Supplier selection
Rank a field of vendors on a weighted basis instead of on the strongest presentation.
— Procurement & Vendors
Scores vendor responses on quality, cost and risk, computes weighted totals, ranks the field and writes a recommendation with trade-offs stated.
3–4 days → ~15 minutes
For a full population, not a sample
No coding required
— USE CASES
Rank a field of vendors on a weighted basis instead of on the strongest presentation.
Re-score an existing supplier panel on the same criteria to see who still earns a place.
Show the weighting and the trade-off behind the recommended vendor.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Each row of your export is processed on the same basis, so no supplier is skipped however long the table is.
Findings on the supplier panel are written up as a document that reads like professional output, with each claim tied back to a supplier.
Derived columns are added row by row, keeping your source data and the judgement about each supplier side by side.
Vendor selection usually comes down to whoever presented best. Supplier selection is the typical trigger — rank a field of vendors on a weighted basis instead of on the strongest presentation. Done properly it is defensible; done at pace it becomes a judgement call nobody can retrace. And "properly" usually means 3–4 days of manual work.
Skillsize turns that work into a Skill: you supply the material, and what comes back is scored and ranked vendors with weighted totals, with a written recommendation with trade-offs stated. What sits between input and output is the codified method: thresholds, sequencing and the points where a human confirms a call — all of it visible and editable in the Skill. In effect, 3–4 days of senior time compresses into ~15 minutes — and the output is comparable across clients, quarters and colleagues instead of shaped by whoever ran it.
Vendor scorecard & rank exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
Evaluates a prospective supplier against your own vendor policy and returns a governed onboarding decision — approve, approve with conditions, refer for deeper due diligence or reject — with the risk reasoning shown and a procurement lead sign-off required before a purchase order can be raised.
Rolls an invoice or contract export up by spend category, charts it, and quantifies savings opportunities with the suggested lever per category.
Runs a vendor due-diligence questionnaire, scores it deterministically into risk bands, and writes the contractual conditions to attach before onboarding.
Scores every supplier line for the risk of failing to deliver, based on how comparable deliveries have actually performed, and sets out where dual-sourcing or contract action is warranted.
Extracts and scores every bid against every evaluation criterion with a reason per cell, rendered as a heatmap showing the decisive differences.
Extracts every RFP requirement, answers each strictly from your documented capability, and compiles a compliance matrix with drafted responses and evidence.