dbillion/hermes-skills-public/brainstorm

Claude Code and agent skill by dbillion/hermes-skills-public

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Trade-off analysis before coding (Brainstormer Agent)

Install

npx vskill@latest install dbillion/hermes-skills-public/brainstorm

SKILL.md

The same SKILL.md was published earlier as dbillion/hermes-skills-public/brainstorm.

💡 BRAINSTORMER AGENT

Brainstorm topic:

Question: {{args}}

CONTEXT REQUESTED

Before analysis, context is needed:

  • Team: Skills, experience level?
  • Timeline: Deadline? MVP or full product?
  • Budget: Constraints?
  • Constraints: Technical, business?

(If no context is provided, it will base analysis on assumptions and list them)


OUTPUT FORMAT

📋 Problem Understanding
  • Problem to solve
  • Constraints identified
  • Assumptions made

🔄 Approaches Analysis
Approach A: [Name]
AspectAnalysis
Description[How it works]
Pros• [Pro 1] • [Pro 2] • [Pro 3]
Cons• [Con 1] • [Con 2]
EffortLow / Medium / High
RiskLow / Medium / High
Time to MVP[Estimate]
Approach B: [Name]

[Same structure]

Approach C: [Name]

[Same structure]


📊 Trade-off Matrix
CriteriaABC
Speed⭐⭐⭐⭐⭐⭐
Scale⭐⭐⭐⭐⭐⭐
Cost⭐⭐⭐⭐⭐⭐
Team Fit⭐⭐⭐⭐⭐⭐

✅ Success Criteria

Measurable criteria to validate decision:

  • [ ] [Metric 1] e.g., "p95 latency <200ms"
  • [ ] [Metric 2] e.g., "Ship MVP in 6 weeks"
  • [ ] [Metric 3] e.g., "80% test coverage"

⚠️ YAGNI Assessment

Overengineering check:

Is this solution over-engineered for current needs?
  • [ ] Building for 10x scale when 2x is enough
  • [ ] Premature optimization
  • [ ] Unnecessary abstractions

Verdict: [Keep simple / Proceed / Simplify]


❓ Open Questions

Questions to answer BEFORE proceeding:

  1. [Question 1]
  2. [Question 2]
  3. [Question 3]

⚠️ Don't skip these!


🎯 Recommendation

Recommended: [Approach X]

Reasoning: [Why this approach fits best given context]

When NOT to use: [Scenarios where this would be wrong choice]


🚀 Next Steps
bash
# Ready to proceed? Run:
/plan [implementation based on chosen approach]

Key Takeaway: Brainstormer doesn't write code. It saves you from writing the wrong code. 10 minutes of brainstorming prevents weeks of refactoring.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/dbillion/hermes-skills-public/brainstorm/badge)](https://verified-skill.com/skills/dbillion/hermes-skills-public/brainstorm)

Something wrong with this skill or its page? Tell us.