CtrlK
BlogDocsLog inGet started
Tessl Logo

weekly-report

Structure and data sources for the weekly inventory report. Load this when the task is "weekly report", "Monday report", or "summarize inventory status".

85

1.03x
Quality

81%

Does it follow best practices?

Impact

87%

1.03x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 token-efficient, well-organized skill body with precise data sources, formulas, and thresholds. The main gaps are the absence of an executable code example for a skill whose central instruction is to write a Python script, and a missing validation/verification checkpoint for a large batch operation.

Suggestions

Add a minimal executable Python snippet showing the load-once / compute / emit-markdown pattern so the central instruction is copy-paste ready, not just specified.

Insert an explicit validation checkpoint (e.g., verify expected row counts from stock_levels.csv or sanity-check that days_cover values are non-negative) before emitting the final markdown.

Number the core workflow steps (load CSVs -> join -> compute cover/stockouts/low-stock/POs/forecast -> emit markdown) so the sequence is explicit rather than implied across sections.

DimensionReasoningScore

Conciseness

Lean and efficient: no explanation of CSVs/libraries/basic concepts, every section (structure template, cadence table, data sources, code note) earns its place and assumes Claude's competence.

3 / 3

Actionability

Concrete specs are strong (exact paths like /mnt/user/data/stock_levels.csv, formulas like on_hand / avg_daily_sales, thresholds like "top 15 by urgency"), but the core instruction to "write one Python script" lacks any executable code example, so it is not copy-paste ready.

2 / 3

Workflow Clarity

The high-level sequence (load once, compute, emit markdown) and the cadence/aging-PO guidance are present, but this batch operation over ~67k rows has no explicit validation or verification checkpoint, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

A short single-purpose skill with no bundle files and well-organized sections (Structure, Operating cadence, Aging-PO check, Data sources, Do this in code) qualifies for a 3 under the simple-skills note.

3 / 3

Total

10

/

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 concise, third-person description that clearly pairs what the skill provides with explicit natural-language triggers, scoring well on completeness, trigger quality, and distinctiveness. Its only weakness is specificity: it names the domain and deliverable rather than enumerating concrete actions.

DimensionReasoningScore

Specificity

Names the domain and deliverable ("Structure and data sources for the weekly inventory report") but describes contents rather than listing multiple concrete actions like extract/merge/fill; concrete actions (read CSVs, compute cover, emit markdown) live in the body, not the description.

2 / 3

Completeness

Explicitly answers both what ("Structure and data sources for the weekly inventory report") and when (the explicit "Load this when the task is..." trigger clause), matching the anchor for full completeness.

3 / 3

Trigger Term Quality

"Load this when the task is 'weekly report', 'Monday report', or 'summarize inventory status'" supplies several natural phrases a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The weekly-inventory-report niche with weekly-specific triggers ("weekly report", "Monday report") is clearly scoped and unlikely to fire for unrelated 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.