŸ‘₯ Users: Who will use this?
    • πŸ“¦ Scope: Must-have vs nice-to-have?
  4. WAIT - Get response before proceeding
  5. SAVE - After brainstorming, save key decisions: /remember [decision]

🧠 Dynamic Question Generation

β›” NEVER use static templates. Read dynamic-questioning.md for principles.

Core Principles

PrincipleMeaning
Questions Reveal ConsequencesEach question connects to an architectural decision
Context Before ContentUnderstand greenfield/feature/refactor/debug context first
Minimum Viable QuestionsEach question must eliminate implementation paths
Generate Data, Not AssumptionsDon't guessβ€”ask with trade-offs

Question Generation Process

1. Parse request β†’ Extract domain, features, scale indicators
2. Identify decision points β†’ Blocking vs. deferable
3. Generate questions β†’ Priority: P0 (blocking) > P1 (high-leverage) > P2 (nice-to-have)
4. Format with trade-offs β†’ What, Why, Options, Default

Question Format (MANDATORY)

### [PRIORITY] **[DECISION POINT]**

**Question:** [Clear question]

**Why This Matters:**
- [Architectural consequence]
- [Affects: cost/complexity/timeline/scale]

**Options:**
| Option | Pros | Cons | Best For |
|--------|------|------|----------|
| A | [+] | [-] | [Use case] |

**If Not Specified:** [Default + rationale]

For detailed domain-specific question banks and algorithms, see: dynamic-questioning.md


Progress Reporting (PRINCIPLE-BASED)

PRINCIPLE: Transparency builds trust. Status must be visible and actionable.

Status Board Format

AgentStatusCurrent TaskProgress
[Agent Name]βœ…πŸ”„β³βŒβš οΈ[Task description][% or count]

Status Icons

IconMeaningUsage
βœ…CompletedTask finished successfully
πŸ”„RunningCurrently executing
⏳WaitingBlocked, waiting for dependency
❌ErrorFailed, needs attention
⚠️WarningPotential issue, not blocking

Error Handling (PRINCIPLE-BASED)

PRINCIPLE: Errors are opportunities for clear communication.

Error Response Pattern

1. Acknowledge the error
2. Explain what happened (user-friendly)
3. Offer specific solutions with trade-offs
4. Ask user to choose or provide alternative

Error Categories

CategoryResponse Strategy
Port ConflictOffer alternative port or close existing
Dependency MissingAuto-install or ask permission
Build FailureShow specific error + suggested fix
Unclear ErrorAsk for specifics: screenshot, console output

Completion Message (PRINCIPLE-BASED)

PRINCIPLE: Celebrate success, guide next steps.

Completion Structure

1. Success confirmation (celebrate briefly)
2. Summary of what was done (concrete)
3. How to verify/test (actionable)
4. Next steps suggestion (proactive)

Communication Principles

PrincipleImplementation
ConciseNo unnecessary details, get to point
VisualUse emojis (βœ…πŸ”„β³βŒ) for quick scanning
Specific"~2 minutes" not "wait a bit"
AlternativesOffer multiple paths when stuck
ProactiveSuggest next step after completion

Anti-Patterns (AVOID)

Anti-PatternWhy
Jumping to solutions before understandingWastes time on wrong problem
Assuming requirements without askingCreates wrong output
Over-engineering first versionDelays value delivery
Ignoring constraintsCreates unusable solutions
"I think" phrasesUncertainty β†’ Ask instead

Frequently asked questions about Brainstorming Protocol

Similar skills