Individual skill
medbridge-sales-ops
Use for MedBridge Sales Ops API tasks that require account-ready JSON matching a provided answer template, including RFQ or quote pricing, EXW and freight decision packages, catalog tier selection, quote policies, opportunity milestone reconciliation, payments, revenue recognition, events, vouchers, and follow-up actions.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_002/fewshot/codex/fewshot_attempt_01/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- sales Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesSKILL.mdcore · 6,552 bytesagents/openai.yamlasset · 231 bytesreferences/medbridge_rules.mddoc · 5,948 bytesscripts/medbridge_fetch.pyruns · 6,747 bytes
Read excerpt
# MedBridge Sales Ops
## Core Workflow
1. Read the task prompt and `input/payloads/answer_template.json` first. Treat the template as the output contract: keep its keys, object nesting, enum vocabulary, booleans, nulls, money precision, and array semantics.
2. Resolve the API base URL from the runner text or environment. Query only the shared MedBridge Sales Ops API. Start with `GET /api`; use direct endpoints when available and fall back to collection lists or `GET /api/search?q=<text>` when an ID endpoint is not implemented.
3. Extract all target IDs and constraints from the prompt: customer, quote/RFQ/opportunity, product/module codes, quantity, quote/as-of date, contact, event, voucher, freight requirement, and any explicit instruction such as EXW-only or module-level pricing.
4. Fetch and cross-check the source records. Do not rely on prompt text alone when the API has a record. Reject distractor records that only partially match, such as wrong customer, wrong opportunity, wrong shipment size, unrelated route, explicit distractor/mismatch status, or component details when the task asks for module-level lines.
5. Fill only the requested template. Output valid JSON only, with no markdown, notes, or extra keys.
Use [references/medbridge_rules.md](references/medbridge_rules.md) for calculation and status rules. Use [scripts/medbridge_fetch.py](scripts/medbridge_fetch.py) to gather linked records quickly without hand-writing repeated curl calls.
## API Discovery