← BROSH CRMCONTENT HISTORY
WHAT CHANGED
Update to BROSH CRM
Snapshot Nov 19, 2026 · 18:11 UTC · version 1.4.2
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Save BROSH CRM 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": "Review BROSH sales pipeline by period, owner, and stage; summarize deal value, coverage, stale deals, close-date risks, and evidence-backed next actions. Use for pipeline health and forecast preparation, not pipeline configuration.",
"included_files": [
{
"relative_path": "agents/openai.yaml",
"size_in_bytes": 258
}
],
"name": "brosh-pipeline-review",
"skill_md_contents": "---\nname: brosh-pipeline-review\ndescription: \"Review BROSH sales pipeline by period, owner, and stage; summarize deal value, coverage, stale deals, close-date risks, and evidence-backed next actions. Use for pipeline health and forecast preparation, not pipeline configuration.\"\n---\n\n# BROSH Pipeline Review\n\nProduce a decision-ready review grounded in actual BROSH opportunities and activities. Review is read-only unless the user also requests specific changes.\n\n## Define and retrieve the population\n\n1. Verify workspace and discover live metadata using `brosh_me` and `brosh_available_tables`. Read records through `brosh_find` and `brosh_get`, using their current argument schemas.\n2. Resolve the requested owners/team, pipeline, period, timezone, currency treatment, and as-of date. Use tenant fiscal periods when available; otherwise label calendar dates explicitly. For an unqualified request, review all accessible open sales opportunities and highlight those closing in the current calendar quarter. State that scope rather than silently restricting to the authenticated user.\n3. Filter `opportunities` to `type=\"Opportunity\"`. Quotes and invoices live in the same table and must not inflate pipeline. Discover actual stage values and won/lost semantics; do not import Salesforce/HubSpot stages or assume a custom stage is open/closed from its name alone.\n4. Retrieve IDs, names, account/contact, owner, stage, amount, currency, close date, creation date, and supported probability/next-step fields. Page through the full selected population using stable ordering where possible and deduplicate IDs. State cutoff and limitations if concurrent changes prevent a consistent snapshot. Do not present the first page as the full pipeline.\n5. Retrieve relevant activities, owners, and accounts, scoped to deal IDs and validated relationships. Activity uses `opportunities` for the deal and `person` for the contact. Distinguish direct deal evidence from account-wide activity. Missing or inaccessible activity is not proof of inactivity.\n\n## Analyze consistently\n\n- Show deal count and known open value by stage, owner, and currency. Report records with missing amount, currency, owner, stage, or close date separately. Null is not zero. Keep unknown-stage deals in an explicit unresolved bucket.\n- Keep currencies separate unless the user requests conversion using an identified rate and date. Round only for presentation; never add dollar, euro, and shekel values as one total.\n- Weighted pipeline is the sum of amount times normalized probability only when supported, with the scale established from metadata (0-1 versus 0-100). Show probability coverage and exclude missing/invalid values from the weighted subtotal; do not use arbitrary stage weights or `progress` as probability. A formula field such as `probability-exp` is read-only.\n- Coverage requires a comparable quota/target, period, currency, and definition. State numerator and denominator; omit the ratio when the target is absent or zero. Weighted pipeline and coverage are planning indicators, not revenue guarantees.\n- Flag past close dates on open deals, absent next steps, overdue tasks, missing owner/contact, material value concentrated in a few deals, and stale engagement. Use organization thresholds if known; otherwise label a 30-day no-substantive-activity threshold as an assumption. Do not mark a deal lost because it is old.\n- Deal age uses creation date. Stage age, close-date slippage, velocity, and changes since last review need historical snapshots or events. `last_modified_date` alone proves none of them. If history is absent, state that historical movement cannot be measured.\n- Win rate, if requested and closed-deal data is available, is won count divided by won plus lost count for a clearly defined close cohort. Keep it separate from open-pipeline totals and report a zero denominator as unavailable. Explain any value-weighted variant.\n\n## Prioritize and deliver\n\nLead with the few findings that could change action this period. Give the exact scope, as-of timestamp, coverage limitations, totals by currency, stage/owner breakdown, and a short ranked risk table: deal ID/name, owner, amount/currency, close date, evidence, recommended action, and proposed timing.\n\nTrace findings to actual record IDs and source dates; use links only when verified. Separate recorded commitments, inferred risks, and proposed follow-ups. Do not manufacture a commit forecast or confidence percentage from stage labels.\n\nIf the user requests updates or tasks, prepare concrete field changes from the review and execute the already authorized scope. Resolve ambiguous owners/dates before writing, re-read affected records to detect concurrent changes, and verify each result. Never automatically move close dates, change deal stages, overwrite probabilities, send messages, or create a recurring review merely because the report recommends action.\n"
}SHA-256 of public snapshot: 2ac69b78e189f527fdcc703b8bac68de9dea0430dbd02c5ad4c1a35e177facb7