1---2name: conversion-research3description: >-4 Researches why a B2B SaaS funnel loses buyers by running 3 passes on it (technical, heuristic and analytics, plus5 an optional qualitative pass), merging what they find by location, and keeping only the issues 2 or more passes6 found, ranked by an estimated loss with its inputs shown. Checks that analytics agrees with the CRM before7 trusting any rate, and sizes each proposed test so nobody runs one the traffic can't finish. Use it when a funnel8 step falls or a page underperforms and the cause isn't obvious. Not for reviewing one page on its own (use9 landing-page-critic) or fixing tracking (use tracking-audit).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Uses connected analytics and a CRM if13 the agent has them, otherwise exports or pasted tables. Python 3 is optional, for leak, segment and sample size14 math.15metadata:16 author: SHAKEUP17 version: "1.0.0"18 stage: get19 plugin: creative-conversion20 homepage: https://www.shakeuphq.com/skills/conversion-research21---22 23# Conversion research24 25Finds where and why a funnel loses buyers, and keeps only what more than one kind of evidence agrees on.26 27## Purpose28 29- One job: one funnel, 3 passes, one ranked list of confirmed issues with the action for each.30- Stage: get. It gathers and structures evidence and ends in a research verdict, not a redesign.31- It never ranks on data it hasn't checked against the CRM, never reports a heuristic opinion as a confirmed issue, never invents a benchmark or a load time, and labels every loss as an estimate with its inputs.32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| A funnel step fell and nobody knows why | this skill |38| A page's conversion rate is low and the page review didn't explain it | this skill |39| Deciding whether a proposed test can finish on your traffic | this skill (step 10), or the script's `sample` command alone |40| Reviewing one page before launch | `landing-page-critic` |41| Analytics and the CRM disagree | `tracking-audit` first |42| Pipeline by channel for a report | `pipeline-report` |43 44## Inputs45 46| Input | Required | Ways to provide, in order | If missing |47| --- | --- | --- | --- |48| The funnel: its steps and what counts each (event or CRM stage) | yes | the reader's note; inferred from the analytics and CRM and confirmed | ask once; with none, `BLOCKED` |49| Step counts, this period and last (same length) | yes, for the analytics pass | connected analytics and CRM; exports; pasted table | analytics pass `not run` |50| CRM counts for the same steps and periods | yes, for the health check | connected CRM; an export; pasted counts | health check `not run`; coverage `partial`; say every rate is unverified |51| Conversion by device and browser | no, for the technical pass | connected analytics; an export; pasted table | browser check `not run` |52| Test submissions, speed reports, error logs | no, for the technical pass | the agent tests if it can browse; the reader's results; PageSpeed Insights output | those checks `not run` |53| The funnel's pages | no, for the heuristic pass | live URLs; screenshots; pasted copy | heuristic pass `not run` |54| Recordings, polls, user tests, sales notes | no | the reader's tools or notes; a `message-mining` handoff | qualitative pass `not run` |55| Weekly visitors to each page under test | no | analytics | test sizing `not run` |56 57Triangulation needs at least 2 passes. With fewer, the verdict is `BLOCKED`.58 59## Profile read60 61From `company-profile.md`: `## Company` (business model and sales cycle, which set the funnel steps and how long a period must be), `## Buyers`, `## Targets` (lead to opportunity and opportunity to closed-won rates, used to turn lost leads into lost opportunities), `## Accounts and data` (which tools hold the counts), `## Channels`, and every `## Learnings` entry for `conversion-research` with status `noted`, `fact` or `accepted`.62 63No profile: ask in one message for the funnel steps, the CRM and analytics tools, and the sales cycle length. Say that `company-profile` saves this next time. Without target rates, losses stop at the step where they're measured.64 65## Steps66 671. **Apply learnings.** A learning that changes a threshold (a known tracking gap, a step to exclude) overrides the defaults. Name it when it fires.68 692. **Map the funnel.** List each step, what counts it (the analytics event or the CRM stage), and the 2 periods. Each period must be at least as long as the sales cycle for steps that sales owns (a shorter period counts opportunities that haven't had time to happen), and the same length as the other.70 713. **Run the health check first.** Use the table in `references/passes.md`. Compare analytics with the CRM for each step both hold, in each period: gap = (analytics minus CRM) divided by CRM, ignoring the sign. A gap over 20% on any step, or more than 1 conversion event per submission, is `TRACKING FIRST`: stop here, and name the causes to check: an event that fires twice, spam or test submissions, a broken form-to-CRM sync, a consent banner change. A gap that appears in one period only points at what changed between them. A step whose definition changed inside a period is excluded from the leak and named.72 734. **Analytics pass.** Find the leak:74 75 ```76 python3 scripts/funnel_math.py leak --csv funnel.csv77 ```78 79 CSV columns: stage, this, last. It gives each step's rate now and before, the relative change, and a p-value; the leak is the biggest fall with p < 0.05, else the biggest fall marked `possible`. Without Python, follow `references/passes.md`. Then cut the leaking step by device, channel, landing page and new against returning visitors, and record each segment that carries the fall as a finding with its location.80 815. **Technical pass.** Run the checks in `references/passes.md`: conversion by browser within each device class (`python3 scripts/funnel_math.py segments --csv segments.csv`), the form on the top browser and device pairs, the conversion event, speed by the tool's own labels, console errors, embedded tools. Record each finding with its location.82 836. **Heuristic pass.** Run `landing-page-critic` on each page in the funnel and take its `failed` list as this pass's findings. Without it, use the 6 questions in `references/passes.md`. Each finding gets a location.84 857. **Qualitative pass (if material exists).** Tag each observation from recordings, polls, user tests or sales notes to a location. 1 observation is an anecdote; record it only when several point the same way.86 878. **Merge by location.** Put every finding in one table: location, symptom, and which passes found it, with the evidence from each. Merge findings at the same page and element, or the same funnel step and segment.88 89 | Found by | Status |90 | --- | --- |91 | 2 or more passes | `confirmed` |92 | A reproduced failure (a test submission that fails, an event that doesn't fire) | `confirmed` on its own: a reproduction is proof |93 | 1 pass | `watch list`, with the pass that would confirm or clear it |94 959. **Estimate the loss** for each confirmed issue, and show the inputs:96 - At a leaking step: the end-of-funnel count lost had that step held its old rate (from the `leak` output).97 - In a segment: its conversions short of its best peer (`sessions_short` from the `segments` output), carried down the funnel with the reader's own rates from `## Targets` or the step counts.98 - With no way to size it: `not available`, and rank it after the sized issues.99 Rank by estimated loss; ties by the number of passes, then by the cheaper fix.100 10110. **Pick the action** for each confirmed issue:102 103 | Issue | Action |104 | --- | --- |105 | A reproduced bug or a broken event | fix now; no test |106 | A change to the offer, message or form | size the test: `python3 scripts/funnel_math.py sample --rate <now> --lift <smallest lift worth it> --weekly <visitors a week, both versions>` |107 | The test fits in 8 weeks | test it (past 8 weeks a B2B test measures a market that keeps moving) |108 | It doesn't fit | test a bigger change, at least the smallest lift the script says the traffic can detect in 8 weeks; or ship the fix and compare periods with the leak method, labelled "not a controlled test" |109 | The cause isn't clear | research more: name the pass that would explain it (a user test, an on-page poll) |110 111 Without Python, the sample size per version is about 16 x p x (1 - p) / (p x lift) squared, for 95% confidence and 80% power, where p is the current rate. Say it's the rough form.112 113## Check and verdict114 115| Verdict | Condition (first match wins) |116| --- | --- |117| `BLOCKED` | No funnel steps, or fewer than 2 passes could run |118| `TRACKING FIRST` | The health check failed: analytics and the CRM differ by more than 20% on a step, or events double count. Ranks built on broken counts point at the wrong step |119| `ISSUES FOUND` | 1 or more confirmed issues |120| `NO CONFIRMED ISSUES` | The passes ran and no issue was found by 2 of them |121 122Before the verdict, check: every rate has its counts beside it; every loss is labelled an estimate with inputs; no heuristic finding is listed as confirmed on its own; every pass that didn't run is named.123 124Named stops: `BLOCKED` asks for the missing funnel or data. `TRACKING FIRST` stops and hands to `tracking-audit`, listing the steps and the gap. No other stops.125 126## Learn127 128Append to `## Learnings` in the profile:129 130- A fix or a test result comes back (the step's rate before and after, or a test read with `funnel_math.py read`): a `fact` with the rates, the dates and the source.131- The reader confirms a known, stable tracking gap ("analytics always counts 15% more submits than the CRM because of spam"): a `fact`, so the health check expects that gap next time.132- A watch-list issue later proves real: a `proposal` to treat that pass as stronger for that kind of issue.133 134Example: `- 2026-10-24 | conversion-research | fact | Removing the budget field lifted demo form completion from 3.1% to 4.0% (not a controlled test) | Why: GA4 and HubSpot, Aug against Sep 2026 | Status: noted`135 136## Output137 138```139Verdict: <ISSUES FOUND | NO CONFIRMED ISSUES | TRACKING FIRST | BLOCKED> · Coverage: <complete | partial (what's missing)>140Funnel: <steps> · Periods: <this> against <last> · Passes run: <list> · Not run: <list and why> · Math: <script | by hand>141Health check: <pass | fail: step, analytics count, CRM count, gap> · Learnings applied: <list or none>142 143Funnel144| Step | This | Last | Rate now | Rate before | Change | p | Real |145 146Confirmed issues (ranked)147| Rank | Issue | Location | Found by | Evidence per pass | Estimated loss (inputs) | Action |148 149Watch list150| Issue | Location | Found by | Pass that would confirm it |151 152Tests153| Change | Rate now | Lift sought | Weekly visitors | Per version | Weeks | Call |154```155 156Then the handoff block.157 158## Hand off159 160```handoff161skill: conversion-research162version: 1.0.0163verdict: ISSUES FOUND164coverage: partial (no session recordings)165for: <funnel name>166outputs:167 leak: <step> (<change>, <real | possible>)168 confirmed: [<issue at location>, <issue at location>]169 fix_now: [<bug>]170 tests: [<change>: <weeks> weeks, <call>]171 watch_list: <n>172next: [landing-page-critic]173open: [<pass to add>]174```175 176`landing-page-critic` takes the pages with confirmed message or friction issues for the rewrite. For `TRACKING FIRST`, `next` is `[tracking-audit]` and `outputs` lists the steps with the gap.177 178## Failure modes179 180| Problem | Do this |181| --- | --- |182| Counts are too small for any fall to pass p < 0.05 | Report the biggest fall as `possible`; widen the periods to the length of 2 sales cycles if the data allows; lean on the technical and heuristic passes |183| Only one period of data | No leak; run the segment cuts within the period and say the analytics pass is partial |184| The reader wants a winner from a finished test | `funnel_math.py read` with each version's visitors and conversions; call a winner only at p < 0.05, and check downstream (opportunities, not only form fills) |185| A segment flag on a browser with odd traffic (bots, an office network) | Check its engagement first; bot traffic is a tracking finding, not a conversion issue |186| The reader wants to test with 2 weeks of traffic | Show the sample size and weeks; never call a test early because it looks ahead |187| The issue sits after the CRM handoff (no-shows, slow follow-up) | Record it with the CRM evidence; it is a sales process finding, still ranked |188 189## Influenced by190 191- CXL's conversion research framework (ResearchXL), which gathers technical, heuristic, analytics and qualitative evidence separately and acts on the issues they agree on. We cut it to 3 required passes with a CRM health check in front, a merge rule by location, and a test-size gate.192- SHAKEUP's funnel leak finder and A/B test calculator: each step compared with itself last period, the leak sized in lost deals, and every test sized before it starts.