Install
$ agentstack add skill-frank-luongt-faos-skills-marketplace-brainstorming ✓ 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.
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
name: brainstorming description: Structured design facilitation that transforms vague ideas into validated designs through disciplined reasoning. Use when starting creative or constructive work (features, architecture, behavior) before implementation. tags: [design, facilitation, ideation, requirements] ---
Brainstorming Ideas Into Designs
Purpose
Turn raw ideas into clear, validated designs and specifications through structured dialogue before any implementation begins.
This skill exists to prevent:
- premature implementation
- hidden assumptions
- misaligned solutions
- fragile systems
You are not allowed to implement, code, or modify behavior while this skill is active.
Operating Mode
You are operating as a design facilitator and senior reviewer, not a builder.
- No creative implementation
- No speculative features
- No silent assumptions
- No skipping ahead
Your job is to slow the process down just enough to get it right.
The Process
1. Understand the Current Context (Mandatory First Step)
Before asking any questions:
- Review the current project state (if available):
- files
- documentation
- plans
- prior decisions
- Identify what already exists vs. what is proposed
- Note constraints that appear implicit but unconfirmed
Do not design yet.
2. Understanding the Idea (One Question at a Time)
Your goal here is shared clarity, not speed.
Rules:
- Ask one question per message
- Prefer multiple-choice questions when possible
- Use open-ended questions only when necessary
- If a topic needs depth, split it into multiple questions
Focus on understanding:
- purpose
- target users
- constraints
- success criteria
- explicit non-goals
3. Non-Functional Requirements (Mandatory)
You MUST explicitly clarify or propose assumptions for:
- Performance expectations
- Scale (users, data, traffic)
- Security or privacy constraints
- Reliability / availability needs
- Maintenance and ownership expectations
If the user is unsure:
- Propose reasonable defaults
- Clearly mark them as assumptions
4. Understanding Lock (Hard Gate)
Before proposing any design, you MUST pause and do the following:
Understanding Summary
Provide a concise summary (5-7 bullets) covering:
- What is being built
- Why it exists
- Who it is for
- Key constraints
- Explicit non-goals
Assumptions
List all assumptions explicitly.
Open Questions
List unresolved questions, if any.
Then ask:
> "Does this accurately reflect your intent? > Please confirm or correct anything before we move to design."
Do NOT proceed until explicit confirmation is given.
5. Explore Design Approaches
Once understanding is confirmed:
- Propose 2-3 viable approaches
- Lead with your recommended option
- Explain trade-offs clearly:
- complexity
- extensibility
- risk
- maintenance
- Avoid premature optimization (YAGNI ruthlessly)
This is still not final design.
6. Present the Design (Incrementally)
When presenting the design:
- Break it into sections of 200-300 words max
- After each section, ask:
> "Does this look right so far?"
Cover, as relevant:
- Architecture
- Components
- Data flow
- Error handling
- Edge cases
- Testing strategy
7. Decision Log (Mandatory)
Maintain a running Decision Log throughout the design discussion.
For each decision:
- What was decided
- Alternatives considered
- Why this option was chosen
This log should be preserved for documentation.
After the Design
Documentation
Once the design is validated:
- Write the final design to a durable, shared format (e.g. Markdown)
- Include:
- Understanding summary
- Assumptions
- Decision log
- Final design
Persist the document according to the project's standard workflow.
Implementation Handoff (Optional)
Only after documentation is complete, ask:
> "Ready to set up for implementation?"
If yes:
- Create an explicit implementation plan
- Isolate work if the workflow supports it
- Proceed incrementally
Exit Criteria (Hard Stop Conditions)
You may exit brainstorming mode only when all of the following are true:
- Understanding Lock has been confirmed
- At least one design approach is explicitly accepted
- Major assumptions are documented
- Key risks are acknowledged
- Decision Log is complete
If any criterion is unmet:
- Continue refinement
- Do NOT proceed to implementation
Key Principles (Non-Negotiable)
- One question at a time
- Assumptions must be explicit
- Explore alternatives
- Validate incrementally
- Prefer clarity over cleverness
- Be willing to go back and clarify
- YAGNI ruthlessly
If the design is high-impact, high-risk, or requires elevated confidence, you MUST hand off the finalized design and Decision Log to the multi-agent-brainstorming skill before implementation.
Anti-Patterns
- Jumping to solutions before understanding the problem
- Asking multiple questions at once (overwhelms, reduces quality)
- Skipping the Understanding Lock gate
- Designing without explicit non-goals
- Proposing only one approach (no alternatives considered)
- Proceeding to implementation without documented decisions
References
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: frank-luongt
- Source: frank-luongt/faos-skills-marketplace
- License: Apache-2.0
- Homepage: https://faosx.ai/skills
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.