pol-probe-advisor
Select the right Proof of Life (PoL) probe based on hypothesis, risk, and resources. Use this to match the validation method to the real learning goal, not tooling comfort.
npx skills add deanpeters/Product-Manager-Skills --skill pol-probe-advisor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill guides a PM through choosing the appropriate Proof of Life (PoL) probe flavor from five options, based on their hypothesis, risk, and available resources. It helps map the learning goal to a concrete validation method and emphasizes using the cheapest prototype that reveals the harsh truth, not what is easiest to build.
How it works
- It presents five probe flavors with explicit questions and matching scenarios.
- For each option, it details what the probe is, typical methods, timeline, tools, success criteria, disposal plan, and next steps.
- After presenting options, it asks the user to choose one and then offers steps to proceed:
- Generate a complete pol-probe artifact using the pol-probe.md template
- Walk through execution steps (tools, methods, recruitment)
- Refine the hypothesis if needed
- It uses structured prompts to align the validation method with the hypothesis and risk, ensuring a narrow, falsifiable focus.
When to use it
Use when you have a clear hypothesis but don’t know which validation method to use, want to avoid overbuilding, and need to eliminate a specific risk quickly (within days).
What it can touch
- Tools and methods vary by option (e.g., Feasibility Check mentions GenAI prompt chains, Postman/Insomnia, Jupyter notebooks; Task-Focused Test mentions Optimal Workshop, UsabilityHub, Maze, Loom; Narrative Prototype mentions Loom, Sora, Synthesia, PowerPoint; Synthetic Data Simulation mentions Synthea, LangFlow, Python+Faker; Vibe-Coded PoL Probe mentions ChatGPT Canvas, Replit, Airtable, Carrd/Webflow).
- It references a default interaction protocol via workshop-facilitation for session structure.
Caveats
- The content is a decision framework and does not guarantee validation success.
- The Vibe-Coded PoL Probe is flagged as the riskiest option with explicit cautions.
- It requires user-provided hypothesis, risk, timeline, and resources to select a probe type.
## Purpose Guide product managers through selecting the right **Proof of Life (PoL) probe** type (of 5 flavors) based on their hypothesis, risk, and available resources. Use this when you need to eliminate a specific risk or test a narrow hypothesis, but aren't sure which validation method to use. This interactive skill ensures you match the cheapest prototype to the harshest truth—not the prototype you're most comfortable building. This is **not** a tool for deciding *if* you should validate (you should). It's a decision framework for choosing *how* to validate most effectively. ## Input **Works best with:** The hypothesis you want to validate or the risk you want to eliminate. **Also useful:** Your resources (time, budget, engineering access), audience access, and what failure would cost. Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask. **Arriving empty-handed? That works too.** The advisor opens by asking what you're trying to learn, then matches you to one of the 5 probe flavors. **Example invocation:** `Which prob
- Purpose
- Input
- Key Concepts
- The Core Problem: Method-Hypothesis Mismatch
- The 5 PoL Probe Flavors (Quick Reference)
- Anti-Patterns (What This Is NOT)
- When to Use This Skill
- Facilitation Source of Truth
- Application
- Step 0: Gather Context
- Step 1: Identify the Core Question
- Step 2: Recommend PoL Probe Type
- Step 3: Apply Component Skill
- Step 4: Refine or Iterate (Optional)
What does the pol-probe-advisor skill do?
Select the right Proof of Life (PoL) probe based on hypothesis, risk, and resources. Use this to match the validation method to the real learning goal, not tooling comfort.
How do I install it?
Run `npx skills add deanpeters/Product-Manager-Skills --skill pol-probe-advisor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From deanpeters/Product-Manager-Skills, a repository with 6,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.