Quick Brainstorm
Lightweight brainstorm — 5 versions with estimated probabilities + assumption surfacing. Use when: brainstorm this, give me options, what are my options, quick brainstorm, /quick-brainstorm.
Install
$ agentstack add skill-exiao-pm-skills-quick-brainstorm ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-exiao-pm-skills-quick-brainstorm) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Quick Brainstorm
Single-pass divergent thinking. No sub-agents, no heavy frameworks.
When the user gives you a question or problem, respond with:
- 5 distinct versions/approaches — each meaningfully different, not variations on a theme. For each, include:
- A short descriptive name
- 2-3 sentence explanation
- Estimated probability of success (as a %)
- Why this one might be the right pick
- Key assumptions — State what assumptions you made that would significantly change your answer if they were false. These are the hidden beliefs your ranking rests on.
- Your ranking — After all options and assumptions, state your preferred order with a one-line justification per option. The user wants your opinion, not just a menu.
Rules
- Keep it tight. No walls of text.
- Probabilities should sum to roughly 100% if the options are mutually exclusive, or can overlap if they're not.
- Be honest about uncertainty. If you don't know, say so.
- The assumptions section is the most valuable part. Don't phone it in.
Follow-up: JTBD narrowing
After brainstorming, if the user hasn't picked yet, offer to run a "jobs to be done" analysis on the options. Ask: "What are the jobs this [page/feature/system] needs to do?" Then score each brainstorm option against the jobs. This consistently surfaces the right pick faster than comparing options in the abstract. Especially powerful for UX/UI decisions where the glance-mode vs work-mode split determines what gets prime screen real estate.
- When brainstorming UX/design alternatives, each option should be a different paradigm (leaderboard vs kanban vs terminal log vs heatmap vs diff viewer), not variations on a theme (table with sidebar vs table without sidebar).
- When the user asks to "map out" or wireframe all options, render each as a full ASCII mockup with realistic data. Don't abbreviate. Users can't compare "a table" vs "a kanban" in prose; they need to see 30+ lines of ASCII showing exactly what each layout looks like with real column headers, data rows, and interactive elements.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: exiao
- Source: exiao/pm-skills
- License: Apache-2.0
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.