CtrlK
BlogDocsLog inGet started
Tessl Logo

xlsx

Excel spreadsheet processing and analysis. Formats: .xlsx, .xlsm, .csv, .tsv. Capabilities: create spreadsheets, formulas (error-free), formatting, data analysis, charts, pivot tables, conditional formatting, data validation, template preservation. Actions: create, edit, analyze, visualize, recalculate spreadsheets. Keywords: Excel, spreadsheet, xlsx, csv, formula, VLOOKUP, SUMIF, pivot table, chart, graph, data analysis, formatting, conditional formatting, data validation, workbook, worksheet, cell reference, named range, macro. Use when: creating spreadsheets, editing Excel files, analyzing tabular data, building formulas, creating charts/graphs, working with CSV/TSV, preserving spreadsheet templates.

71

Quality

86%

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

The canonical home for this skill is xlsx in anthropics/skills

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

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

The body excels at actionability and provides an exemplary validate-fix-recalculate workflow with concrete code and error-recovery loops. Its weaknesses are redundancy (error codes and prevention rules repeated across three sections) and a monolithic structure that inlines financial-modeling standards and references a recalc.py script that is not actually present in the bundle.

Suggestions

Consolidate the thrice-repeated formula error codes and the duplicated error-prevention guidance ('Formula Error Prevention' vs 'Formula Verification Checklist' vs 'Common Pitfalls') into one section to cut token cost.

Move the financial-model standards (color coding, number formatting, source documentation) into a references/ file (e.g., financial-modeling.md) linked from SKILL.md, and ship recalc.py under scripts/ so the referenced path resolves.

Delete meta-filler lines like 'A user may ask you to create, edit, or analyze the contents of an .xlsx file' — the description and section headers already establish this.

DimensionReasoningScore

Conciseness

The body is mostly imperative and code-heavy, but contains notable duplication and padding: the four formula error codes (#REF!, #DIV/0!, #VALUE!, #NAME?) are listed three separate times ('Zero Formula Errors', 'Common Workflow' step 6, and 'Common Pitfalls'), error-prevention guidance appears in both 'Formula Error Prevention' and 'Formula Verification Checklist', and filler like 'A user may ask you to create, edit, or analyze the contents of an .xlsx file. You have different tools and workflows available' teaches nothing new. It fits the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor.

3 / 5

Actionability

Guidance is fully executable throughout: runnable openpyxl/pandas snippets, the exact command 'python recalc.py output.xlsx 30', the JSON output schema for interpreting results with example keys, exact RGB values for color coding, and concrete number-format strings like '$#,##0;($#,##0);-'. This matches the copy-paste-ready anchor with common cases covered.

5 / 5

Workflow Clarity

The 'Common Workflow' is a clear numbered sequence (choose tool → create/load → modify → save → recalculate → verify) with an explicit validation checkpoint ('MANDATORY IF USING FORMULAS') and a feedback loop: 'Fix the identified errors and recalculate again', plus error-type-to-fix mapping and a verification checklist. This matches the top anchor's validate-fix-retry structure.

5 / 5

Progressive Disclosure

The body repeatedly references a provided 'recalc.py' script, but no scripts/ directory (or any bundle files) exist, so navigation to it is unresolved; and ~60 lines of financial-modeling standards (color coding, number formats, source documentation) are inlined monolithically in a single ~290-line file with no one-level-deep references. This fits 'some structure but could be better organized; references present but not clearly signaled; content that should be separate is inline' rather than the good-structure anchor at 4.

3 / 5

Total

16

/

20

Passed

Description

96%Weight 40%Scale 1-5

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 that comprehensively states capabilities, formats, keywords, and explicit 'Use when' triggers, closely matching the rubric's good examples. The only weakness is a keyword list whose generic entries (chart, graph, data analysis, formatting) create minor conflict risk with visualization and data-analysis skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'create spreadsheets, formulas (error-free), formatting, data analysis, charts, pivot tables, conditional formatting, data validation, template preservation' — covering creation, editing, analysis, and visualization comprehensively. It clearly matches the comprehensive-coverage anchor; there are no vague or generic action statements that would pull it toward a 4.

5 / 5

Completeness

It explicitly answers 'what' ('Excel spreadsheet processing and analysis' plus enumerated capabilities and actions) and 'when' with a concrete 'Use when:' clause listing seven concrete triggers ('creating spreadsheets, editing Excel files, analyzing tabular data, building formulas...'). Both elements are explicit with concrete trigger phrases, matching the anchor for 5.

5 / 5

Trigger Term Quality

Keywords include natural terms and synonyms users would say — 'Excel, spreadsheet, xlsx, csv, formula, VLOOKUP, SUMIF, pivot table, chart, graph' — plus file extensions '.xlsx, .xlsm, .csv, .tsv'. Coverage of natural terms including synonyms and extensions clearly matches the top anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is clear (Excel/spreadsheet files) with distinct format-specific triggers, but the keyword list includes broadly overlapping terms like 'chart, graph, data analysis, formatting, macro' that could trigger this skill for non-spreadsheet chart or general data-analysis requests. This is best described as 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict anchor at 5.

4 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
samhvw8/dot-claude
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.