CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

94

1.66x
Quality

91%

Does it follow best practices?

Impact

98%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

96%

31%

Supplier Selection for SKU-0422

Python-scored supplier ranking with output JSON

Criteria
Without context
With context

Python script produced

100%

100%

Code reads catalog CSV

90%

80%

Code reads suppliers CSV

90%

80%

Filters by SKU

100%

100%

Min-max normalization

100%

100%

Correct score weights

0%

100%

SUP-12 reliability adjusted

0%

100%

result.json format

100%

100%

No prose comparison

100%

100%

Tie-break rule documented

0%

100%

Rationale mentions overrides

57%

100%

100%

44%

Supplier Selection for Reno Warehouse Replenishment

Warehouse-adjusted supplier ranking (WH-WEST) with volume pricing override

Criteria
Without context
With context

Python script produced

100%

100%

WH-WEST lead time adjustment

33%

100%

SUP-05 not double-adjusted

10%

100%

SUP-04 price break mentioned

20%

100%

SUP-07 caveat applied

37%

100%

Correct score weights

0%

100%

Min-max normalization in code

100%

100%

result.json format

100%

100%

Override changes pick noted

100%

100%

Correct data file paths

87%

100%

No per-supplier prose comparison

85%

100%

98%

42%

Urgent Supplier Selection for SKU-0731

Expedite override with MOQ filtering and import-risk flagging

Criteria
Without context
With context

Python script produced

100%

100%

Expedite logic used

40%

100%

SUP-09 MOQ eliminated

75%

100%

SUP-07 urgency warning

16%

100%

MOQ filter in code

100%

100%

Correct data file paths

0%

100%

result.json format

100%

100%

SUP-01 notice requirement noted

0%

100%

Score vs expedite distinction

60%

100%

No per-supplier prose comparison

80%

80%

Repository
anthropics/cwc-workshops
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.