xlsx

Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for Word documents, HTML reports, standalone Python scripts, database pipelines, or Google Sheets API work.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

The body is highly actionable with a clear, validated workflow and executable code, but loses points on conciseness (recalc explained three times) and progressive disclosure (large standards blocks kept inline rather than offloaded to reference files). Trimming duplication and splitting the financial-model conventions into a referenced file would lift both dimensions.

Suggestions

Consolidate the recalculation guidance into a single section: the 'Recalculating formulas' section already covers usage and JSON output, so remove the duplicated recalc prose from Common Workflow step 5 and Best Practices and link to it instead.

Move the financial-model color-coding and number-formatting standards into a separate referenced file (e.g. references/financial-models.md) and keep only a one-line pointer inline, reducing the body length and improving progressive disclosure.

Trim opinionated filler such as 'pandas which provides powerful data manipulation capabilities' to keep the prose lean and assume Claude's competence.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but redundant — formula recalculation is explained in three places (Common Workflow step 5, the 'Recalculating formulas' section, and Best Practices) and LibreOffice prerequisites repeat the adjacent table, matching the 'could be tightened' score-2 anchor rather than the lean score-3 case.	2 / 3
Actionability	Provides fully executable code (pandas read/write, openpyxl create/edit with real imports, formula examples) plus copy-paste-ready commands like 'python skills/xlsx/scripts/recalc.py output.xlsx 30' and a concrete JSON output spec, matching the score-3 anchor.	3 / 3
Workflow Clarity	The Common Workflow is a 6-step sequence with an explicit mandatory recalc step and a validate→fix→recalc feedback loop, reinforced by a Formula Verification Checklist with checkboxes — matching the score-3 anchor with checkpoints and error recovery.	3 / 3
Progressive Disclosure	References real bundle files (scripts/recalc.py, scripts/office/soffice.py) one level deep, but bulky detail — the financial-model color/number standards and the full recalc JSON schema — is kept inline in a single ~318-line file rather than split into signaled reference files, matching the score-2 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is strong across all dimensions: concrete capabilities, natural trigger terms, explicit when-guidance, and a clear exclusion list that sharply bounds the skill. No substantive weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create, edit, analyze, or convert Excel spreadsheets' plus formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup — matching the score-3 anchor rather than the partial-action score-2 anchor.	3 / 3
Completeness	Explicitly answers both what ('Create, edit, analyze, or convert...') and when ('Use for formulas, formatting, financial models...'), with a dedicated 'Use for' trigger clause that clears the score-2 cap on missing triggers.	3 / 3
Trigger Term Quality	Covers natural terms users say — 'Excel spreadsheets (.xlsx, .xlsm)', '.csv/.tsv', 'financial models', 'formulas' — with good variation, matching the strong-coverage anchor; not the score-2 case which only mentions 'PDF files'.	3 / 3
Distinctiveness Conflict Risk	A clear spreadsheet niche plus an explicit exclusion list ('Do NOT use for Word documents, HTML reports, standalone Python scripts, database pipelines, or Google Sheets API work') makes conflict with adjacent skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/xlsx/SKILL.md
Commit: 757b63b

Reviewed: about 12 hours 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.