How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

brainstorm - Prompt - OpenSmartRoute

Name: brainstorm
Author: pmweekly

Prompt file imported from pmweekly/one-station (.github/prompts/brainstorm.prompt.md). Copyright stays with the author.

Brainstorm

Generate creative product ideas or experiment designs from three perspectives (PM, Designer, Engineer), tailored to whether you're working on an existing product or building something new.

Examples

/brainstorm ideas existing Mobile banking app engagement
/brainstorm ideas new AI-powered meal planning for busy parents
/brainstorm experiments existing Onboarding flow redesign
/brainstorm experiments new Marketplace for freelance designers
/brainstorm

Workflow

Step 1: Determine Mode

Parse the arguments to identify two dimensions:

What to brainstorm: ideas (feature concepts) or experiments (validation tests)
Product stage: existing (continuous discovery) or new (initial discovery)

If either dimension is missing, ask the user. If both are missing, ask:

"Are you brainstorming ideas for what to build, or experiments to validate assumptions?"
"Is this for an existing product or a new product concept?"

Step 2: Gather Context

Ask the user for context. Be conversational — ask the most critical question first:

For existing products:

What is the product? Who are current users?
What opportunity area or problem space are you exploring?
Any constraints (technical debt, platform limitations, team capacity)?
What has been tried before?

For new products:

What is the product concept? What problem does it solve?
Who is the target user? What's their current alternative?
What stage are you at? (napkin sketch, validated problem, early prototype)
What are the riskiest assumptions?

Accept context from uploaded files (PRDs, research docs, strategy decks), pasted text, or conversation.

Step 3: Generate Output

If brainstorming ideas — apply the brainstorm-ideas-existing or brainstorm-ideas-new skill:

Generate ideas from three perspectives: Product Manager (user value, business impact), Designer (UX, delight, accessibility), Engineer (technical innovation, platform leverage, scalability)
For each idea: name, description, target user impact, feasibility assessment
Rank the top 5 ideas with rationale
Flag which ideas could be quick wins vs. strategic bets

If brainstorming experiments — apply the brainstorm-experiments-existing or brainstorm-experiments-new skill:

For existing products: suggest A/B tests, prototypes, fake-door tests, wizard-of-oz, concierge experiments, and spikes
For new products: create XYZ+S hypotheses and suggest pretotype experiments (landing pages, explainer videos, pre-orders, concierge MVPs)
For each experiment: hypothesis, method, success criteria, effort estimate, expected timeline
Rank by learning-per-effort ratio

Step 4: Deepen and Iterate

After presenting initial results, offer:

"Want me to detail any of these ideas into a fuller spec?"
"Should I identify assumptions behind the top ideas?" (chains into the identify-assumptions-existing or identify-assumptions-new skill)
"Want to design experiments to validate the top ideas?" (chains into experiment mode)
"Should I prioritize these against your current backlog?" (chains into the prioritize-features skill)

Output Format

For Ideas:

## Brainstorm: [Product/Feature Area]
**Mode**: Ideas for [existing/new] product
**Context**: [1-2 sentence summary]

### PM Perspective
1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L]
2. ...

### Designer Perspective
1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L]
2. ...

### Engineer Perspective
1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L]
2. ...

### Top 5 Recommendations
| Rank | Idea | Why | Quick Win? |
|------|------|-----|------------|

### Next Steps
[What to do with these ideas]

For Experiments:

## Experiment Design: [Product/Feature Area]
**Mode**: Experiments for [existing/new] product

### Hypotheses
1. **[Hypothesis]** — XYZ format: [X]% of [Y] will [Z] within [S timeframe]

### Recommended Experiments
| # | Experiment | Tests Hypothesis | Method | Effort | Timeline |
|---|-----------|-----------------|--------|--------|----------|

### Experiment Details
[For each experiment: setup, success criteria, risks, what you'll learn]

Notes

For existing products, ground ideas in current user behavior and validated problems
For new products, focus on desirability and feasibility risks first
If the user uploads a research doc or interview transcript, extract insights before brainstorming
Encourage breadth first, then depth — generate many ideas before evaluating

Install brainstorm and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

# Brainstorm Generate creative product ideas or experiment designs from three perspectives (PM, Designer, Engineer), tailored to whether you're working on an existing product or building something new. ## Examples ```text /brainstorm ideas existing Mobile banking app engagement /brainstorm ideas new AI-powered meal planning for busy parents /brainstorm experiments existing Onboarding flow redesign /brainstorm experiments new Marketplace for freelance designers /brainstorm ``` ## Workflow ### Step 1: Determine Mode Parse the arguments to identify two dimensions: 1. **What to brainstorm**: `ideas` (feature concepts) or `experiments` (validation tests) 2. **Product stage**: `existing` (continuous discovery) or `new` (initial discovery) If either dimension is missing, ask the user. If both are missing, ask: - "Are you brainstorming **ideas** for what to build, or **experiments** to validate assumptions?" - "Is this for an **existing** product or a **new** product concept?" ### Step 2: Gather Context Ask the user for context. Be conversational — ask the most critical question first: **For existing products:** - What is the product? Who are current users? - What opportunity area or problem space are you exploring? - Any constraints (technical debt, platform limitations, team capacity)? - What has been tried before? **For new products:** - What is the product concept? What problem does it solve? - Who is the target user? What's their current alternative? - What stage are you at? (napkin sketch, validated problem, early prototype) - What are the riskiest assumptions? Accept context from uploaded files (PRDs, research docs, strategy decks), pasted text, or conversation. ### Step 3: Generate Output **If brainstorming ideas** — apply the **brainstorm-ideas-existing** or **brainstorm-ideas-new** skill: - Generate ideas from three perspectives: Product Manager (user value, business impact), Designer (UX, delight, accessibility), Engineer (technical innovation, platform leverage, scalability) - For each idea: name, description, target user impact, feasibility assessment - Rank the top 5 ideas with rationale - Flag which ideas could be quick wins vs. strategic bets **If brainstorming experiments** — apply the **brainstorm-experiments-existing** or **brainstorm-experiments-new** skill: - For existing products: suggest A/B tests, prototypes, fake-door tests, wizard-of-oz, concierge experiments, and spikes - For new products: create XYZ+S hypotheses and suggest pretotype experiments (landing pages, explainer videos, pre-orders, concierge MVPs) - For each experiment: hypothesis, method, success criteria, effort estimate, expected timeline - Rank by learning-per-effort ratio ### Step 4: Deepen and Iterate After presenting initial results, offer: - "Want me to **detail** any of these ideas into a fuller spec?" - "Should I **identify assumptions** behind the top ideas?" (chains into the `identify-assumptions-existing` or `identify-assumptions-new` skill) - "Want to **design experiments** to validate the top ideas?" (chains into experiment mode) - "Should I **prioritize** these against your current backlog?" (chains into the `prioritize-features` skill) ## Output Format ### For Ideas: ```markdown ## Brainstorm: [Product/Feature Area] **Mode**: Ideas for [existing/new] product **Context**: [1-2 sentence summary] ### PM Perspective 1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L] 2. ... ### Designer Perspective 1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L] 2. ... ### Engineer Perspective 1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L] 2. ... ### Top 5 Recommendations | Rank | Idea | Why | Quick Win? | |------|------|-----|------------| ### Next Steps [What to do with these ideas] ``` ### For Experiments: ```markdown ## Experiment Design: [Product/Feature Area] **Mode**: Experiments for [existing/new] product ### Hypotheses 1. **[Hypothesis]** — XYZ format: [X]% of [Y] will [Z] within [S timeframe] ### Recommended Experiments | # | Experiment | Tests Hypothesis | Method | Effort | Timeline | |---|-----------|-----------------|--------|--------|----------| ### Experiment Details [For each experiment: setup, success criteria, risks, what you'll learn] ``` ## Notes - For existing products, ground ideas in current user behavior and validated problems - For new products, focus on desirability and feasibility risks first - If the user uploads a research doc or interview transcript, extract insights before brainstorming - Encourage breadth first, then depth — generate many ideas before evaluating

{ "prompt": "# Brainstorm\n\nGenerate creative product ideas or experiment designs from three perspectives (PM, Designer, Engineer), tailored to whether you're working on an existing product or building something new.\n\n## Examples\n\n```text\n/brainstorm ideas existing Mobile banking app engagement\n/brainstorm ideas new AI-powered meal planning for busy parents\n/brainstorm experiments existing Onboarding flow redesign\n/brainstorm experiments new Marketplace for freelance designers\n/brainstorm\n```\n\n## Workflow\n\n### Step 1: Determine Mode\n\nParse the arguments to identify two dimensions:\n\n1. **What to brainstorm**: `ideas` (feature concepts) or `experiments` (validation tests)\n2. **Product stage**: `existing` (continuous discovery) or `new` (initial discovery)\n\nIf either dimension is missing, ask the user. If both are missing, ask:\n- \"Are you brainstorming **ideas** for what to build, or **experiments** to validate assumptions?\"\n- \"Is this for an **existing** product or a **new** product concept?\"\n\n### Step 2: Gather Context\n\nAsk the user for context. Be conversational — ask the most critical question first:\n\n**For existing products:**\n- What is the product? Who are current users?\n- What opportunity area or problem space are you exploring?\n- Any constraints (technical debt, platform limitations, team capacity)?\n- What has been tried before?\n\n**For new products:**\n- What is the product concept? What problem does it solve?\n- Who is the target user? What's their current alternative?\n- What stage are you at? (napkin sketch, validated problem, early prototype)\n- What are the riskiest assumptions?\n\nAccept context from uploaded files (PRDs, research docs, strategy decks), pasted text, or conversation.\n\n### Step 3: Generate Output\n\n**If brainstorming ideas** — apply the **brainstorm-ideas-existing** or **brainstorm-ideas-new** skill:\n- Generate ideas from three perspectives: Product Manager (user value, business impact), Designer (UX, delight, accessibility), Engineer (technical innovation, platform leverage, scalability)\n- For each idea: name, description, target user impact, feasibility assessment\n- Rank the top 5 ideas with rationale\n- Flag which ideas could be quick wins vs. strategic bets\n\n**If brainstorming experiments** — apply the **brainstorm-experiments-existing** or **brainstorm-experiments-new** skill:\n- For existing products: suggest A/B tests, prototypes, fake-door tests, wizard-of-oz, concierge experiments, and spikes\n- For new products: create XYZ+S hypotheses and suggest pretotype experiments (landing pages, explainer videos, pre-orders, concierge MVPs)\n- For each experiment: hypothesis, method, success criteria, effort estimate, expected timeline\n- Rank by learning-per-effort ratio\n\n### Step 4: Deepen and Iterate\n\nAfter presenting initial results, offer:\n- \"Want me to **detail** any of these ideas into a fuller spec?\"\n- \"Should I **identify assumptions** behind the top ideas?\" (chains into the `identify-assumptions-existing` or `identify-assumptions-new` skill)\n- \"Want to **design experiments** to validate the top ideas?\" (chains into experiment mode)\n- \"Should I **prioritize** these against your current backlog?\" (chains into the `prioritize-features` skill)\n\n## Output Format\n\n### For Ideas:\n```markdown\n## Brainstorm: [Product/Feature Area]\n**Mode**: Ideas for [existing/new] product\n**Context**: [1-2 sentence summary]\n\n### PM Perspective\n1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L]\n2. ...\n\n### Designer Perspective\n1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L]\n2. ...\n\n### Engineer Perspective\n1. **[Idea Name]** — [description] | Impact: [H/M/L] | Effort: [H/M/L]\n2. ...\n\n### Top 5 Recommendations\n| Rank | Idea | Why | Quick Win? |\n|------|------|-----|------------|\n\n### Next Steps\n[What to do with these ideas]\n```\n\n### For Experiments:\n```markdown\n## Experiment Design: [Product/Feature Area]\n**Mode**: Experiments for [existing/new] product\n\n### Hypotheses\n1. **[Hypothesis]** — XYZ format: [X]% of [Y] will [Z] within [S timeframe]\n\n### Recommended Experiments\n| # | Experiment | Tests Hypothesis | Method | Effort | Timeline |\n|---|-----------|-----------------|--------|--------|----------|\n\n### Experiment Details\n[For each experiment: setup, success criteria, risks, what you'll learn]\n```\n\n## Notes\n\n- For existing products, ground ideas in current user behavior and validated problems\n- For new products, focus on desirability and feasibility risks first\n- If the user uploads a research doc or interview transcript, extract insights before brainstorming\n- Encourage breadth first, then depth — generate many ideas before evaluating", "variables": [], "notes": "Brainstorm product ideas or experiments from PM, Designer, and Engineer perspectives for existing or new products. Arguments: [ideas|experiments] [existing|new] <product or feature description>.", "metadata": { "source": { "provider": "github-prompts", "repository": "https://github.com/pmweekly/one-station", "path": ".github/prompts/brainstorm.prompt.md", "ref": "71b3c3168c44f6d85d947d7797b63359b7aeb458", "url": "https://github.com/pmweekly/one-station/blob/71b3c3168c44f6d85d947d7797b63359b7aeb458/.github/prompts/brainstorm.prompt.md", "key": "pmweekly/one-station/.github/prompts/brainstorm.prompt.md" } } }

brainstorm

About

Brainstorm

Examples

Workflow

Step 1: Determine Mode

Step 2: Gather Context

Step 3: Generate Output

Step 4: Deepen and Iterate

Output Format

For Ideas:

For Experiments:

Notes

Install brainstorm and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews