skill Claude Code CX Codex Cursor GitHub Copilot
Open on GitHub
brainstorm-experiments-existing — Claude Code skill: design low-cost
This skill helps plan experiments to validate assumptions about an existing product before committing to full builds. Use it to test hypotheses with prototypes, A/B tests, spikes, and other lean methods.
Install into Claude Code · Skills CLI (Vercel)
All methods and platforms ↓
npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a claude-codeWhat brainstorm-experiments-existing does
The skill walks through a step-by-step process for designing low-effort experiments. You describe your feature idea and list assumptions that need validation. The agent clarifies what to test, suggests methods (first-click tests, fake doors, technical spikes, A/B tests, Wizard of Oz, behavioral surveys), and for each experiment specifies the assumption, exact steps, metric, and success threshold.
The skill focuses on measuring actual user behavior, not opinions. For production tests like A/B tests, it explains risk mitigation strategies. Results are presented as a table or structured list and can be saved to markdown.
What it helps with
- pick a validation method for a product assumption
- design an A/B test with risk mitigation for existing features
- plan a prototype experiment before full development
- set metrics and success thresholds for a fake door or spike
- organize hypotheses and test methods into a single plan
Example prompts for the agent
- We want to test whether users will click a new menu button. Design a test for it.
- The team isn't sure if a sync feature is worth building. Help plan cheap validation.
- Here's a document of assumptions about this feature. For each one, suggest an experiment and metrics.
How to install brainstorm-experiments-existing
1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a claude-code2Manually: put the files in place
~/.claude/skills/brainstorm-experiments-existing/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/brainstorm-experiments-existing/
1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a codex2Manually: put the files in place
.agents/skills/brainstorm-experiments-existing/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a cursor2Manually: put the files in place
.cursor/skills/brainstorm-experiments-existing/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install phuryn/pm-skills brainstorm-experiments-existing2Manually: put the files in place
.github/skills/brainstorm-experiments-existing/SKILL.md1Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a gemini-cli2Platform CLI
gemini skills install https://github.com/phuryn/pm-skills --path pm-product-discovery/skills/brainstorm-experiments-existingManually: put the files in place
.devin/skills/brainstorm-experiments-existing/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set61
The whole set →
create-prd This skill builds a lean PRD from an 8-section template. Use it to define a feature, document product requirements, or review an existing PRD.
Claude Code CX Codex Cursor +1
10,800installs
pre-mortem Runs a pre-mortem risk assessment on PRDs and launch plans. Catches critical launch blockers, surfaces hidden team assumptions, and maps action items.
Claude Code CX Codex Cursor +1
10,200installs
outcome-roadmap Rewrites feature-heavy roadmaps into outcome-focused statements tied to business and customer impact. Helps teams replace rigid feature lists with measurable strategic goals.
Claude Code CX Codex Cursor +1
9,900installs
prioritization-frameworks Reference guide to 9 prioritization frameworks: RICE, ICE, Opportunity Score, Kano, MoSCoW and more. Helps you pick the right method, compare approaches, and rank tasks by importance.
Claude Code CX Codex Cursor +1
9,900installs
strategy-red-team Stress-tests PRDs, roadmaps, and strategies by attacking load-bearing assumptions before reality does, returning kill criteria and cheap tests.
Claude Code CX Codex Cursor +1
9,200installs
competitor-analysis This skill researches direct competitors and compares their positioning, strengths, weaknesses, and pricing. Use it to prepare a competitive brief or find ways to differentiate a product.
Claude Code CX Codex Cursor +1
3,800installs
business-model Skill generates a Business Model Canvas with all 9 building blocks: from key partners and activities to channels and revenue streams. Use it to create a business model, document how value flows, or analyze an existing business.
Claude Code CX Codex Cursor +1
3,700installs
privacy-policy Skill drafts a detailed privacy policy accounting for GDPR, CCPA, and other regulations. Use it when building a new product, updating data protection docs, or preparing for compliance audits.
Claude Code CX Codex Cursor +1
3,500installs
Similar
logo-generator Generates SVG logos with at least six design variants and creates high-end showcase images using 12 professional background styles via Gemini API.
Claude Code CX Codex Cursor +1
3,900installs
superdesign Create and refine interfaces, presentations, and graphics on the Superdesign canvas. Useful for drafting new layouts or comparing results from different models.
Claude Code CX Codex Cursor +1
11,200installs
appllama-app-design-skill Skill for building native iOS and Android screens with Expo and React Native. Designs with Apple HIG fidelity, semantic colors, Reanimated motion, proper navigation semantics, and simulator-verified iteration.
Claude Code CX Codex Cursor +1
4,700installs
ai-image-generation Generates and edits images through belt with selectable models. Use it for illustrations, mockups, and changes to existing images.
Claude Code CX Codex Cursor +1
861,200installs
scroll-experience This skill guides an agent through scroll animations, parallax scenes, and interactive web narratives. Use it when scrolling should reveal part of a page’s story.
Claude Code CX Codex Cursor +1
2,000installs
frontend-design
official This skill guides intentional visual design for new interfaces and redesigns. Use it when a generic generated UI is not enough.
Claude Code Claude.ai
1,025,790installs
grill-me grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts.
Claude Code
1,424,476installs
design-taste-frontend This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished.
Claude Code CX Codex Cursor +1
673,100installs
Questions about brainstorm-experiments-existing
How do I install brainstorm-experiments-existing in Claude Code?
Run npx skills add phuryn/pm-skills --skill brainstorm-experiments-existing -a claude-code. The skill file will be saved to ~/.claude/skills/brainstorm-experiments-existing/SKILL.md.
What does brainstorm-experiments-existing do?
It helps design experiments to test product assumptions. The agent suggests methods (A/B tests, prototypes, fake doors, technical spikes), clarifies metrics, and sets success thresholds for each test.
Which platforms support this skill?
The skill works with Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. Each platform has its own install command.
Source text
SKILL.md · MIT
--- name: brainstorm-experiments-existing description: "Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments." --- ## Design Experiments (Existing Product) Design low-effort experiments to test product assumptions before committing to full implementation. ### Context You are helping a product team design experiments for **$ARGUMENTS**. The team has a feature idea and assumptions that need validation. If the user provides files (PRDs, assumption lists, designs), read them first. ### Instructions The user will describe their idea and assumptions. Work through these steps: 1. **Clarify the idea and assumptions**: Confirm what the team wants to build and what they need to validate. 2. **Suggest experiments** for each assumption. Consider methods like: - First-click testing or task completion with a prototype - Feature stubs or fake door tests - Technical spikes - A/B tests on production (with risk mitigation) - Wizard of Oz approaches - Survey-based validation (behavioral, not opinion-based) 3. **Key principles to follow**: - Measure actual behavior, not users' opinions - Test responsibly — don't put users or the business at risk - For production tests (e.g., A/B tests), explain risk mitigation strategies - Aim for maximum validated learning with minimal effort 4. **For each experiment**, specify: - **Assumption**: What do we believe? - **Experiment**: What exactly will we do to validate it? - **Metric**: What will be measured? - **Success threshold**: The expected value if we are right Think step by step. Present experiments in a clear table or structured format. Save as markdown if substantial. --- ### Further Reading - [Testing Product Ideas: The Ultimate Validation Experiments Library](https://www.productcompass.pm/p/the-ultimate-experiments-library) - [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas) - [What Is Product Discovery? The Ultimate Guide Step-by-Step](https://www.productcompass.pm/p/what-exactly-is-product-discovery) - [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)
© phuryn · MIT · phuryn/pm-skills
