TriMed 33 v1.1.1
Read-only CRM insights
Save this plugin to Following and return to review observed changes. Follow up to 10 plugins free.
From the marketplace listing
33CRM is a business CRM connection for company administrators to review leads, customers, deals, pipeline, bookings, conversation operational metadata, stored Meta advertising data, WhatsApp campaign aggregates, and bounded business performance reports in ChatGPT. The connection is scoped to the company bound to the administrator’s OAuth grant and is read-only. It cannot create, update, delete, assign, book, cancel, send, launch, sync, refresh, or select another tenant. Conversation message bodies, attachments, clinical notes, appointment notes, credentials, recipient lists, WhatsApp template content or variables, advertising audiences, and creative URLs are not returned. Some tools may return CRM contact fields such as name, phone number, and email when those fields are part of the requested business record.
Language: English · Automatically detected from descriptions.
Oct 27, 2026 · 1 saved observations
Metadata · Oct 27, 2026 · 00:51 UTC · Compared with Oct 24, 2026 · 13:38 UTC
Package or technical metadata updated
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Oct 24, 2026 · 13:38 UTC
Not present
Oct 27, 2026 · 00:51 UTC
false
From the developer’s listing and package; capabilities are not independently tested. Package observed Nov 3, 2026.
Review scenarios; not an exhaustive list.
33CRM provides read-only access to CRM business data through this plugin. The plugin does not sell products, process payments, or execute commerce transactions.
Terms may have changed since this observation.
Exact text from the indicated source. A mention alone does not establish support for your task.
33CRM is a business CRM connection for company administrators to review leads, customers, deals, pipeline, bookings, conversation operational metadata, stored Meta advertising data, WhatsApp campaign aggregates, and bounded business performance reports in ChatGPT. The connection is scoped to the company bound to the administrator’s OAuth grant and is read-only. It cannot create, update, delete, assign, book, cancel, send, launch, sync, refresh, or select another tenant. Conversation message bodies, attachments, clinical notes, appointment notes, credentials, recipient lists, WhatsApp template content or variables, advertising audiences, and creative URLs are not returned. Some tools may return CRM contact fields such as name, phone number, and email when those fields are part of the requested business record.
---
name: booking-attendance-review
description: Analyze 33CRM booking volume, attendance, no-shows, cancellations, status mix, branches, owners, and upcoming booking records. Use for appointment operations, attendance reviews, no-show analysis, and branch booking workload.
---
Use this skill for booking and attendance operations.
Workflow:
1. Resolve the requested date range.
2. Call `get_booking_report` for total bookings, attended count/share, status breakdown, and branch breakdown.
3. Call `list_bookings` when the user requests the actual booking records, upcoming appointments, a status filter, branch, sales rep, or lead.
4. Call `get_booking` only for one identified booking.
5. Call `list_branches` or `list_sales_reps` when IDs/names are needed for filters.
Output:
- Booking volume
- Attendance and status mix
- Branch distribution
- Upcoming / filtered booking list when requested
- Operational attention items
- Data caveats
Rules:
- `attended_share_of_all_bookings` uses all bookings in the period as the denominator; it is not necessarily a completed-appointment show-up rate.
- Do not infer treatment type, diagnosis, clinical status, or patient outcome.
- Appointment notes and clinical fields are not available and must not be invented.
- Reply in the user's language.
- Read-only only.
Referenced files: 1 — file references are metadata, not package contents.
---
name: conversation-operations-review
description: Review 33CRM conversation workload by channel and operational status, including active, waiting, escalated, resolved, timestamps, and message counters. Use for inbox workload, escalation volume, channel mix, stale-conversation checks, or conversation operations.
---
Use this skill for conversation operations, not conversation-content analysis.
Workflow:
1. Resolve the period.
2. Call `get_conversation_report` for volume by current channel and status for conversations created in the window.
3. Call `list_conversations` for operational records filtered by channel, status, or activity dates.
4. Call `get_conversation` for one conversation's metadata and total/inbound/outbound/per-sender counters.
5. Use pagination when needed.
Output:
- Conversation volume
- Channel mix
- Status mix
- Escalated / waiting workload
- Specific conversation counters when requested
- Operational attention items
- Caveats
Rules:
- Never claim to have read message text: message bodies, attachments, and media are not returned.
- Current status is an as-of snapshot and may differ from status during the requested window.
- Do not infer customer intent, medical information, sentiment beyond the explicit stored field, or content not returned.
- Reply in the user's language.
- Read-only only.
Referenced files: 1 — file references are metadata, not package contents.
---
name: daily-weekly-admin-brief
description: Produce a concise daily or weekly operating brief from 33CRM. Use when a company admin asks what happened today, this week, yesterday, or over a short operating window and wants sales, bookings, marketing, pipeline, and conversation signals in one brief.
---
Use this skill for short recurring operating briefs.
Period handling:
1. If the user says today, use today's UTC calendar date as both date bounds where supported.
2. If the user says yesterday, use yesterday as both bounds.
3. If the user says this week or weekly, use the requested calendar week when clear; otherwise use the most recent 7 days and say so.
4. If the user asks for a comparison, call the same report tools for the immediately preceding equal-length period.
Core tools:
- `sales_summary`
- `get_sales_report`
- `get_booking_report`
- `get_marketing_report`
- `get_conversation_report`
- `pipeline_summary` when a current pipeline snapshot is useful
Output:
- Period covered
- What changed / what happened
- Sales and lead pulse
- Bookings and attendance
- Marketing pulse
- Conversation workload
- Current pipeline snapshot when relevant
- 3-5 attention items based only on observed data
Rules:
- Reply in the user's language.
- Distinguish current snapshots from period metrics.
- Do not treat booked value as revenue or current amount paid as period cash flow.
- Do not claim causation between Meta spend and CRM conversion unless the returned data directly supports it.
- Do not read or summarize conversation content; only operational metadata is available.
- If data is empty, stale, or pagination-limited, say so explicitly.
- Read-only workflow; never claim to create, assign, send, book, or modify anything.
Referenced files: 1 — file references are metadata, not package contents.
---
name: executive-crm-brief
description: Create a management-level 33CRM brief across sales, pipeline, bookings, marketing, and conversation operations. Use when an owner, CEO, or company admin asks for an executive overview, business pulse, management summary, or cross-functional CRM performance brief.
---
Use this skill for a cross-functional executive view of the authenticated company.
Core workflow:
1. Resolve the requested period. If the user gives no period, use the most recent 30 days for period reports and clearly label `pipeline_summary` as a current snapshot.
2. Call `sales_summary` for lead-cohort performance.
3. Call `get_sales_report` for deal count, booked value, amount paid to date, stage, and owner breakdowns.
4. Call `pipeline_summary` for the current pipeline snapshot.
5. Call `get_booking_report` for booking volume and attendance.
6. Call `get_marketing_report` for stored Meta delivery/spend by ad account.
7. Call `get_conversation_report` for conversation volume by channel/status.
8. Use pagination or narrower filters if a tool says results are incomplete.
Output:
- Executive summary
- Key commercial metrics
- Pipeline position
- Booking/attendance position
- Marketing delivery
- Conversation workload
- Items needing management attention
- Data caveats
Rules:
- Reply in the user's language.
- Keep lead metrics and deal metrics separate; they are different populations.
- `booked_value` is agreed deal value, not recognized revenue.
- `amount_paid_to_date` is the current collected amount on deals in the selected deal cohort, not cash received during the period.
- Meta provider leads are not CRM leads and must not be treated as directly attributed conversions.
- Stored Meta data may be stale; do not imply a live provider refresh.
- Conversation tools return operational metadata and counters, not message bodies.
- Do not infer clinical, medical, treatment, or patient outcomes.
- Do not invent benchmarks, targets, trends, or causes that are not supported by the returned data.
- This workflow is read-only. Never imply that CRM records were changed.
Referenced files: 1 — file references are metadata, not package contents.
---
name: growth-performance-brief
description: Combine 33CRM marketing delivery with CRM lead-funnel and sales outcomes in one growth brief. Use when the user wants marketing plus lead sources plus funnel conversion side by side, without assuming direct attribution between Meta and CRM outcomes.
---
Use this skill for a combined growth view.
Workflow:
1. Resolve the requested period.
2. Call `get_marketing_report` for stored Meta delivery/spend by account.
3. Call `sales_summary` for CRM lead volume, source mix, qualification, attendance, won/lost outcomes, and rates.
4. Call `get_sales_report` when the user also wants deal/booked-value context.
5. Use `get_ad_insights` only when daily marketing detail is needed.
6. Use `list_leads` only when the user asks to inspect the underlying CRM leads.
Output:
- Growth summary
- Marketing delivery and spend
- CRM lead-source mix
- Lead-funnel outcomes
- Deal context when requested
- Side-by-side observations
- Attribution/data caveats
Rules:
- Present Meta provider metrics and CRM outcomes side by side unless a direct relationship is explicitly present in returned data.
- Do not claim that a campaign caused CRM leads, deals, revenue, or attendance merely because dates overlap.
- Provider leads are not the same as CRM leads.
- Booked value is not recognized revenue.
- Stored Meta figures may lag the provider.
- Reply in the user's language.
- Read-only only.
Referenced files: 1 — file references are metadata, not package contents.
---
name: lead-funnel-review
description: Review the 33CRM lead funnel, lead sources, qualification/win/loss outcomes, pipeline-stage distribution, and recent lead records. Use when the user asks about lead generation quality, funnel health, conversion, sources, or leads needing operational attention.
---
Use this skill for lead-funnel questions.
Workflow:
1. Resolve the requested period.
2. Call `sales_summary` first for lead-cohort totals, qualified/attended/won/lost metrics, by-stage and by-source breakdowns.
3. Use `list_leads` when the user needs the underlying recent leads, workflow status, source, stage, or owner.
4. Use `get_lead` only after identifying a specific lead and when stage history is needed.
5. Use `pipeline_summary` only as supplemental current deal-pipeline context; do not present it as the lead funnel.
Output:
- Funnel overview
- Source mix
- Stage / outcome mix
- Leads needing follow-up based on returned workflow state when requested
- Data quality / pagination notes
- Clear distinction between lead funnel and deal pipeline
Rules:
- Do not infer ad attribution from a lead source beyond what the CRM explicitly stores.
- Do not infer reasons for won/lost outcomes from fields that are not returned.
- Do not expose or imply clinical information.
- Reply in the user's language.
- Read-only only.
Referenced files: 1 — file references are metadata, not package contents.
---
name: meta-ads-performance-review
description: Analyze stored Meta campaign, ad, and insight data in 33CRM, including impressions, clicks, provider leads, spend, account context, and data freshness. Use for Meta ads performance, campaign review, spend review, or ad-delivery analysis.
---
Use this skill for Meta advertising performance stored in 33CRM.
Workflow:
1. Resolve the period and optional ad-account/campaign filters.
2. Call `get_marketing_report` for account-level stored totals.
3. Call `get_ad_insights` for daily rows or ad/campaign/account-level detail.
4. Call `list_meta_campaigns` and `get_meta_campaign` for campaign status/objective/schedule context.
5. Call `list_ads` to identify ads for insight filtering when needed.
Output:
- Spend and delivery summary
- Account-level performance
- Campaign/ad context
- Daily trend observations when enough data is available
- Data freshness
- Caveats and operational observations
Rules:
- Data is stored in 33CRM; these tools do not call or refresh Meta live.
- Provider-reported leads are not automatically CRM leads or conversions.
- Do not calculate or claim ROI, revenue attribution, CTR/CPC, or other derived metrics unless the user explicitly requests a mathematically valid derivation from compatible returned data.
- Never sum daily reach as unique reach.
- Never combine spend across different currencies.
- Reply in the user's language.
- Read-only only.
Referenced files: 1 — file references are metadata, not package contents.
---
name: sales-performance-review
description: Analyze 33CRM sales performance using lead-cohort metrics, deal reports, owner breakdowns, and the current pipeline. Use for sales reviews, conversion reviews, owner/team performance, booked value, amount paid, and pipeline health questions.
---
Use this skill for sales performance analysis.
Workflow:
1. Resolve the date window.
2. Call `sales_summary` for lead-cohort counts, conversion-related rates, source breakdowns, and stage breakdowns.
3. Call `get_sales_report` for period deals, booked value, current amount paid to date, by stage and owner.
4. Call `pipeline_summary` when the user asks about pipeline health or current stage distribution.
5. Call `list_sales_reps` only when you need the current active sales-rep directory for context.
6. If the user asks for a specific deal, use `list_deals` or `get_deal`.
Output:
- Sales summary
- Lead funnel metrics
- Deal and money metrics
- Owner/team breakdown
- Pipeline observations
- Risks / attention items supported by the data
- Metric caveats
Rules:
- Leads and deals are different entities; never merge their counts or rates as if they were the same cohort.
- `booked_value` is agreed deal value, not recognized revenue.
- `amount_paid_to_date` is not a dated cash-receipts metric.
- Current pipeline stages are a snapshot and are not necessarily the stage held during the selected period.
- Avoid subjective employee rankings unless the user explicitly asks for a factual comparison; present documented metrics rather than unsupported judgments.
- Reply in the user's language.
- Read-only only.
Referenced files: 1 — file references are metadata, not package contents.
Adds eight reusable 33CRM skills and a secure read-only MCP integration for leads, deals, pipeline, sales reporting, conversations, customers, bookings, WhatsApp campaign reporting, and stored Meta advertising data. This submission includes five validated positive reviewer test cases, three negative test cases, and a reviewer demo recording.
Declared in the saved package. Remote tools may change independently.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 3, 2026.
plugin_asdk_app_6ac14ac19fa08191aee9823a6f41d6a7
Download plugin data (JSON)