Prism-Shadow

Reconcile MedBridge Sales Ops CRM tasks (B2B medical wholesale + implementation-services) against the remote Sales Ops API and emit the account-ready JSON answer. Covers QUOTE decision packages (EXW pricing, freight options, route risk, recommended mode, payment terms) and milestone RECONCILIATION packages (invoice/payment state, outstanding balance, revenue-recognition coverage, CRM follow-up routing, event/voucher linkage). Use whenever a task references MedBridge, quotes like Q-TR-*, RFQ-TR-*, opportunities like OPP-TR-*, milestones MS1/MS2/MS3, freight-quotes, revenue-journals, or the shared Sales Ops API base URL.

SCN_003 CRM support-operations solver. Resolve ticket batches (fixed-line diagnostics + gates), mobile contact-center triage, and enterprise export-complaint response packages against the shared support-console API. Apply exact metric thresholds, gate order, root-cause->team map, mobile action decision tree, and enterprise package derivation rules.

SCN_003 CRM support-console analyst. Resolve same-day ticket batches, mobile triage queues, mobile-data recovery worklists, and enterprise export-complaint response packages by querying the shared support-console API and applying fixed diagnostic thresholds, gating order, root-cause routing, and per-family decision trees.

Resolve CRM support-console tasks (SCN_003) — ticket-batch classification, mobile-data triage, and enterprise export-complaint response packages — against a remote support-console API. Use when a task asks to classify service tickets / queue snapshots, triage mobile data cases, or build an enterprise export-failure response package and references a support console API.

Resolve SCN_003 CRM support-console tasks: ticket-batch resolution, mobile contact-center triage, and enterprise export-complaint response packages. Drive the remote console API, apply diagnostic floors + gating order, and emit the per-family JSON answer.

Solve ApexCloud Retention Operations analytics tasks against the remote Retention Operations API. Encode and reproduce the exact business rules, data-hygiene conventions, policy codes, ranking/precision rules, churn-model spec, and per-archetype output schemas. Use for any CRM retention task (renewal risk queue / save plan, QBR metrics packet, receivables + pipeline operations digest, churn model validation + outreach ranking, high-touch retention action board / watchlist).

ApexCloud Retention Operations — reusable rules and verified conventions for producing renewal-risk, QBR, receivables/pipeline, churn-model, and retention-board answers from the data API.

Solve private-wealth-advisory structured planning tasks (Roth/RMD, ILIT/Crummey, GRAT/CRAT, estate-liquidity) against a remote advisory API with conflicting source documents. Produce exact JSON conforming to each task's answer template.

Guidance for using the AgentHub Python SDK (`agenthub-python`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request `agenthub-python`, or already import it.

Guidance for using the AgentHub TypeScript SDK (`@prismshadow/agenthub`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request `@prismshadow/agenthub`, or already import it.

Run the Verify LLM Vendors benchmark using the PyPI-installed `agent-vendor-verifier` CLI; before each test run validate that config.yaml is complete, ask the user for any missing required config values, then read config and confirm with the user the list of models, vendors and baseline from config plus test-file-path, config-file-path, vendor-concurrency, request-concurrency, retries, timeout; before running, check whether `agent-vendor-verifier` is installed and install it from PyPI if missing; when the user asks to add or update a benchmark test plan, ask for model name, model id, vendor, api key, provider if needed, and write the entry into config.yaml; generate or edit config.yaml; check whether runs succeeded via summary.json; aggregate or report run data and final results. Use when the user wants to run the tool-call validation benchmark, add or update test plans, create or change benchmark config, inspect benchmark outcomes, verify success from summary files, or get a consolidated view of metrics (suc