domain-logistics
Skill1 starsChanged 7 days agoMITView on GitHub
Logistics and fulfillment domain knowledge for Business Analysts - glossary, core processes (order intake, first-mile pickup, hub sorting, last-mile delivery, failed delivery and return-to-sender, COD collection and remittance, returns, warehouse inbound/putaway/pick/pack/outbound, inventory control, carrier management and rate cards, tracking, claims), business rules (volumetric and chargeable weight, zone pricing, delivery attempts, COD limits, status model, inventory reservation, SLA), data model with status sets, integrations (OMS/e-commerce, carriers, maps/geocoding, scanners, payment/bank for COD), regulatory touchpoints and a BA question checklist. Use together with any BA task whenever the context is parcel delivery, courier, 3PL, warehouse (WMS), transportation (TMS), last mile, COD or fulfillment - or the user mentions "vận chuyển", "giao hàng", "kho", "WMS", "TMS", "vận đơn", "COD", "đối soát COD", "giao thất bại", "hoàn hàng", "chặng cuối", "đơn vị vận chuyển".
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-specSkill
- ba-diagramsSkill
- bpmn-modelingSkill
- decision-tableSkill
- domain-bankingSkill
- domain-ecommerceSkill
- domain-lendingSkill
- domain-paymentsSkill
- edge-case-finderSkill
- functional-decompositionSkill
- meeting-to-requirementsSkill
- requirements-linterSkill
- screen-specSkill
- user-story-writerSkill
The file
Files
Domain Pack: Logistics & Fulfillment / Vận chuyển và kho vận
This skill adds domain knowledge on top of the BA method skills (meeting-to-requirements, requirements-linter, functional-decomposition, user-story-writer, decision-table, edge-case-finder, api-spec, screen-spec, bpmn-modeling, ba-diagrams). It makes their output logistics-correct. For the selling side (checkout, orders, returns policy) also load domain-ecommerce; for cash collected on delivery and settlement also see domain-payments.
How to use the references
| Task | Read |
| Terminology | references/glossary.md |
| Decompose functions, draw processes | references/processes.md |
| Requirements, stories, AC, decision tables (pricing, routing) | references/business-rules.md + references/checklist.md |
| ERD, API payloads, status sets | references/data-model.md |
| Context/sequence diagrams, integration specs | references/integrations.md |
| Compliance | references/regulations.md |
| Goals, reports | references/kpis.md |
How to apply domain knowledge
- Identify the role and scope: shipper/seller, carrier (courier), 3PL warehouse, marketplace logistics, or in-house fleet; parcels or pallets; first/middle/last mile; warehouse only. It changes almost every rule.
- Add the scenarios a logistics BA never forgets: failed delivery and retry limits, return-to-sender, COD collected but not remitted, wrong or unnormalised address, parcel lost/damaged claim, weight disputes (actual vs volumetric), partial delivery, split shipment, reroute, scan gaps, inventory mismatch after counting.
- Think in event streams: tracking events and handover scans are the facts; statuses are derived.
- Ask, don't invent: rate cards, divisors, retry counts, COD limits and claim windows are commercial decisions ->
[value - confirm]. - Flag regulatory touchpoints (restricted/dangerous goods, personal data of recipients, COD handling, vehicle and driver rules) with "verify the current regulation with Legal/Compliance".
Guardrails
- Generic typical practice (Vietnam focus); each carrier or warehouse differs. Do not name a carrier as required unless the user did.
references/regulations.mdhas a "last reviewed" date and lists topics to ask about, not legal conclusions.- Mask recipient names, phone numbers and addresses in examples.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.