agentleFS
GabrieleDattileGabrieleDattile/agent-superpowers/skills/workflow/feature-brainstormer/SKILL.md

feature-brainstormer

Skill1 starsChanged 15 days agoMITView on GitHub

Socratic feature brainstorming and requirement refiner. Prevents premature code generation by teasing out specifications, clarifying architectural tradeoffs, and establishing non-goals.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing any code, formulate up to 3 high-impact clarifying questions covering:

    line 30
  2. Distinctive:

    Ask the user for explicit approval: *"Does this plan match your vision?

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

💡 Skill: Feature Brainstormer (Socratic Requirements Refiner)

1. When to Trigger (Routing)

  • TRIGGER WHEN:
    • The user requests a brand-new feature, component, tool, or architecture with open-ended or ambiguous wording.
    • The user says: "help me design X", "how should we build Y", or "brainstorm a solution for Z".
  • DO NOT TRIGGER WHEN:
    • The user provided a hyper-specific, line-by-line task instruction with no architectural ambiguity.
    • The task is an urgent bug fix (route directly to ghost-runner).

2. Fundamental Philosophy

"The cost of fixing a bad assumption in code is 100x higher than asking a clarifying question upfront. Feature Brainstormer forces the agent to pause, probe for architectural constraints, and define acceptance criteria before touching an editor."


3. Operational Protocol

Step 1: Clarification & Trade-Off Interview

Before writing any code, formulate up to 3 high-impact clarifying questions covering:

  1. Target Persona & Usage Pattern: CLI, Web, API, background worker?
  2. Persistence & State: Ephemeral in-memory, SQLite, PostgreSQL, JSON files?
  3. Non-Goals & Scope Limits: What should this feature explicitly NOT do in v1?

Step 2: Architecture & Flow Proposal

Draft a concise Markdown specification including:

  • Input/Output data schema.
  • Expected error modes and fallback behaviors.
  • Dependency impacts on existing code modules.

Step 3: Phase Gate Confirmation

  • Ask the user for explicit approval: "Does this plan match your vision? Once confirmed, I will instantiate an isolated worktree and proceed with implementation."

4. Guardrails & Negative Constraints

  • ❌ NEVER output full code files during the brainstorming phase.
  • ❌ NEVER ask trivial questions that can be answered by inspecting the current repository.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.