← Follow Up BossCONTENT HISTORY
WHAT CHANGED
Update to Follow Up Boss
Snapshot Nov 18, 2026 · 06:19 UTC · version 0.2.5
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Save Follow Up Boss and check future changes in Following.
Up to 3 plugins free · no card required.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Analyze Follow Up Boss team performance, agent activity, conversation counts, follow-up queues, lead sources, stage consistency and bounded CRM records while preserving metric definitions and coverage.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 119
}
],
"name": "fub-reporting",
"skill_md_contents": "---\nname: fub-reporting\ndescription: Analyze Follow Up Boss team performance, agent activity, conversation counts, follow-up queues, lead sources, stage consistency and bounded CRM records while preserving metric definitions and coverage.\n---\n\n# FUB reporting\n\nInspect the live FUB tools before choosing a report. The [catalog](../fub-mcp-tools/references/tool-index.md) documents the source surface; deployment and user permissions may expose fewer tools. Prefer purpose-built reports to reconstructing metrics from incomplete raw lists.\n\n## Choose by metric\n\n| Question | Tool |\n| --- | --- |\n| Team performance, response speed, trends, stuck stages | `get_team_performance` |\n| Manager daily brief and per-agent next actions | `get_team_daily_brief` → `render_team_daily_brief` |\n| Follow-up leads for the selected brief agent | `get_agent_follow_up_leads` → `render_agent_follow_up_leads` |\n| Internal manager note for the selected lead | `draft_manager_follow_up_note` from the canonical selected lead; posting uses the separate interaction review |\n| Per-agent counts under the follow-up rule | `get_needs_follow_up_counts` |\n| Calls and occurred appointments by agent | `get_agent_activity_counts` |\n| Qualifying call conversations for one agent | `get_agent_conversation_count` |\n| Qualifying call conversations for a supplied team | `get_team_conversation_counts` |\n| Bounded lead-source comparison | `get_source_performance`, if available |\n| Stage/timeframe/note contradictions | `get_stage_definitions` then `get_stage_consistency_review` |\n| Why a contact appears in a list or automation | `inspect_fub_diagnostics` plus relevant authorized readers |\n| Account vocabulary and completeness | `get_account_schema`; select only required resource groups |\n\nFor raw data, use the appropriate `get_events`, `get_calls`, `get_text_messages`, `get_tasks`, `get_appointments`, `get_deals`, `get_pipelines`, `get_users`, `get_teams`, `get_automations`, `get_action_plans`, `get_custom_fields`, `get_templates` or `get_relationships` contract. `query_people` supplies contact searches/details; `list_notes` and `search_notes` supply note context. Read each schema rather than transferring filters between resources.\n\n## Keep definitions explicit\n\n- Qualifying conversations in the conversation-count tools are active public calls of at least 120 seconds attributed by `userId`, not all messages or all attempted calls. Supply authoritative agent IDs; for the team tool preserve exact ID/name pairs.\n- `get_agent_activity_counts` reports occurred appointments, not appointments created by the agent. Account-wide sent-text counts are unavailable there; null is not zero.\n- `get_team_performance` uses the FUB report definitions. The team mean response time is the average of agents' averages, while median/slowest use the team's underlying leads. Lead-stage snapshots are current snapshots, not date-window changes. Preserve returned exceptions.\n- `get_source_performance`'s `dealsPerScannedPerson` is a ratio of unwindowed first-page deals to activity-window people; it can exceed 1 and is not a conversion rate. Do not relabel it as one.\n- Stage consistency uses `updated` as a proxy because native stage-change time is unavailable. Explain this limit rather than claiming exact days since the stage changed.\n- `get_account_schema` distinguishes available, empty, forbidden and unavailable resources. Account tag vocabulary is unavailable; tags can be read from contacts. Template identity is not template content.\n\n## Bound conclusions by the evidence\n\nChoose explicit dates and timezone matching the user's question. Record-created filters do not measure occurrence, completion, close or activity dates. Use unchanged filters with returned pagination. Raw call phone filtering is local to a source page, so an empty matching page does not establish no calls exist.\n\nKeep totals as lower bounds when the tool says coverage is incomplete; suppress unavailable totals rather than calculating false precision. Compare agents only over equivalent periods and definitions. Report permission-limited or timed-out sections separately from empty results.\n\nData/render pairs preserve canonical results. Do not change totals, filter away missing rows without explaining, or hide limitations when passing a result to a renderer. Team-brief agent handoffs must use the exact returned user ID. Manager-note drafts do not notify or contact the agent, and drafting does not post a note.\n\nIf `fub_reference` and `fub_execute` are available, use the [read-operation workflow](../fub-mcp-tools/references/read-operations.md) for a supported bounded set of raw reads. Do not use it as a bypass for an unavailable report, permission check, or write workflow.\n"
}SHA-256 of public snapshot: 04ae8554a195030fba12f8f5a64c0069940f7440ed4c22e6c9d13fa39deb0c54