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.

92

1.66x
Quality

88%

Does it follow best practices?

Impact

98%

1.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is lean, concrete, and well-organized, with an exact scoring formula and explicit tie-breaks. Its main weakness is the absence of an explicit validation/verification checkpoint before committing a supplier pick to a purchase order.

Suggestions

Add an explicit verification step after scoring: confirm the winning supplier's min_order_qty <= target order qty and that any applicable supplier/warehouse overrides were applied, before returning the supplier_id for the PO.

Make the Python example fully executable (fill in the join/normalize/sort and a print of the winner) so it is copy-paste ready, or explicitly label it as a skeleton while keeping the formula as the source of truth.

Note how overrides interact with the expedite path (e.g., whether SUP-09's strict MOQ still applies when expedite ignores the score) to remove ambiguity in edge cases.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it gives the exact scoring formula, compact code shape, and tight override/warehouse notes without explaining what a SKU, supplier, or PO is. Every section earns its place.

3 / 3

Actionability

It provides the exact score formula, concrete file paths, explicit tie-breaks, and a concrete JSON output shape; the abbreviated 'example shape' code block is the only non-copy-paste element, but the full logic is specified unambiguously in the Method steps.

3 / 3

Workflow Clarity

The five-step sequence and tie-breaks are clear, but there is no explicit validation checkpoint (e.g., confirm the winner's MOQ <= order qty, confirm overrides applied) before emitting the supplier for the PO, leaving validation implicit.

2 / 3

Progressive Disclosure

A self-contained single-purpose skill with no bundle files and no external references; its clearly headed sections are well-organized, which scores 3 for a simple skill with no need for progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

90%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states what the skill does and when to load it, with natural trigger terms and a distinct niche. Its only gap is naming a single composite action rather than enumerating several concrete capabilities.

Suggestions

List a couple more discrete actions (e.g., 'rank suppliers, score quotes, generate a recommended supplier') to lift specificity from a single composite action to multiple concrete ones.

DimensionReasoningScore

Specificity

It names a concrete action ('rank and pick a supplier for a SKU') tied to a specific domain object, but lists only a single composite action rather than multiple distinct concrete actions like the score-3 example.

2 / 3

Completeness

It answers both what ('rank and pick a supplier for a SKU') and when with an explicit trigger clause ('Load this whenever a task involves choosing a supplier, comparing quotes, or creating a purchase order').

3 / 3

Trigger Term Quality

'choosing a supplier, comparing quotes, or creating a purchase order' are natural phrases a user would actually say, giving good coverage rather than a single keyword or jargon.

3 / 3

Distinctiveness Conflict Risk

The supplier/SKU/quote/purchase-order niche has distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/cwc-workshops
Reviewed

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.