Individual skill

northwind-erp-ops

Solve Northwind Components ERP operational desk tasks using the shared REST API and structured JSON answer templates. Use this skill whenever the task involves expedite-queue dispatch, production replenishment, supplier quality scorecards, allocation-desk transfer decisions, procurement quality controls, or any Northwind operational workflow that references a REST API at a task-environment base URL and expects a JSON output conforming to a provided template.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_007/fewshot/opencode/fewshot_attempt_03/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
Yes
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

# Northwind ERP Operations Desk

This skill covers reusable patterns for solving Northwind Components operational desk tasks. Every task in this family follows the same skeleton: read a desk memo, query the shared REST API for live records, apply decision logic, and return a structured JSON response matching a supplied answer template.

## Core workflow

When a memo or prompt arrives, follow this sequence:

1. Read every payload file the prompt points to. These contain the task parameters (target wave, BOMs, supplier list, date ranges, decision policies).
2. Read the answer template. Note every required key, allowed enum value, ordering rule, and numeric precision constraint.
3. Query the API for live records. Pull fresh data for every entity the task touches -- orders, products, inventory, customers, suppliers, warehouses, POs, BOMs, incidents, shipping quotes. Do not reuse stale data from previous calls.
4. Compute derived values. Effective inventory is always `on_hand - reserved - quarantined`. Percentages and costs always round to the precision stated in the template.
5. Apply decision logic by mapping the live data to the enums in the template. Decision rules come from the memo or the template itself, not from any hardcoded policy outside the task.
6. Sort every list and every sub-list exactly as the template dictates (usually ascending by ID or SKU).
Back to top