1---2name: crm-feedback-loop3description: >-4 Plans and checks how a B2B SaaS company sends CRM stages (MQL, SQL, opportunity, closed-won) back to Google Ads,5 LinkedIn Ads, Meta Ads and ChatGPT Ads so they bid for pipeline instead of form fills. Measures each stage's timing6 against each platform's documented window, picks the stage each platform should bid on, values stages from the7 company's own stage-to-won rates, and handles sales cycles longer than the windows. Use it when platforms bid on8 leads that never become pipeline, before setting up offline imports or a conversions API, or when the sales cycle9 changes. Not for checking existing tracking (use tracking-audit first) or reporting pipeline (use pipeline-report).10 It recommends; it never changes an account.11license: MIT12compatibility: >-13 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Reads a connected CRM read-only if the14 agent has one, otherwise a CSV export or pasted rows. Opens the platforms' documentation if the agent can browse.15 Python 3 is optional, for the stage timing.16metadata:17 author: SHAKEUP18 version: "1.0.0"19 stage: make20 plugin: markops21 homepage: https://www.shakeuphq.com/skills/crm-feedback-loop22---23 24# CRM feedback loop25 26Turns CRM stages into the signal each ad platform bids on, within the time each platform allows.27 28## Purpose29 30- One job: produce a feedback plan per platform (which stage it bids on, which it reports, with what value, sent how and how often) and check the plan before handing it over.31- Stage: make. It ends with its own check, at most 2 rounds.32- It never changes an ad account, a CRM or an integration. It writes the spec; people build it.33- It never invents a window, a limit, a conversion rate or a stage value. Windows come from `references/platform-windows.md` (dated, cited); rates and values come from the reader's CRM.34 35## Use when / not36 37| Situation | Use |38| --- | --- |39| Platforms bid on leads that sales rejects | this skill |40| Setting up offline imports or a conversions API | this skill, after `tracking-audit` |41| The sales cycle got longer, or a new platform starts | this skill |42| Imports exist but the data looks wrong | `tracking-audit` |43| Building the score that could serve as an early stage | `lead-scoring` |44| Reporting pipeline per channel | `pipeline-report` |45 46## Inputs47 48| Input | Required | Ways to provide, in order | If missing |49| --- | --- | --- | --- |50| Leads with their stage dates (created or click date, MQL, SQL, opportunity, closed-won), platform or source, and won amount, last 12 months | yes | a connected CRM, read-only; a CSV export of contacts or leads with stage date properties; pasted rows | `BLOCKED`: ask for the export |51| Stage definitions: names and entry rules | yes | CRM settings; the reader | ask once; without them, use the export's column names and mark them unconfirmed |52| The `tracking-audit` handoff: match key rate per platform, existing imports, stage dates | no | the handoff block; else check click ID columns in the export | measure the click ID share from the export; coverage `partial` |53| Platforms in scope | no | `## Channels`; the reader | every paid platform marked `active` |54| Each platform's current window settings (conversion action windows, LinkedIn rule types, Meta attribution setting) | no | a connected ad account, read-only; screenshots; the reader | plan with the documented limits; open item |55| A `lead-scoring` handoff with verdict READY | no | its handoff block | no predicted stage option |56 57## Profile read58 59From `company-profile.md`: `## Company` (Sales cycle, Average deal size, Regions for consent, Business model), `## Channels` (paid platforms, status, budget), `## Targets` (opportunity to closed-won rate, as a cross-check only: the plan uses rates measured from the export), `## Accounts and data` (CRM, connected ad accounts), and every `## Learnings` entry for `crm-feedback-loop`.60 61No profile: ask in one message for the paid platforms, the CRM, the stage names and the regions the company sells in. Say that `company-profile` saves this next time.62 63## Steps64 651. **Apply learnings.** Accepted rules override the defaults (a different floor, a stage the reader never sends). Name each one that fires.66 672. **Check the preconditions.** From the `tracking-audit` handoff or the export:68 69 | Condition | Do |70 | --- | --- |71 | No stage has a date field | Stop at `NOT READY`; deliver the data contract (step 8) only |72 | A platform's match key rate is under 50% | That platform is `NOT READY`; plan the others |73 | Match key rate 50% to 79% | Plan it; open item to raise the rate |74 | No platform or source column | Apply the volume test to all leads, label it `volume per platform not available`, and make each bid-on stage conditional on that platform's share of the volume |75 763. **Write the stage ladder.** Lead created, then the reader's stages, shallow to deep. For each: entry rule, date field, value field, and whether sales can move a record back (a stage that can be undone is sent once, when first reached).77 784. **Measure the timing.** Run the script on the export:79 80 ```81 python3 scripts/stage_timing.py --csv leads.csv --stages "mql=mql_date,sql=sql_date,opp=opp_date,won=won_date" \82 --start-col click_date --platform-col source --amount-col amount83 ```84 85 Without Python, by hand: for each stage, list the days from the click date (or the lead's created date) to the stage date; sort them; take the middle value (median) and the value 9 in 10 fall under (p90); count the share at or under each platform's window from `references/platform-windows.md`; count stage events in the last 90 days and divide by 3 for a monthly volume, per platform. Drop rows where a stage is dated before the one above it, and count them. Say which way you ran it.86 875. **Value the stages from the reader's own data.** Stage value = the share of leads reaching that stage that went on to close won, times the median won amount. Measure the share on a mature cohort only: leads that started at least the p90 days to closed-won before the export's last date, so open deals don't pull the rate down. Under 10 won deals in the mature cohort: write values as `not available` (one deal more or less moves the rate by 10% or more) and send stages without values.88 896. **Pick the bid-on stage per platform.** Take the deepest stage that passes both tests:90 91 | Test | Default | Why |92 | --- | --- | --- |93 | Inside the window | 80% or more of the stage's events happen within the platform's window | Below that, more than 1 in 5 events never arrive, and bidding learns from the deals that move fastest |94 | Volume | 15 or more events a month on that platform, or the platform's own published minimum where it has one (Meta Conversion Leads: 200 leads a month) | At 15 a month, chance alone moves a month by about 8 either way, so a smaller stage can't show a real change |95 96 Then handle the gap between the sales cycle and the window:97 98 | Situation (first match wins) | Plan |99 | --- | --- |100 | The opportunity or closed-won stage passes | Bid on it. Send the earlier stages as secondary conversions for reporting |101 | A deeper stage fails the window, an earlier one passes | Bid on the earlier stage with its stage value. Send deeper stages as secondary inside the window; report the share lost |102 | Only the lead stage passes, and `lead-scoring` returned READY | Offer a predicted stage: send leads graded A as their own conversion at creation, valued by grade A's won rate from the scoring hold-out. This is a `NEEDS DECISION` |103 | Only the lead stage passes, no READY score | Bid on leads; send deeper stages as secondary; say plainly that this platform can't learn pipeline yet |104 | Nothing passes the volume test | Send every stage as secondary for measurement; bid on the platform's lead event; revisit when volume grows |105 106 For Meta, Conversion Leads applies only to Instant Forms leads; website leads go through the Conversions API as measurement.107 1087. **Write the spec per platform.** One table per platform: conversion action name (the CRM stage name, so reports and bidding read the same word), type (LinkedIn: the rule type, such as `SALES_QUALIFIED_LEAD`; Meta: the CRM event for Conversion Leads; OpenAI: `lead_created` or `custom` with a `custom_event_name`), primary or secondary, value rule, identifiers sent, deduplication ID, upload path (the CRM's native integration, Data Manager, an automation tool, or the API), frequency, the window setting, and consent fields. Platform specifics: `references/platform-windows.md`.109 1108. **Write the data contract.** The CRM fields the plan needs: each platform's click ID on the contact, copied to the opportunity when it is created; a date field per stage; the won amount; consent state where the regions need it. Hash email and phone at upload, never before storing them in the CRM.111 1129. **Check the plan** (the loop below), then hand over.113 114## Check and verdict115 116Checks on the plan:117 118| ID | Passes when |119| --- | --- |120| L1 | Each bid-on stage has 80% or more of its events inside that platform's window |121| L2 | Each bid-on stage meets the volume test |122| L3 | Each platform has 1 primary conversion per real event; deeper stages are secondary |123| L4 | Every value shows its inputs (stage-to-won share, median won amount, cohort size) from the reader's data |124| L5 | Every identifier the spec sends is in the data contract, and the platform's match key rate is 50% or more |125| L6 | Upload frequency is at least daily where the event age limit is 7 days, and never longer than any limit |126| L7 | Where the regions include the EEA, the UK or Switzerland, uploads carry consent; only hashed personal data leaves the CRM |127| L8 | Every window and limit cites its page and the date checked, and the date is under 90 days old |128| L9 | Each event carries the date the stage happened, and stages that can be undone are sent once |129 130| Verdict | Condition (first match wins) |131| --- | --- |132| `BLOCKED` | No lead or stage data of any kind (no export, no report) after asking |133| `NOT READY` | The CRM holds no stage dates, or every platform in scope has under 50% match keys: fix tracking first and deliver the data contract |134| `NEEDS DECISION` | 2 plans are both viable and trade depth for volume (a deeper stage near the floor against a shallower one with several times the volume), or a predicted stage is on offer |135| `READY WITH GAPS` | The plan passes L1 to L9, and a platform loses deeper stages to its window, or coverage is partial |136| `READY` | The plan passes L1 to L9 for every platform with full coverage |137 138Named stops: `BLOCKED` asks for the export. `NEEDS DECISION` shows both plans side by side: stage, monthly volume, share inside the window, the value used, and what each teaches the platform. No other stops.139 140## Loop141 1421. Run L1 to L9 on the plan.1432. Fix each failure: L1 or L2, move the bid-on stage up 1 level; L4, drop the value or show its inputs; L5, add the field to the data contract or mark the platform `NOT READY`; L6, raise the frequency; L7, add the consent field; L8, re-read the page or mark the figure `to re-check`.1443. Check again. At most 2 rounds, then hand over with what still fails, labelled.145 146## Learn147 148- The reader picks a plan at `NEEDS DECISION`: write the choice and reason as a `fact`.149- 60 to 90 days after launch, the reader reports what changed (opportunities from the platform, cost per opportunity): write a `fact` with the figures and the CRM report as source.150- The reader changes a default (floor, the 80% test): write a `proposal`.151- A platform window changed since the reference date: write a `fact` with the page and the new figure.152 153Example: `- 2026-10-24 | crm-feedback-loop | fact | LinkedIn bids on SQL (365-day rule), Google on MQL with stage values | Why: reader chose at NEEDS DECISION, sales cycle 74 days median | Status: noted`154 155## Output156 157```158Verdict: <READY | READY WITH GAPS | NEEDS DECISION | NOT READY | BLOCKED> · Coverage: <complete | partial (what's missing)> · Timing: <script | by hand> · Windows checked: <date>159 160Stage timing (days from click):161| Stage | Events | Median | p90 | Inside: Google GCLID 90 / ECL 63 / LinkedIn 365 / Meta 28 / OpenAI 30 | Per month by platform | Stage-to-won (cohort) | Value |162 163Plan per platform:164| Platform | Bid on | Secondary | Value rule | Identifiers | Upload path, frequency | Window setting | Share of deeper stages lost |165 166Spec: <one table per platform, step 7>167Data contract: <fields to add or fix>168Checks: L1 to L9 pass or fail, with the round they passed in169Gaps: <what the windows lose, by stage and platform>170Learnings applied: <list, or none>171```172 173Then the handoff block.174 175## Hand off176 177```handoff178skill: crm-feedback-loop179version: 1.0.0180verdict: READY WITH GAPS181coverage: partial (no Meta Instant Forms leads)182for: <company> paid platforms183outputs:184 bid_on: {google: mql, linkedin: sql, openai: lead}185 values_from: mature cohort of 214 leads, median won amount from CRM186 lost_to_window: {google: {won: 0.71}, openai: {sql: 0.64, won: 1.0}}187 fields_to_add: [oppref, li_fat_id on opportunity]188 windows_checked: 2026-10-24189next: [tracking-audit, pipeline-report]190open: [confirm LinkedIn rule type supports 365 days]191```192 193`tracking-audit` runs again after the build to check the imports. `pipeline-report` reads `bid_on` to note which stage each platform was optimizing for.194 195## Failure modes196 197| Problem | Do this |198| --- | --- |199| The export has lead created dates but no click dates | Use the created date and say windows are measured from the lead, which runs a few days later than the click |200| Stage dates are overwritten when a record re-enters a stage | Use the first date; if only the latest exists, say timing is understated |201| The reader asks what match rate or conversion rate to expect | There is no such figure here; the plan uses their own data and the platforms' limits only |202| A platform's page has changed since the reference date | Use the current page, cite today's date, write a `fact` learning |203| The sales cycle differs a lot by segment (deal size, region) | Run the timing per segment and plan the bid-on stage per segment's campaigns |204| The reader asks the agent to set up the import | Decline: this skill writes the spec. Point to the platform's own integration or the person who owns the account |205 206## Influenced by207 208- Google's documentation on enhanced conversions for leads and offline conversion imports, including the 90-day and 63-day upload limits: https://support.google.com/google-ads/answer/15713840?hl=en209- LinkedIn's, Meta's and OpenAI's conversions API documentation, for their windows and event age limits (links and dates in `references/platform-windows.md`).210- SHAKEUP's MarkOps practice: bid on the deepest stage the window allows, value earlier stages with the company's own conversion rates, and say what each platform can't see.