Skip to content
cccskills
FreePublished on GitHub

supplier-selection

How to rank and pick a supplier for a SKU. Load this whenever a task involves choosing a supplier, comparing quotes, or creating a purchase order.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

<!-- Copyright 2026 Anthropic PBC --> <!-- SPDX-License-Identifier: Apache-2.0 -->

Supplier Selection

Ranking suppliers is arithmetic, not judgment. Compute it in Python via code execution — do not reason about it in prose.

Method

For a given SKU:

  1. Read /mnt/user/data/supplier_catalog.csv and filter to rows matching the SKU. This gives you (supplier_id, unit_price, min_order_qty) for each candidate.
  2. Join with /mnt/user/data/suppliers.csv on supplier_id to get lead_time_days and reliability.
  3. Normalize price and lead time across the candidates (min-max to [0,1], where 0 is best). Reliability is already on [0,1] where higher is better.
  4. Score each candidate:
    score = 0.5 × (1 − norm_price) + 0.3 × (1 − norm_lead_time) + 0.2 × reliability
    
  5. Pick the highest score. Tie-breaks: lowest unit_price, then lowest lead_time_days, then alphabetical supplier_id.

Do this in code

Write and run a short Python script — don't call a tool per supplier, and don't compare quotes by describing them. Example shape:

import csv
sku = "SKU-0057"
catalog = [r for r in csv.DictReader(open("/mnt/user/data/supplier_catalog.csv")) if r["sku"] == sku]
suppliers = {r["supplier_id"]: r for r in csv.DictReader(open("/mnt/user/data/suppliers.csv"))}
# join, normalize, score, sort — print the winner as JSON

Supplier-specific overrides

These quirks are not in the catalog data. Apply them after computing the score; if one changes your pick, say so in the rationale.

SupplierOverride
SUP-01 Cascade DistributionOrders >500 units need 48h notice or they auto-split into two shipments — add to lead-time math for large POs.
SUP-02 Alpine WholesaleClosed Dec 20 – Jan 3. POs in that window aren't acknowledged until Jan 4. Land holiday replenishment before Dec 15.
SUP-03 Backcountry Supply CoTwo short-ships on Tents & Shelter this year. Prefer an alternate for that category if lead is comparable.
SUP-04 Sierra OutfittersUnlisted 3% price break at 250+ units. If recommended qty is 200–249, often worth rounding up.
SUP-05 Granite Gear PartnersWest-coast DC only. Add 2–3 days to catalog lead time for WH-EAST deliveries.
SUP-07 Ridgecrest ImportsImport-only; lead times are port-congestion sensitive. Don't rely on stated lead for an urgent order.
SUP-09 Summit SourceMOQ is enforced strictly — they reject (not round up) below-MOQ POs.
SUP-12 Trailhead MercantileNew on roster. Treat reliability as one notch lower than stated until 6 months of history.

Warehouse lead-time adjustments

  • WH-WEST (Reno): most suppliers ship from east-coast DCs — add +2 days to catalog lead time as a rule of thumb unless a supplier note says otherwise.
  • WH-EAST (Carlisle): two-shift receiving dock; best destination for an expedited PO that needs same-day inbound scheduling.
  • WH-CENTRAL (Kansas City): overflow / transfer hub. If you're sourcing an inter-warehouse transfer rather than a PO, WH-CENTRAL is almost always the origin.

Expedite override

If the reorder-policy skill flagged expedite, ignore the score and pick the supplier with the lowest lead_time_days whose min_order_qty ≤ your target order qty.

Output

Return {"supplier_id": "SUP-03", "unit_price": 21.40, "lead_time_days": 7, "score": 0.81} and use that supplier_id in the PO.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K/10-Q data, or company financials.

The English summary is being prepared. Showing the original description.

anthropics/cwc-workshops2.2KUpdated Oct 17, 2026

How to produce a demand forecast for a SKU, and when to delegate that to a subagent vs. compute it yourself. Load this for any task involving "forecast", "how much will we sell", "next month", promos, or seasonal SKUs.

The English summary is being prepared. Showing the original description.

anthropics/cwc-workshops2.2KUpdated Oct 17, 2026

The SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked "what caused X" about a production service.

The English summary is being prepared. Showing the original description.

anthropics/cwc-workshops2.2KUpdated Oct 17, 2026

mining

Free

Where diamonds spawn in Minecraft 1.20.

The English summary is being prepared. Showing the original description.

anthropics/cwc-workshops2.2KUpdated Oct 17, 2026

Fixed-format templates for Slack alerts, supplier emails, and escalations. Load this whenever the task is "notify", "alert", "email", or "tell ops".

The English summary is being prepared. Showing the original description.

anthropics/cwc-workshops2.2KUpdated Oct 17, 2026

How the SRE team writes a postmortem PDF. Use this whenever asked for a postmortem, an incident report, a write-up to share, or a PDF of what happened.

The English summary is being prepared. Showing the original description.

anthropics/cwc-workshops2.2KUpdated Oct 17, 2026

See all skills by anthropics

Report a problem with this skill