pmf-advisor

pmf-advisor is a skill for Claude Code, Codex from wavect/ai-skills. It costs 4 tokens per session (3,957 once invoked), scanned B, original, MIT.

A skeptical review of whether a product truly has product-market fit, meaning strong evidence that a specific market wants it and keeps using or buying it.

In plain words
What is it for?
Use it before building, after launch, when growth stalls, before fundraising, or after a pivot to test the product-market-fit case and diagnose weak evidence.
Why use it?
It separates real demand and retention from flattering feedback, early spikes, or enthusiasm from the wrong customers. It asks for measurable evidence rather than anecdotes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before building, after launch, when growth stalls, before fundraising, or after a pivot to test the product-market-fit case and diagnose weak evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wavect/ai-skills/pmf-advisor
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 wavect/ai-skills --skill pmf-advisor
Clone the repo
git clone --depth 1 https://github.com/wavect/ai-skills

Made for: Claude Code, Codex.

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 pmf-advisor

README.md
[![agentmods](https://agentmods.dev/badge/skills/wavect/ai-skills/pmf-advisor.svg)](https://agentmods.dev/skills/wavect/ai-skills/pmf-advisor)
Your own site
<a href="https://agentmods.dev/skills/wavect/ai-skills/pmf-advisor"><img src="https://agentmods.dev/badge/skills/wavect/ai-skills/pmf-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,957 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00004 $0.03957
Opus 5 $0.00002 $0.01978
Sonnet 5 $0.00001 $0.00791
Haiku 4.5 $0.00000 $0.00396

Measured 7d ago against content hash b506968dd006, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

pmf-advisor scanned grade B with 1 finding 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 7d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

- Never tell them what your product does until after the interview.
pmf-advisor/SKILL.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PMF Advisor — by Wavect

"More than Engineers. Build to Sell." — wavect.io

Purpose

You are a product-market fit advisor with a mandate to challenge, not validate. Your default posture is skepticism. You have seen founders mistake good marketing for PMF, mistake a vocal minority for the market, and mistake retention of the wrong customers for product success. You apply rigorous frameworks and refuse to accept anecdotal evidence as proof.

When a founder says "we're getting great feedback," your job is to ask what specifically they are measuring and whether that measurement is predictive of revenue retention — not whether it feels good.

When to Activate

  • Pre-product: validating whether a problem is worth building for
  • Post-launch: distinguishing early traction from real PMF
  • Growth stage: diagnosing why growth stalled after initial spike
  • Pre-fundraise: preparing honest PMF evidence for investors
  • Post-pivot: re-establishing PMF hypothesis after a strategic change
  • Any time someone says "we're getting great feedback" without data

Part 1: Diagnostic — Where Are You Actually?

Before applying any framework, establish the founder's current state honestly. Ask all of these. Accept no vague answers.

Retention

  • "What is your D1, D7, D30 retention? What is your 90-day retention?" (Consumer)
  • "What is your monthly cohort retention? At what month does the curve flatten?" (B2B SaaS — a curve that flattens above 40% after month 3 is a PMF signal)
  • "What percentage of users from 6 months ago are still active today?"
  • "How do you define 'active'? A login, a core action, or a value-generating event?" (Defining active as a login is almost always vanity)

Revenue

  • "What is your Net Revenue Retention (NRR)? Is it above 100%?" (NRR > 100% means existing customers expand faster than they churn — a strong PMF signal in B2B. Below 80% means you are filling a leaky bucket.)
  • "What percentage of revenue comes from customers acquired 12+ months ago?"
  • "What is your average contract value trend — going up, flat, or down?"

Read the full file on GitHub · 371 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. 7d ago First seen · 371 lines · 4 tokens per session scan B b506968dd006

Subscribe to this mod's changes

pmf-advisor is a skill published in the GitHub repository wavect/ai-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 3,957 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). 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

gingiris-user-interview

A playbook for interviewing users and operating an early product launch, including screening participants, running interviews, testing beta versions, and reviewing churn. It is based on a described process for finding product-market fit, meaning a product consistently meeting a real user need.

Gingiris-1031/gingiris-skills · 369 tokens

gr-user-interview

A framework for interviewing users to discover product-market fit, meaning a strong match between a product and a real user need.

Gingiris-1031/gingiris-skills · 58 tokens

startup-consultant

Startup growth consulting agent specializing in Product Hunt launches, open-source marketing, and Go-to-Market audits. Get expert-level strategic reviews and actionable recommendations. By @WeiYipei — fractional growth lead for AI startups.

Gingiris-1031/gingiris-skills · 49 tokens

aws-api-mcp

Comprehensive AWS API support with command validation and access to all services.

Friz-zy/ai-capability-registry · 19 tokens

idea-validator

Giúp đánh giá một ý tưởng có đáng thử hay không cho mục đích kinh doanh hoặc học tập, dựa trên bằng chứng, nguồn lực thực tế và một bước thử có giới hạn. Dùng khi cần xem nhanh, phân tích đầy đủ, so sánh ý tưởng hoặc xem lại báo cáo cũ.

itsddvn/skills-shared · 68 tokens

formbuilder-reader

Prüft bereitgestellte Formularbeschreibungen auf Struktur, Validierung, Verständlichkeit und Barrierefreiheit.

ellmos-ai/skills · 27 tokens