AGENT SKILL

brainstorming

Structured Socratic questioning for exploring ideas and solutions. Use when exploring new features, evaluating approaches, or thinking through complex decisions. DO NOT USE FOR: architecture evaluation or SOLID analysis (use software-architecture), UI component design (use frontend-design), or coordinating implementation lanes (use parallel-execution).

使用场景前端开发
License 许可
MIT
最近更新
2026-08-16
Stars
★ 3
Forks
0

01 前言 Front Matter

name
brainstorming
description
Structured Socratic questioning for exploring ideas and solutions. Use when exploring new features, evaluating approaches, or thinking through complex decisions. DO NOT USE FOR: architecture evaluation or SOLID analysis (use software-architecture), UI component design (use frontend-design), or coordinating implementation lanes (use parallel-execution).

03 SKILL.md 正文

Brainstorming Skill

Guide for structured exploration of ideas through Socratic questioning.

When to Use

  • Exploring new feature ideas or requirements
  • Evaluating multiple solution approaches
  • Challenging assumptions about a problem
  • Breaking down complex decisions
  • Early-stage design discussions

Socratic Questioning Framework

1. Clarifying Questions

  • What do you mean by...?
  • What is the core problem we're solving?
  • Can you give an example?
  • What would success look like?

2. Probing Assumptions

  • What are we assuming here?
  • Why do we believe this is true?
  • What if the opposite were true?
  • What are we taking for granted?

3. Exploring Perspectives

  • How would [stakeholder] view this?
  • What would a user expect?
  • What would a skeptic say?
  • How have others solved similar problems?

4. Examining Evidence

  • What evidence supports this approach?
  • Are there counter-examples?
  • What data would change our mind?
  • How confident are we in this?

5. Considering Consequences

  • What happens if we do this?
  • What are the second-order effects?
  • What could go wrong?
  • What's the cost of being wrong?

6. Questioning the Question

  • Is this the right question to ask?
  • What question should we be asking instead?
  • Are we solving the right problem?

Brainstorming Session Structure

1. DEFINE (5 min)
   - State the problem/opportunity clearly
   - Identify constraints and goals

2. DIVERGE (15 min)
   - Generate many ideas without judgment
   - Build on each other's ideas
   - Encourage wild ideas

3. CHALLENGE (10 min)
   - Apply Socratic questions to top ideas
   - Identify hidden assumptions
   - Explore edge cases

4. CONVERGE (10 min)
   - Evaluate ideas against criteria
   - Combine complementary approaches
   - Select promising directions

5. NEXT STEPS (5 min)
   - Define concrete actions
   - Assign owners and timelines

Project-Specific Context

[CUSTOMIZE] Add domain-specific questions relevant to your project:

  • Industry-specific considerations
  • Technical constraints unique to your stack
  • Stakeholder perspectives to consider
  • Common assumptions in your domain

Output Artifacts

After brainstorming, document:

  1. Problem statement (refined)
  2. Key insights discovered
  3. Assumptions identified (and which were challenged)
  4. Top approaches with pros/cons
  5. Decision and rationale
  6. Open questions for future exploration

Gotchas

Trigger Gotcha Fix
"This approach seems good" in the first few minutes Premature convergence — first idea is never fully examined Enforce a DIVERGE phase before CONVERGE; exhaust alternatives before committing
Everyone agrees quickly with no pushback Groupthink — consensus silences better options Assign devil's advocate; use §2 Probing Assumptions questions to challenge the consensus
30+ minutes of questioning with no decision Analysis paralysis — endless questioning without converging Time-box phases using the Session Structure; reach CONVERGE by minute 30
Questions framed as "Shouldn't we use X?" Leading questions — forecloses alternatives before exploration Rephrase as open questions per §1 Clarifying format ("What are the options here?")
Socratic questions met with defensiveness Defensive responses — posture shuts down exploration Frame questions as discovery, not criticism; restate the exploration goal

04 同仓库更多 Skills

Grimblaz
Grimblaz/agent-orchestra

webapp-testing

Playwright end-to-end testing guidance for web apps, with practical patterns and setup steps. Use when creating or improving browser-based E2E coverage, test stability, and CI execution. DO NOT USE FOR: React component tests (use ui-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), or randomized property tests (use property-based-testing).

测试与质量前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

verification-before-completion

Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any "I'm finished" declaration; also when naming a baseline commit for a differential suite claim, when designing a mutation campaign or red-run evidence, when making an absence claim, a universal claim, or a one-time demonstration offered as a standing guarantee, when attributing a measurement or claiming a sweep or verification loop is complete, and when stating what a check or a CI suite will do about a change. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use code-review-intake).

★ 3
Grimblaz
Grimblaz/agent-orchestra

validation-methodology

Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or step execution flow (keep those in Code-Conductor).

★ 3
Grimblaz
Grimblaz/agent-orchestra

upstream-onboarding

Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a user-invocable agent receives a request referencing an existing GitHub issue and must load solution-authoring and upstream-onboarding at the opening phase. DO NOT USE FOR: subagent dispatches (which already operate within an assessed session context); post-merge review (use post-pr-review); research or non-tree subagents.

人力资源Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

ui-testing

Resilient React component testing strategies focusing on user behavior. Use when writing or reviewing component-level React tests, fixing flaky component tests, or establishing React testing patterns. DO NOT USE FOR: Playwright E2E tests (use webapp-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), UI component design (use frontend-design), or randomized property tests (use property-based-testing).

设计师测试与质量前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

ui-iteration

Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or major redesign strategy work (use Code-Smith or frontend-design).

设计师前端开发
★ 3