AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Brainstorm

skill-aksoftcode-aicrew-brainstorm · by AKSoftCode

Generate 3 materially different implementation options with trade-offs before coding, using project-specific brainstorm overrides when available.

↗ Website ↗ Repository
— No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add skill-aksoftcode-aicrew-brainstorm

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Brainstorm? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Brainstorm (Codex)

Use this skill when the user asks to brainstorm, compare approaches, or resolve design decisions before implementation.

Default output

Caveman/lean style by default. See ~/Agents/agents/caveman.md and ~/Agents/agents/context-economy.md. /normal or /lean off restores verbose.

Lookup order

Before generating options, check for project-specific guidance in this order:

  1. .ai/skills/agents/brainstorm.md
  2. AGENTS.md
  3. ~/Agents/agents/brainstorm.md

If a project override exists, follow it. If not, use the default workflow below.

Default workflow

  1. Restate the problem in one sentence.
  2. Identify the key decisions that must be resolved before coding.
  3. Generate exactly 3 materially different options.
  4. For each option, evaluate:
  • Complexity
  • Risk
  • Reversibility
  • Test surface
  • Prior art in the codebase
  1. Recommend one option with a short rationale.
  2. Ask the user to choose or modify an option before proceeding.

Guardrails

  • Do not invent domain rules, contracts, or constraints.
  • Tie non-obvious claims to code or docs when possible.
  • Prefer the smallest, most testable, most reversible option.
  • Flag options that weaken validation, auditability, or traceability.

Output format

BRAINSTORM:

Problem statement:

DECISIONS TO RESOLVE BEFORE CODING:
1. ...
2. ...
3. ...

OPTION A — ...
OPTION B — ...
OPTION C — ...

RECOMMENDATION:

OPEN QUESTIONS:
- ...

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills