product-discovery

product-discovery is a skill for Claude Code from MartinOlivero/saas-builder. It costs 113 tokens per session (637 once invoked), scanned A, original, MIT.

A workflow for turning an uncertain product idea into a clearly defined minimum viable product, or MVP—the smallest version that can test whether the idea solves a real problem. It examines the users, their current alternatives, the market, and the first useful result.

In plain words
What is it for?
Use it to explore a product idea, identify the people and problem involved, check how they cope today, assess demand, and decide what the first version should contain.
Why use it?
It helps avoid spending time building features for a problem that is unclear, uncommon, or not valuable enough for people to pay for. It keeps early planning focused on the problem before the feature list.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the saas-builder plugin — 18 skills, 1 hook shipped together

Good fit Use it to explore a product idea, identify the people and problem involved, check how they cope today, assess demand, and decide what the first version should contain.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martinolivero/saas-builder/product-discovery
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add MartinOlivero/saas-builder --skill product-discovery
Clone the repo
git clone --depth 1 https://github.com/MartinOlivero/saas-builder

Made for: Claude Code.

Or install saas-builder, the plugin that ships this one along with the rest of its 18 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for product-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/martinolivero/saas-builder/product-discovery/github.svg)](https://agentmods.dev/skills/martinolivero/saas-builder/product-discovery)
Your own site
<a href="https://agentmods.dev/skills/martinolivero/saas-builder/product-discovery"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/product-discovery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for product-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/martinolivero/saas-builder/product-discovery"><img src="https://agentmods.dev/badge/skills/martinolivero/saas-builder/product-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00113 $0.00637
Opus 5 $0.00056 $0.00318
Sonnet 5 $0.00023 $0.00127
Haiku 4.5 $0.00011 $0.00064

Measured 12d ago against content hash 7ba8156cdee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

product-discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/product-discovery/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Discovery

This skill turns a fuzzy idea into a sharp, buildable MVP. It is inspired by Design Sprint and Lean Startup, and it resists the urge to jump to features before the problem is understood.

Analogy: do not prescribe medicine before diagnosing the illness. Most failed products are perfectly built cures for a disease nobody has.

Workflow

PHASE 1 — Understand the problem (not the solution)

Force the conversation onto the problem first. Ask:

  • What specific problem are you solving?
  • Who has that problem? Describe that person concretely.
  • How do they solve it today? (even if it is Excel, WhatsApp, or by hand)
  • Why is that current solution not good enough?

Do not let the discussion drift to features yet. If the user describes a solution, redirect to the problem it serves.

PHASE 2 — Validate the market

  • Do you (or your target users) already pay for something similar? How much?
  • Do you know other people with this same problem?
  • Do you have access to potential customers to validate with?

The goal is evidence that the problem is real and painful enough that someone will pay.

PHASE 3 — Define the MVP

  • What is the minimum result that would make someone pay?
  • Which features are "nice to have" but not essential?
  • How soon do you want something to show?

The MVP is the smallest thing that delivers the core result — not a small version of the full vision.

PHASE 4 — Output

Deliver these five items:

  1. Problem definition — in one sentence.
  2. Ideal customer avatar — who they are, concretely.
  3. MVP scope — a prioritized feature list:
    • P0 — must exist for the MVP to deliver its core result.
    • P1 — important, but can wait for v1.1.
    • P2 — nice to have; explicitly deferred.
  4. Success metric — how we will know it worked (e.g. "10 paying users in 30 days," "40% of signups complete the core action").
  5. Concrete next step — the single next action to take.

Handoff

Once the MVP is defined, hand off to architecture-primer to decide how to build it, then ui-design to build the interface. Discovery answers (scale expectations, user type, timeline) feed directly into the architecture discovery phase — pass them along.

Read the full file on GitHub · 57 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 57 lines · 113 tokens per session scan A 7ba8156cdee0

Subscribe to this mod's changes

product-discovery is a skill published in the GitHub repository MartinOlivero/saas-builder (2 stars, last pushed 24d ago), licensed MIT. It adds 113 tokens to every session and 637 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.