pm-hypotheses

pm-hypotheses is a skill for Claude Code from ljucask/pureinn-product-development. It costs 0 tokens per session (5,106 once invoked), scanned A, original, MIT.

A validation tool that turns assumptions about a product into testable hypotheses, assigns experiments, records evidence, and produces a Go, Pivot, or Stop decision. A hypothesis is a claim that can be checked with evidence.

In plain words
What is it for?
Use it to plan validation experiments, track their results, rank risks, and decide whether to continue, change direction, or stop.
Why use it?
It helps teams test whether a problem is important before spending months building a solution. Success measures are defined before experiments run, making results easier to judge.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the pureinn-product-development plugin — 51 skills, 1 command shipped together

Good fit Use it to plan validation experiments, track their results, rank risks, and decide whether to continue, change direction, or stop.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ljucask/pureinn-product-development/pm-hypotheses
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 ljucask/pureinn-product-development --skill pm-hypotheses
Clone the repo
git clone --depth 1 https://github.com/ljucask/pureinn-product-development

Made for: Claude Code.

Or install pureinn-product-development, the plugin that ships this one along with the rest of its 51 skills, 1 command.

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 pm-hypotheses

README.md
[![agentmods](https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-hypotheses/github.svg)](https://agentmods.dev/skills/ljucask/pureinn-product-development/pm-hypotheses)
Your own site
<a href="https://agentmods.dev/skills/ljucask/pureinn-product-development/pm-hypotheses"><img src="https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-hypotheses/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 pm-hypotheses

Your own site · 80×15
<a href="https://agentmods.dev/skills/ljucask/pureinn-product-development/pm-hypotheses"><img src="https://agentmods.dev/badge/skills/ljucask/pureinn-product-development/pm-hypotheses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,106 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 $0.00000 $0.05106
Opus 5 $0.00000 $0.02553
Sonnet 5 $0.00000 $0.01021
Haiku 4.5 $0.00000 $0.00511

Measured 10d ago against content hash 7a54b370fc2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pm-hypotheses 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 10d 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/pm-hypotheses/SKILL.md · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PM - Hypothesis Validation

Agent mode (--agent)

This skill's value is the live dialogue - --agent is not supported. If invoked with --agent, warn once ("this skill needs interactive back-and-forth; agent mode would hollow it out") and proceed interactively.


What this skill does

Turns raw assumptions into structured, testable hypotheses. Assigns the right experiment to each hypothesis. Tracks evidence as experiments run. Produces a Go/No-Go decision with pre-defined success metrics.

This skill runs in two modes:

  • Plan mode (first run): structure hypotheses from design-thinking outputs, rank by risk, assign experiment types, define success criteria before any experiment runs
  • Results mode (follow-up run): record experiment outcomes, update hypothesis status, issue Go / Pivot / Stop decision

Both modes use the same artifact - the Hypothesis Register - which is updated progressively.


Why validate this way

Most startups fail not because of bad ideas but because they build solutions for problems that are not painful enough. Skipping structured validation means:

  • Months of engineering for a product nobody buys
  • No ability to distinguish signal from noise in early feedback
  • Confirmation bias: founders hear what they want to hear

The goal of validation is not to get a yes or no. It is to learn. Every experiment is a clue that reduces uncertainty before capital and engineering time are committed.


Validation stages

This skill covers the full 5-stage validation arc:

Stage Goal Primary method
1 - Hypothesis Define riskiest assumptions about problem, customer, solution, market Assumption map + hypothesis register
2 - Qualitative Understand pain points and context from real people Customer discovery interviews (The Mom Test approach)
3 - Quantitative Measure real-world demand with low-cost experiments Landing page, smoke test, pre-order, targeted ads
4 - Lightweight MVP Test value delivery with minimum build Concierge MVP, Wizard of Oz, no-code prototype
5 - Go/No-Go Evidence-based decision: go, pivot, or stop Success metric review, decision table

Read the full file on GitHub · 461 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. 10d ago First seen · 461 lines · 0 tokens per session scan A 7a54b370fc2b

Subscribe to this mod's changes

pm-hypotheses is a skill published in the GitHub repository ljucask/pureinn-product-development (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,106 tokens. 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.

Related

Other skills, from other repositories

ai-native-design

A workflow for turning a product brief and API contract into frontend design prompts and implementation guidance. It supports three outside design channels and keeps generated frontend work aligned with the same brief and contract.

dhslegen/digital-delivery-team · 105 tokens

backend-development

A set of instructions for building server-side code such as APIs and database-backed applications. It uses API contracts, data models, the chosen technology stack, and tests as the project’s reference points.

dhslegen/digital-delivery-team · 72 tokens

decision-gate

A decision checkpoint for software-project workflows. After each phase produces its files, it asks the user to accept the result, request a change, add information, or regenerate it before the next phase begins.

dhslegen/digital-delivery-team · 62 tokens

frontend-development

A set of instructions for building the user-facing part of a web application, such as its pages, controls, and interactions. It applies to single-page applications and follows the project’s API, product, technology, and design documents.

dhslegen/digital-delivery-team · 75 tokens

relay

A Chinese-language procedure for handing an unfinished task from one AI session to another without losing its context.

dhslegen/digital-delivery-team · 111 tokens

validation-loop

A development routine that checks each important file immediately after it is changed by running the project’s build, lint, type-check, or test commands.

dhslegen/digital-delivery-team · 53 tokens