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

91%

Does it follow best practices?

Impact

98%

1.40x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

92%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.

A concise, highly actionable skill body with a clear gated workflow and explicit validation/escalation checkpoints. The only gap is progressive disclosure: referenced script files are not part of the bundle to verify.

Suggestions

Ship the referenced scripts under a scripts/ bundle (rolling_mean.py, batch_days_of_cover.py) so the paths in the body resolve to real files.

Consider moving the seasonal-calendar table or promotional-handling detail into a reference file if the body grows, keeping SKILL.md as a tight overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding about what a forecast is or how rolling means work — and every section earns its place with tight, actionable prose.	3 / 3
Actionability	It provides fully executable commands (rolling_mean.py and the batch script invocations), an explicit JSON contract, concrete numeric thresholds, and a worked example, all copy-paste ready.	3 / 3
Workflow Clarity	The two-path structure is gated by explicit all-of/any-of conditions, with validation checkpoints (strict JSON parsing, confidence < 0.6 escalation) and a documented fallback when callable_agents is unavailable.	3 / 3
Progressive Disclosure	Sections are well organized, but no references/scripts/assets bundle directories exist, and the two referenced scripts (rolling_mean.py, batch_days_of_cover.py) are not present in the bundle to verify, leaving references unconfirmed rather than cleanly one-level-deep.	2 / 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, specific description with explicit trigger guidance and a clear niche. The only deduction is the second-person voice ("yourself"), which the rubric penalizes on the specificity dimension.

Suggestions

Rephrase in third person to avoid the voice penalty, e.g. 'Produces a demand forecast for a SKU and determines when to delegate to a subagent vs. computing it inline.'

Dimension	Reasoning	Score
Specificity	The description names concrete actions ("produce a demand forecast for a SKU" and the delegate-vs-compute decision), matching the multi-action anchor, but the second-person phrasing ("compute it yourself") triggers the voice penalty reducing specificity by one level.	2 / 3
Completeness	It explicitly answers both what (produce a forecast, delegate vs. compute) and when via the explicit "Load this for any task involving..." clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	It surfaces natural phrasings a user would actually say — "forecast", "how much will we sell", "next month", promos, seasonal SKUs — giving good coverage of real trigger language.	3 / 3
Distinctiveness Conflict Risk	The niche is specific (per-SKU demand forecasting with a subagent-delegation heuristic) and the triggers are distinct, making overlap with unrelated skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/cwc-workshops
Path: agent-decomposition/.claude/skills/forecasting/SKILL.md
Commit: 059482d

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.