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

Quality

Content

77%

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

This is a strong, well-structured skill that provides clear decision criteria, executable commands, and a worked example. Its main strengths are the unambiguous two-path decision tree, concrete bash commands, and the explicit confidence-threshold contract with downstream skills. Minor weaknesses include some verbosity in explanatory passages (e.g., why subagents help with context windows) and inline content (seasonal table, promo handling) that could be split into referenced files for better progressive disclosure.

Suggestions

Trim the 'Why a subagent' paragraph — Claude understands context window tradeoffs; a single sentence ('Subagent gets its own context for the ~90-row history') suffices.

Consider moving the seasonal calendar table and promotional handling details into separate referenced files (e.g., SEASONAL.md, PROMO_HANDLING.md) to keep the main skill leaner and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining basic concepts, but some sections are slightly verbose — e.g., the 'Why a subagent' paragraph explains context window management which Claude already understands, and the promotional handling section could be tightened. Overall reasonable but not maximally lean.	2 / 3
Actionability	Provides concrete, executable bash commands for both single-SKU and batch forecasting, specifies exact decision criteria (flags, horizon thresholds), includes a worked example with real JSON output, and gives precise fallback behavior with confidence thresholds. The guidance is copy-paste ready and leaves no ambiguity about what to do.	3 / 3
Workflow Clarity	The two-path decision tree is clearly defined with explicit boolean conditions. Validation is built in via confidence thresholds and the escalation contract (confidence < 0.6 → escalate). The fallback when callable_agents is unavailable includes a specific confidence cap. The worked example demonstrates the full decision chain including the error-recovery path (malformed JSON = error, not guess).	3 / 3
Progressive Disclosure	The skill references external scripts (rolling_mean.py, batch_days_of_cover.py) and another skill (reorder-policy), which is good progressive disclosure. However, no bundle files were provided to verify these references exist, and the content is fairly long (~100 lines) with the seasonal calendar table and promotional handling sections that could potentially be split into referenced files. The structure is reasonable but not optimally layered.	2 / 3
	Total	10 / 12 Passed

Description

89%

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

This is a solid skill description that excels at trigger term coverage and completeness, with explicit 'Load this for...' guidance and natural user phrases. Its main weakness is that the capability description could be more specific about what concrete actions the skill enables beyond the general 'produce a demand forecast' — e.g., does it handle data loading, model selection, accuracy evaluation, visualization?

Suggestions

Add more specific concrete actions to improve specificity, e.g., 'Loads historical sales data, applies seasonal decomposition, incorporates promotional uplift, and generates point and interval forecasts for SKUs.'

Dimension	Reasoning	Score
Specificity	The description names the domain (demand forecasting for SKUs) and mentions some actions (produce a demand forecast, delegate to subagent vs. compute yourself), but doesn't list multiple concrete actions like specific forecasting methods, data processing steps, or output formats.	2 / 3
Completeness	Clearly answers both what ('produce a demand forecast for a SKU, and when to delegate that to a subagent vs. compute it yourself') and when ('Load this for any task involving "forecast", "how much will we sell", "next month", promos, or seasonal SKUs'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'forecast', 'how much will we sell', 'next month', 'promos', 'seasonal SKUs'. These are realistic phrases a user would naturally use when needing demand forecasting.	3 / 3
Distinctiveness Conflict Risk	The description carves out a clear niche around demand forecasting for SKUs with specific trigger terms like 'promos', 'seasonal SKUs', and 'how much will we sell' that are unlikely to conflict with other skills.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/cwc-workshops
Commit: 970b040

Reviewed: 17 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.