Home / vandanaajaydubey111 / great-pm · GitHub

funnel-diagnostics SKILL.md skillA

funnel-diagnostics from vandanaajaydubey111/great-pm is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add vandanaajaydubey111/great-pm/funnel-diagnostics@git:20260721.86de099

Pins git:20260721.86de099 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: vandanaajaydubey111/great-pm
Path: skills/funnel-diagnostics/SKILL.md
Versions recorded: 1
Latest version: git:20260721.86de099, committed Jul 21, 2026
Size: 14,419 bytes
Repository stars: 3
License: MIT

The step-by-step drop-off diagnostic workflow — define the funnel, measure each step's conversion, find the worst drop, diagnose WHY (segment-by-segment + qual), fix, and re-measure. Turns "the numbers dropped" into a located, explained, validated fix. The segmentation step is what separates diagnosis from description. Used by analytics-analyst.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

> **Provenance.** great-pm-original, authored 2026-05-29, grounded in the
> cited sources (Plane, FullSession, Datadog Product Analytics). Host
> agent: analytics-analyst.

# Funnel Diagnostics — locate, explain, fix, re-measure

A funnel is **diagnostic, not descriptive — but only once you segment
it.** An aggregate funnel tells you *where* users drop. That is necessary
and almost useless on its own: "60% drop at the upload step" prompts a
quarter of guesswork. The leap from *description* to *diagnosis* is
**segmentation + session review** — splitting the drop by device, source,
plan, cohort until the loss concentrates in a group, because the group
where the drop concentrates *is the diagnosis*. Then you prioritize the
drop that blocks value for the **largest group**, fix it, and **re-measure
the specific step** to confirm the curve moved.

The single biggest failure in funnel work is reading the aggregate
number, "fixing onboarding" generically, and shipping a change that moves
nothing because the real loss was a PDF-parser failure for one bank,
invisible in the average.

## 1. The 5-step workflow

### Step 1 — Define the journey
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add vandanaajaydubey111/great-pm/funnel-diagnostics@sha256:665c26d0cb8dc295

The line at the top of this page pins the label git:20260721.86de099, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_ylakgwthswbu6wtv.svg)](https://markdownregistry.com/a/art_ylakgwthswbu6wtv)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 21, 2026.

version	committed	commit	size	audit
git:20260721.86de099 latest	2026-07-21	86de099	14,419 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (14419 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

vandanaajaydubey111/great-pm · 3 stars · license MIT · pushed 2026-09-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ylakgwthswbu6wtv
GET https://markdownregistry.com/api/v1/resolve?ref=vandanaajaydubey111/great-pm/funnel-diagnostics
GET https://markdownregistry.com/api/v1/blob/665c26d0cb8dc295d5d326edeef6d7f34dc0fcc141c363c361b5fdf91c5704f5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from vandanaajaydubey111/great-pm

great-pm-runtime SKILL.md skill

vandanaajaydubey111/great-pm · codex/source-skills/great-pm-runtime/SKILL.md · Use when a GreatPM workflow needs to select, spawn, coordinate, or collect results from its specialist…