aesthetic-instrument
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks,…
Domain knowledge for the logistics & supply-chain vertical (SMB shipping & inventory) so architect and pm don't spec naively. Covers the vocabulary (TMS vs WMS, multi-carrier rate shopping, dimensional weight, BOL/ASN, lot/batch, reorder point), the non-obvious rules incumbents
$ npx -y skills add avelikiy/great_cto --skill vertical-logistics --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vertical-logisticsContext preview
The summary Claude sees to decide when to auto-load this skill.
Domain knowledge for the logistics & supply-chain vertical (SMB shipping & inventory) so architect and pm don't spec naively. Covers the vocabulary (TMS vs WMS, multi-carrier rate shopping, dimensional weight, BOL/ASN, lot/batch, reorder point), the non-obvious rules incumbents
name: vertical-logistics
description: Domain knowledge for the logistics & supply-chain vertical (SMB shipping & inventory) so architect and pm don't spec naively. Covers the vocabulary (TMS vs WMS, multi-carrier rate shopping, dimensional weight, BOL/ASN, lot/batch, reorder point), the non-obvious rules incumbents get right, what a naive build gets wrong, and the entities each of the four products (shipment-tracking, warehouse-lite, route-optimization, po-mgmt) must model. Applied by architect when writing ARCH-{slug}.md and by pm when writing PLAN-{slug}.md for any logistics product.
when_to_use: |
Apply when:
- architect writes ARCH-{slug}.md for shipment-tracking, warehouse-lite, route-optimization, or po-mgmt
- pm writes PLAN-{slug}.md and needs to scope logistics work without underestimating carrier/inventory complexity
- any spec touches shipments, carriers, tracking, warehouses, inventory, purchase orders, or routes
Do NOT apply to non-logistics products (use the matching vertical skill instead).
effort: low
allowed-tools: Read, Write, Grep, Glob
paths:
- "docs/architecture/**"
- "docs/plans/**"
- "docs/design/**"SMB shipping & inventory has a deep vocabulary and a pile of rules that look optional until a real customer's data hits them. The incumbents (ShipHero, CartonCloud, Descartes ShipRush, GoFreight, AfterShip, FreightPOP) encode decades of this. A naive spec models a "shipment" as a tracking number and a "warehouse" as a quantity column — and ships a toy. This skill is the domain framing so architect/pm don't.
The four products and their incumbents:
| Product | Archetype | Wedge | Closest incumbent | |---|---|---|---| | shipment-tracking | dashboard | branded customer-facing tracking | AfterShip (lite) | | warehouse-lite | crud | small-warehouse WMS | ShipHero / CartonCloud | | route-optimization | booking | multi-stop route optimization | Descartes / FreightPOP | | po-mgmt | crud | purchase-order lifecycle | GoFreight / FreightPOP |
carriers, rates, routes, tracking) vs Warehouse Management System (goods at rest inside a building: SKUs, locations, pick/pack/ship). Don't conflate them; route-optimization + shipment-tracking are TMS-flavoured, warehouse-lite is WMS, po-mgmt straddles.
Each has its own API, label format, status codes, and webhook shape.
SLA. Drives carrier choice; depends on dimensional weight.
A big light box bills as if heavy. Ignoring DIM under-quotes every rate.
receiving so the warehouse knows what's arriving before it lands.
production run (expiry, recall, FIFO). Same SKU, different lots, are not interchangeable.
on-hand honest without shutting the warehouse.
lead-time) + safety stock. Drives PO creation timing.
PO, put away into locations.
warehouse.
against.
and status vocabulary differs ("In Transit" vs "MV" vs "departed facility"). You must map each carrier's raw events onto ONE normalized status enum (e.g. `pending → info_received → in_transit → out_for_delivery → delivered / exception`). The normalized timeline is the product; the raw event is provenance.
see a branded tracking page instead of the carrier's. Cheap to switch to, sticky once adopted — it's the AfterShip-lite entry point. (See shipment-tracking below.)
distance". Capacity, time windows, vehicle count, and service times make it NP-hard. **Defer the algorithm to [[geo-routing-engineer]]** — this skill only frames the domain and the entity shape; do not let the spec hand-roll the solver.
produces wrong prices. Capture L×W×H on every parcel.
expiry (FIFO/FEFO), and audit honesty all require lot granularity and periodic counts.
"done"; it accrues
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
Repo: avelikiy/great_cto
great_cto's own committed aesthetic — the instrument panel. Dark five-step surface ladder, exactly one accent, two faces divided by MEANING (Geist speaks,…
Catalogue of known SDLC anti-patterns that great_cto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect…
Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes.…
Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow. Defines the output artifact (TM-{slug}.md),…
Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models…
Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact release.