forecasting

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.

1.40x

Quality

83%

Does it follow best practices?

Impact

98%

1.40x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

40%

Restocking Decision for SKU-0057

Path A routing and rolling mean script

Criteria

Without context

With context

Uses rolling_mean script

100%

Correct SKU argument

100%

Correct horizon argument

100%

No subagent spawned

100%

Forecast result fields present

100%

Confidence not dropped

100%

Flags not dropped

100%

No manual rolling mean

100%

35%

Daily Low-Stock Sweep

Batch days-of-cover sweep script usage

Criteria

Without context

With context

Uses batch script

100%

Correct top-N argument

100%

No per-SKU tool loop

100%

JSON output preserved

33%

100%

Ranked by urgency

100%

Command recorded

100%

95%

Reorder Planning for an Upcoming Promotional Campaign

Promo forecast Path B and escalation handling

Criteria

Without context

With context

Path B selected

80%

70%

Minimal subagent context

80%

forecast_qty field present

100%

confidence field present

100%

flags field present

100%

Uplift anchored in number

100%

Low-confidence escalation

86%

100%

Post-promo dip noted

100%

Confidence not dropped

100%

Flags not dropped

100%

Repository: anthropics/cwc-workshops
Commit: 970b040

Evaluated: 22 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Restocking Decision for SKU-0057 Daily Low-Stock Sweep Reorder Planning for an Upcoming Promotional Campaign

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.