Churn Scanner
Rank clients for human retention review using observed evidence. This is an
explainable prioritization, not a calibrated probability of cancellation.
A client roster is required; every signal family is optional.
Anti-triggers
- Working a single contract, invoice, or ticket record: use the connected
vendor skill, such as
autotask-contracts, autotask-tickets, qbo-invoices,
xero-invoices, or halopsa-tickets.
- Contract entitlements versus invoices: use
finance-pack-agreement-reconciliation.
- Per-client profitability or margin: use
finance-pack-margin-analysis.
- Executing escalation for tickets already breaching SLA: use
ops-pack-sla-escalation-playbooks.
Workflow
- Discover first. Start every scan with
conduit__search_tools. Search for
company/client rosters, tickets, surveys, invoices, agreements, and devices.
Read returned schemas and use the exact discovered names, often shaped like
<vendor-slug>__<tool_name>. The table below lists canonical MCP names, not
guaranteed gateway spellings. Never assume a vendor is connected or invent
a tool. A connected vendor without an allowed tool for the needed data is
an unavailable signal, with the missing capability described in prose.
- Establish the roster. Use every discovered roster tool from the table,
one per connected PSA (Autotask, HaloPSA, ConnectWise PSA, Syncro, or
SuperOps). If none is available, stop: "No client roster tool is available
through Conduit, so a client churn ranking cannot be produced." Do not
substitute ticket or invoice customers for a complete roster. Page through
each roster fully, retaining source, stable client IDs, and active/inactive
status. Then reconcile them into one roster: merge a client that appears in
more than one PSA only after confirming identity, and keep unconfirmed
duplicates separate and listed as coverage gaps. If one roster read fails,
continue with the others and report that PSA's clients as out of scope; if
all fail, report the errors and stop. If the operator limits the scan to one
PSA, state that scope in the summary.
- Set scope and join identities. Default to active clients, the most recent
complete 30 days versus the preceding 30 days, and renewals within 90 days.
State dates, timezone, as-of time, and operator overrides. Match sources by
explicit cross-system IDs first, then verified unique company identities.
Ask about ambiguous matches; exclude unresolved joins from scoring, and
list them as coverage gaps. Deduplicate invoices and tickets across sources.
- Read available evidence. Use only the discovery result matching an
allowed table entry. Paginate and apply the same client, date, and status
scope across both comparison windows. Retain source, record identifiers,
timestamps, counts, and denominators. Use detail tools only where needed.
On permission errors or missing fields, mark the affected signal unavailable;
on rate limits, follow the returned retry guidance with bounded retries.
Unfinished pagination is incomplete coverage, never a zero result: if any
required page for a family cannot be read, that family is unassessable for
every client the missing pages could cover. Do not score partial counts.
- Score and report. Apply the rules below per client. Preserve every roster
client, including those with no usable signals. Recommend human review only;
this scan does not contact clients or change operational records.
Only read-only list, get, search, or report tools are permitted. Never create,
update, delete, send, void, resolve, run, install, reboot, or use raw-request,
execute-tool, custom-mutation, or other passthrough tools, even if discovered.
Allowed evidence sources
| Family |
Canonical MCP tools and interpretation |
| Required roster |
autotask_search_companies; halopsa_clients_list, halopsa_clients_get, halopsa_clients_search; cw_search_companies, cw_get_company; syncro_customers_list; superops_clients_list, superops_clients_get, superops_clients_search |
| Ticket volume and text |
autotask_search_tickets, autotask_get_ticket_details, autotask_search_ticket_history, autotask_list_ticket_priorities, autotask_list_ticket_statuses; halopsa_tickets_list, halopsa_tickets_get; cw_search_tickets, cw_get_ticket; syncro_tickets_list; superops_tickets_list, superops_tickets_get; ninjaone_tickets_list, ninjaone_tickets_get; atera_tickets_list, atera_tickets_get |
| Sentiment |
Prefer a survey platform. CrewHu: crewhu_surveys_list, crewhu_surveys_search, crewhu_surveys_detractors, crewhu_surveys_promoters, crewhu_surveys_get. SmileBack: smileback_reviews_list, smileback_reviews_list_recent, smileback_reviews_get, smileback_nps_responses_list, smileback_nps_responses_get, smileback_csat_companies_list; it has no per-client endpoint, so group reviews and NPS responses by company. Preserve the returned survey scale and detractor classification. Fallback: autotask_search_ticket_notes, autotask_get_ticket_note, cw_get_ticket_notes, or subject/description fields from allowed ticket tools. Label fallback sentiment as inferred from ticket text, never as a CSAT score. |
| SLA misses |
Use the allowed ticket list/get tools and their SLA/due-date fields; there is no dedicated breach-list tool. Autotask details expose resolution-plan/due-date information; HaloPSA details can expose deadlinedate, target timestamps, and hold state. Inspect actual fields and tenant semantics before use. |
| Overdue invoices |
qbo_invoices_list (Paid/Unpaid/Overdue status filter), qbo_invoices_get; xero_invoices_list, xero_invoices_get, xero_reports_aged_receivables; autotask_search_invoices, autotask_get_invoice_details; halopsa_invoices_list, halopsa_invoices_get; cw_search_invoices, cw_get_invoice; syncro_invoices_list |
| Renewals |
autotask_search_contracts, autotask_get_contract, autotask_list_expiring_contracts; cw_search_agreements, cw_get_agreement, cw_get_agreement_additions. HaloPSA and Syncro have no contract/agreement list tool in this catalog; if those are the only PSAs, renewal evidence is unavailable. |
| Usage proxy |
datto_list_devices, datto_get_device, datto_find_device, datto_list_sites, datto_get_site; ninjaone_devices_list, ninjaone_devices_get, ninjaone_organizations_list, ninjaone_organizations_get, ninjaone_organizations_devices; cwautomate_computers_list, cwautomate_computers_get, cwautomate_computers_search, cwautomate_clients_list, cwautomate_clients_get; atera_agents_list, atera_agents_get, atera_customers_list, atera_customers_get; ncentral_list_devices, ncentral_list_devices_by_org_unit, ncentral_get_device, ncentral_get_device_service_status; superops_assets_list, superops_assets_get; syncro_assets_list; immybot_computers_list, immybot_computers_get |
RMM sources are last-seen/online/offline proxies, not product-usage analytics.
There is no dedicated product-usage or M365 usage-report tool for this skill.
With a snapshot only, report the current mix and explicitly say a trend could
not be computed. Never invent a baseline or equate offline devices with churn.
Explainable ranking
These defaults are rules of thumb for review, not industry benchmarks. Accept
operator overrides and print every threshold actually used. Each family fires
at most once, regardless of the number of sources or records supporting it.
| Independent family |
Default adverse threshold |
Intensity, 1 normally, 2 when severe |
| Ticket volume |
Recent count is at least 30% above this client's earlier count, with at least 5 earlier tickets |
Severe at 60% growth. If earlier count is below 5, show counts only, without a growth flag. |
| Sentiment |
At least 1 detractor returned by a survey platform (a CrewHu detractor, or a SmileBack negative review or NPS detractor) in the recent window |
Severe at 3 detractors. Show survey count and detractor share in both windows when available. Without surveys, flag at least 2 distinct tickets with explicit dissatisfaction; severe at 4. Cite text evidence briefly, label it qualitative inference, and count the family only once. |
| SLA misses |
Recent miss rate exceeds this client's earlier rate by at least 10 percentage points, with at least 5 assessable tickets per window |
Severe at 20 percentage points. Use tickets missing at least one assessable target divided by assessable tickets, without double-counting response and resolution misses. |
| Overdue invoices |
At least 1 unpaid invoice is at least 30 days past due as of the scan |
Severe at 60 days. Report invoice aging and overdue amount as returned by the invoice tool; preserve currencies separately. |
| Renewal proximity |
At least 1 active agreement expires within 90 days |
Severe within 30 days. Proximity is a review prompt, not proof of dissatisfaction; show days remaining and any known notice deadline. |
| Dropping usage proxy |
Historical comparable snapshots show online share falling by at least 20 percentage points against this client's earlier window |
Severe at 40 percentage points. Report fleet denominators and scope changes. Snapshot-only evidence is descriptive and does not fire a decline flag. |
For SLA assessment, use explicit breach outcomes or actual response/resolution
completion timestamps against their applicable targets. For open targets, use
the as-of time. Honor business-hours and hold semantics. A current due date
alone cannot prove a historical breach or establish an earlier miss rate;
mark the comparison unavailable when outcomes or semantics cannot be verified.
Label generic due-date comparisons as proxies rather than contractual SLA facts.
Rank by descending adverse-family count first, then summed intensity of fired
families, then client identifier for stable ties. Show the count as [N] adverse
of [N] assessable families, plus the intensity sum. A family is assessable for a
client only when every read its rule needs completed and its prerequisites are
met. Ticket volume and SLA misses need both windows and their minimum samples.
Sentiment needs the recent window; earlier surveys are context only. Overdue
invoices and renewal proximity need current data as of the scan. The usage
proxy needs comparable historical snapshots. An unassessable family contributes
neither evidence of health nor an adverse flag, is excluded from the assessable
count, and its observed counts are shown as context only. Do not normalize
sparse clients into apparently healthy accounts. Mark single-family rankings
as partial;
mark zero-family clients unranked (insufficient evidence), after ranked clients.
Flag unequal coverage so the operator can compare like-for-like cohorts.
Report format
Use placeholders only in templates; populate results solely from returned data.
Portfolio summary
As of: [timestamp and timezone]
Recent window: [window]; earlier window: [window]
Clients: [N] in scope; [N] ranked; [N] partial; [N] unranked
Sources used: [discovered names]; thresholds and overrides: [rules used]
Coverage limitations: [missing families, incomplete pages, or unresolved joins]
Clients, highest risk first
[Rank]. [Client] ([source client identifier])
Evidence: [N] adverse / [N] assessable families; intensity sum [N]
Coverage: [families assessed]; [partial or incomplete limitations]
Driving signals: [family, current metric, earlier metric if available,
threshold crossed, intensity, source tool, record identifier, timestamp]
Other observed signals: [non-adverse evidence or snapshot-only proxy]
Suggested review: [evidence-based human follow-up]
Unavailable signals per source
[Source or unconnected family]: [signal unavailable and why]
[Client or scope]: [missing fields, failed reads, uncertain identity, or history gap]
If no optional signals are available, return the roster coverage summary and
unavailable-signal section, with all clients unranked. Never fabricate data,
convert missing data to zero, or describe a lack of observations as low risk.
Related Skills
- Agreement Reconciliation:
finance-pack-agreement-reconciliation, entitlement and invoice matching.
- Margin Analysis:
finance-pack-margin-analysis, client profitability.
ops-pack-sla-escalation-playbooks (SLA Escalation Playbooks, in the separately installed ops-pack plugin): operational escalation.
1---2name: churn-scanner3description: >4 Cross-vendor client retention risk ranking from ticket volume, customer5 sentiment, SLA misses, overdue invoices, upcoming agreement renewals, and6 RMM availability proxies. Covers evidence-based scoring, source coverage,7 and incomplete-data reporting through Conduit.8when_to_use: >-9 When scanning an MSP client portfolio for churn risk or deciding which10 accounts need retention attention. Use when: churn scanner, at-risk clients,11 retention review, who might leave, customer health ranking, or churn signals.12metadata:13 source: https://skillmd.com/skills/wyre-ai/churn-scanner14---1516# Churn Scanner1718Rank clients for human retention review using observed evidence. This is an19explainable prioritization, not a calibrated probability of cancellation.20A client roster is required; every signal family is optional.2122## Anti-triggers2324- **Working a single contract, invoice, or ticket record:** use the connected25 vendor skill, such as `autotask-contracts`, `autotask-tickets`, `qbo-invoices`,26 `xero-invoices`, or `halopsa-tickets`.27- **Contract entitlements versus invoices:** use `finance-pack-agreement-reconciliation`.28- **Per-client profitability or margin:** use `finance-pack-margin-analysis`.29- **Executing escalation for tickets already breaching SLA:** use30 `ops-pack-sla-escalation-playbooks`.3132## Workflow33341. **Discover first.** Start every scan with `conduit__search_tools`. Search for35 company/client rosters, tickets, surveys, invoices, agreements, and devices.36 Read returned schemas and use the exact discovered names, often shaped like37 `<vendor-slug>__<tool_name>`. The table below lists canonical MCP names, not38 guaranteed gateway spellings. Never assume a vendor is connected or invent39 a tool. A connected vendor without an allowed tool for the needed data is40 an unavailable signal, with the missing capability described in prose.412. **Establish the roster.** Use every discovered roster tool from the table,42 one per connected PSA (Autotask, HaloPSA, ConnectWise PSA, Syncro, or43 SuperOps). If none is available, stop: "No client roster tool is available44 through Conduit, so a client churn ranking cannot be produced." Do not45 substitute ticket or invoice customers for a complete roster. Page through46 each roster fully, retaining source, stable client IDs, and active/inactive47 status. Then reconcile them into one roster: merge a client that appears in48 more than one PSA only after confirming identity, and keep unconfirmed49 duplicates separate and listed as coverage gaps. If one roster read fails,50 continue with the others and report that PSA's clients as out of scope; if51 all fail, report the errors and stop. If the operator limits the scan to one52 PSA, state that scope in the summary.533. **Set scope and join identities.** Default to active clients, the most recent54 complete 30 days versus the preceding 30 days, and renewals within 90 days.55 State dates, timezone, as-of time, and operator overrides. Match sources by56 explicit cross-system IDs first, then verified unique company identities.57 Ask about ambiguous matches; exclude unresolved joins from scoring, and58 list them as coverage gaps. Deduplicate invoices and tickets across sources.594. **Read available evidence.** Use only the discovery result matching an60 allowed table entry. Paginate and apply the same client, date, and status61 scope across both comparison windows. Retain source, record identifiers,62 timestamps, counts, and denominators. Use detail tools only where needed.63 On permission errors or missing fields, mark the affected signal unavailable;64 on rate limits, follow the returned retry guidance with bounded retries.65 Unfinished pagination is incomplete coverage, never a zero result: if any66 required page for a family cannot be read, that family is unassessable for67 every client the missing pages could cover. Do not score partial counts.685. **Score and report.** Apply the rules below per client. Preserve every roster69 client, including those with no usable signals. Recommend human review only;70 this scan does not contact clients or change operational records.7172Only read-only list, get, search, or report tools are permitted. Never create,73update, delete, send, void, resolve, run, install, reboot, or use raw-request,74execute-tool, custom-mutation, or other passthrough tools, even if discovered.7576## Allowed evidence sources7778| Family | Canonical MCP tools and interpretation |79|---|---|80| Required roster | `autotask_search_companies`; `halopsa_clients_list`, `halopsa_clients_get`, `halopsa_clients_search`; `cw_search_companies`, `cw_get_company`; `syncro_customers_list`; `superops_clients_list`, `superops_clients_get`, `superops_clients_search` |81| Ticket volume and text | `autotask_search_tickets`, `autotask_get_ticket_details`, `autotask_search_ticket_history`, `autotask_list_ticket_priorities`, `autotask_list_ticket_statuses`; `halopsa_tickets_list`, `halopsa_tickets_get`; `cw_search_tickets`, `cw_get_ticket`; `syncro_tickets_list`; `superops_tickets_list`, `superops_tickets_get`; `ninjaone_tickets_list`, `ninjaone_tickets_get`; `atera_tickets_list`, `atera_tickets_get` |82| Sentiment | Prefer a survey platform. CrewHu: `crewhu_surveys_list`, `crewhu_surveys_search`, `crewhu_surveys_detractors`, `crewhu_surveys_promoters`, `crewhu_surveys_get`. SmileBack: `smileback_reviews_list`, `smileback_reviews_list_recent`, `smileback_reviews_get`, `smileback_nps_responses_list`, `smileback_nps_responses_get`, `smileback_csat_companies_list`; it has no per-client endpoint, so group reviews and NPS responses by company. Preserve the returned survey scale and detractor classification. Fallback: `autotask_search_ticket_notes`, `autotask_get_ticket_note`, `cw_get_ticket_notes`, or subject/description fields from allowed ticket tools. Label fallback sentiment as inferred from ticket text, never as a CSAT score. |83| SLA misses | Use the allowed ticket list/get tools and their SLA/due-date fields; there is no dedicated breach-list tool. Autotask details expose resolution-plan/due-date information; HaloPSA details can expose `deadlinedate`, target timestamps, and hold state. Inspect actual fields and tenant semantics before use. |84| Overdue invoices | `qbo_invoices_list` (Paid/Unpaid/Overdue status filter), `qbo_invoices_get`; `xero_invoices_list`, `xero_invoices_get`, `xero_reports_aged_receivables`; `autotask_search_invoices`, `autotask_get_invoice_details`; `halopsa_invoices_list`, `halopsa_invoices_get`; `cw_search_invoices`, `cw_get_invoice`; `syncro_invoices_list` |85| Renewals | `autotask_search_contracts`, `autotask_get_contract`, `autotask_list_expiring_contracts`; `cw_search_agreements`, `cw_get_agreement`, `cw_get_agreement_additions`. HaloPSA and Syncro have no contract/agreement list tool in this catalog; if those are the only PSAs, renewal evidence is unavailable. |86| Usage proxy | `datto_list_devices`, `datto_get_device`, `datto_find_device`, `datto_list_sites`, `datto_get_site`; `ninjaone_devices_list`, `ninjaone_devices_get`, `ninjaone_organizations_list`, `ninjaone_organizations_get`, `ninjaone_organizations_devices`; `cwautomate_computers_list`, `cwautomate_computers_get`, `cwautomate_computers_search`, `cwautomate_clients_list`, `cwautomate_clients_get`; `atera_agents_list`, `atera_agents_get`, `atera_customers_list`, `atera_customers_get`; `ncentral_list_devices`, `ncentral_list_devices_by_org_unit`, `ncentral_get_device`, `ncentral_get_device_service_status`; `superops_assets_list`, `superops_assets_get`; `syncro_assets_list`; `immybot_computers_list`, `immybot_computers_get` |8788RMM sources are last-seen/online/offline proxies, not product-usage analytics.89There is no dedicated product-usage or M365 usage-report tool for this skill.90With a snapshot only, report the current mix and explicitly say a trend could91not be computed. Never invent a baseline or equate offline devices with churn.9293## Explainable ranking9495These defaults are rules of thumb for review, not industry benchmarks. Accept96operator overrides and print every threshold actually used. Each family fires97at most once, regardless of the number of sources or records supporting it.9899| Independent family | Default adverse threshold | Intensity, 1 normally, 2 when severe |100|---|---|---|101| Ticket volume | Recent count is at least 30% above this client's earlier count, with at least 5 earlier tickets | Severe at 60% growth. If earlier count is below 5, show counts only, without a growth flag. |102| Sentiment | At least 1 detractor returned by a survey platform (a CrewHu detractor, or a SmileBack negative review or NPS detractor) in the recent window | Severe at 3 detractors. Show survey count and detractor share in both windows when available. Without surveys, flag at least 2 distinct tickets with explicit dissatisfaction; severe at 4. Cite text evidence briefly, label it qualitative inference, and count the family only once. |103| SLA misses | Recent miss rate exceeds this client's earlier rate by at least 10 percentage points, with at least 5 assessable tickets per window | Severe at 20 percentage points. Use tickets missing at least one assessable target divided by assessable tickets, without double-counting response and resolution misses. |104| Overdue invoices | At least 1 unpaid invoice is at least 30 days past due as of the scan | Severe at 60 days. Report invoice aging and overdue amount as returned by the invoice tool; preserve currencies separately. |105| Renewal proximity | At least 1 active agreement expires within 90 days | Severe within 30 days. Proximity is a review prompt, not proof of dissatisfaction; show days remaining and any known notice deadline. |106| Dropping usage proxy | Historical comparable snapshots show online share falling by at least 20 percentage points against this client's earlier window | Severe at 40 percentage points. Report fleet denominators and scope changes. Snapshot-only evidence is descriptive and does not fire a decline flag. |107108For SLA assessment, use explicit breach outcomes or actual response/resolution109completion timestamps against their applicable targets. For open targets, use110the as-of time. Honor business-hours and hold semantics. A current due date111alone cannot prove a historical breach or establish an earlier miss rate;112mark the comparison unavailable when outcomes or semantics cannot be verified.113Label generic due-date comparisons as proxies rather than contractual SLA facts.114115Rank by descending adverse-family count first, then summed intensity of fired116families, then client identifier for stable ties. Show the count as [N] adverse117of [N] assessable families, plus the intensity sum. A family is assessable for a118client only when every read its rule needs completed and its prerequisites are119met. Ticket volume and SLA misses need both windows and their minimum samples.120Sentiment needs the recent window; earlier surveys are context only. Overdue121invoices and renewal proximity need current data as of the scan. The usage122proxy needs comparable historical snapshots. An unassessable family contributes123neither evidence of health nor an adverse flag, is excluded from the assessable124count, and its observed counts are shown as context only. Do not normalize125sparse clients into apparently healthy accounts. Mark single-family rankings126as partial;127mark zero-family clients unranked (insufficient evidence), after ranked clients.128Flag unequal coverage so the operator can compare like-for-like cohorts.129130## Report format131132Use placeholders only in templates; populate results solely from returned data.133134```text135Portfolio summary136As of: [timestamp and timezone]137Recent window: [window]; earlier window: [window]138Clients: [N] in scope; [N] ranked; [N] partial; [N] unranked139Sources used: [discovered names]; thresholds and overrides: [rules used]140Coverage limitations: [missing families, incomplete pages, or unresolved joins]141142Clients, highest risk first143[Rank]. [Client] ([source client identifier])144 Evidence: [N] adverse / [N] assessable families; intensity sum [N]145 Coverage: [families assessed]; [partial or incomplete limitations]146 Driving signals: [family, current metric, earlier metric if available,147 threshold crossed, intensity, source tool, record identifier, timestamp]148 Other observed signals: [non-adverse evidence or snapshot-only proxy]149 Suggested review: [evidence-based human follow-up]150151Unavailable signals per source152[Source or unconnected family]: [signal unavailable and why]153[Client or scope]: [missing fields, failed reads, uncertain identity, or history gap]154```155156If no optional signals are available, return the roster coverage summary and157unavailable-signal section, with all clients unranked. Never fabricate data,158convert missing data to zero, or describe a lack of observations as low risk.159160## Related Skills161162- [Agreement Reconciliation](../agreement-reconciliation/SKILL.md): `finance-pack-agreement-reconciliation`, entitlement and invoice matching.163- [Margin Analysis](../margin-analysis/SKILL.md): `finance-pack-margin-analysis`, client profitability.164- `ops-pack-sla-escalation-playbooks` (SLA Escalation Playbooks, in the separately installed `ops-pack` plugin): operational escalation.