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

Brainstorming

skill-hnikoloski-imlazy-imlazy-brainstorm · by hnikoloski

For Heavy-tier tasks only — turn ideas into specs through one-question-at-a-time dialogue, present design in sections, write spec doc, hand off to planning skill

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

Install

$ agentstack add skill-hnikoloski-imlazy-imlazy-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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-hnikoloski-imlazy-imlazy-brainstorm)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Brainstorming? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

brainstorming

When to use

The router invokes this skill ONLY for Heavy-tier tasks (multi-component, unclear scope, new subsystem, or user explicitly requests design/plan/architecture).

For Standard or Quick tier, skip brainstorming entirely — go straight to Skill(imlazy-planning) in light mode or inline execution.

This skill's job: produce a spec doc that Skill(imlazy-planning) can turn into an implementation plan.

Process

  1. Explore project context — read existing files, check recent commits before asking any questions.
  2. Ask clarifying questions one at a time. Prefer multiple-choice. One question per message. Focus on: purpose, constraints, success criteria.
  3. Assess scope first. If the request describes multiple independent subsystems, flag this and help the user decompose into sub-projects before proceeding. Each sub-project gets its own spec → plan → implementation cycle.
  4. Propose 2-3 approaches with tradeoffs and your recommendation. Lead with the recommended option.
  5. Present the design in sections. Get user approval section by section. Cover: architecture, components, data flow, error handling, testing.
  6. Write the spec to docs/imlazy/specs/YYYY-MM-DD--design.md. Self-review for placeholders, contradictions, scope, and ambiguity. Fix inline.
  7. Ask the user to review the spec before proceeding.
  8. Hand off to Skill(imlazy-planning) in full mode. Do not invoke any other skill.

Key principles

  • One question at a time. Multiple-choice preferred over open-ended.
  • YAGNI ruthlessly — cut unrequested features from the design.
  • Always propose 2-3 approaches before settling.
  • Explore the existing codebase before proposing changes. Follow existing patterns. Targeted improvements to broken code you are touching are fine; unrelated refactoring is not.
  • Be flexible — go back and clarify when something does not make sense.

Spec self-review checklist

Before asking the user to review, check:

  1. Placeholder scan — any TBD/TODO/incomplete sections?
  2. Internal consistency — do sections contradict each other?
  3. Scope check — focused enough for one implementation plan?
  4. Ambiguity check — can any requirement be interpreted two ways?

Fix issues inline. No need to re-review.

Hand-off

After the user approves the spec, invoke Skill(imlazy-planning) in full mode. Do not invoke any other skill — imlazy-planning is the terminal state for this skill.

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 Productivity