CtrlK
BlogDocsLog inGet started
Tessl Logo

reorder-policy

How to decide whether and how much to reorder a SKU. Load this whenever a task involves reorder recommendations, purchase orders, or "should we restock" questions.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary instruction skill: token-efficient, fully actionable, with a sequenced decision workflow that includes a confidence-guard checkpoint and escalation path, all in one well-organized file.

DimensionReasoningScore

Conciseness

Lean throughout: it jumps straight into inputs, formulas, and thresholds without explaining CSVs, inventory concepts, or libraries Claude already knows, so every token earns its place.

3 / 3

Actionability

Concrete formulas ('safety_stock = 1.5 × avg_daily_sales × lead_time_days'), exact file paths, numeric thresholds, and copy-paste JSON output shapes make the guidance fully executable.

3 / 3

Workflow Clarity

Decision rules are numbered 1–4 with an explicit confidence guard ('if confidence < 0.6, do not place a PO automatically') acting as a validation checkpoint and escalation feedback loop before any side effect.

3 / 3

Progressive Disclosure

A single self-contained file organized into clearly headed sections (Inputs, Decision rules, Worked example, Prioritization, Transfer vs reorder, Compliance, Output) with no nested references or wall-of-text problem.

3 / 3

Total

12

/

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, third-person description with explicit what/when structure and natural trigger terms; its only soft spot is specificity, which frames the task as a binary decision rather than listing several concrete actions.

Suggestions

Expand the 'what' clause to name concrete actions (e.g. '...compute order quantity, flag low-confidence forecasts for review, and write purchase orders') to lift specificity to a 3.

DimensionReasoningScore

Specificity

Names the domain ('reorder a SKU') and two decisions ('whether and how much') but does not enumerate multiple concrete actions, so it stops short of the multi-action anchor.

2 / 3

Completeness

'How to decide whether and how much to reorder a SKU' states what, and 'Load this whenever a task involves...' gives an explicit when-trigger, satisfying both halves.

3 / 3

Trigger Term Quality

'reorder recommendations, purchase orders, or "should we restock" questions' gives natural phrasings a user would actually say, including a quoted vernacular trigger.

3 / 3

Distinctiveness Conflict Risk

The reorder/purchase-order niche with 'should we restock' triggers is distinct and unlikely to fire for unrelated skills (it even defers to separate supplier/forecasting skills).

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.