Menu

Individual skill

medbridge-sales-ops-json

0upvotes

Use this skill for MedBridge Sales Ops API tasks that require an account-ready JSON answer for quotes, RFQs, freight comparisons, customer policies, opportunity milestone reconciliation, revenue recognition, payments, events, or vouchers. Use it whenever the prompt mentions the MedBridge Sales Ops API, quote/RFQ decision packages, EXW pricing, freight validity or route risk, milestone invoices, accounting follow-ups, or asks for JSON matching an answer_template.json.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_002/fewshot/opencode/fewshot_attempt_02/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# MedBridge Sales Ops JSON

Use this skill to produce the final JSON for MedBridge Sales Ops tasks. The API is the business source of truth, and the task's `input/payloads/answer_template.json` is the output schema.

## Core Workflow

1. Read the user prompt and `input/payloads/answer_template.json` first.
2. Extract every requested identifier and constraint from the prompt: customer, quote, RFQ, opportunity, product/module codes, event, voucher, quote date or as-of date, confirmed quantities, destination/freight scope, named contact, and any requested controlled statuses.
3. Resolve the API base URL from the prompt or runner environment variables such as `TASK_ENV_BASE_URL` or `BASE_URL`. Do not hard-code a creator-side URL.
4. Discover the API with `GET /api`, then use `GET /api/search?q=<id-or-name>` for broad record discovery.
5. Fetch exact records when available: `/api/customers/{id}`, `/api/products/{code}`, `/api/rfqs/{id}`, `/api/quotes/{id}`, `/api/freight-quotes/{id}`, `/api/policies/{id}`, and `/api/opportunities/{id}`. Some finance/event detail routes may not exist; if an exact route returns `not_found`, use `/api/search` and collection endpoints such as `/api/invoices`, `/api/payments`, `/api/revenue-journals`, `/api/events`, and `/api/vouchers`, then filter locally.
6. Build the response in the exact template shape. Preserve key order and nesting, add no extra keys, and return only valid JSON.

Use exact ID joins over name matches. When using search results, reject distractors by checking the linking fields: `customer_id`, `quote_id`, `rfq_id`, `opportunity_id`, `invoice_id`, `event_id`, `voucher_code`, product code, destination, shipment size, status, and dates.
Back to top