xlsx

Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) 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

94%

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

88%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 content is high quality: executable commands and code, a robust recalculate workflow with explicit validation and feedback loops, and well-organized sections pointing to real bundle scripts. It loses a point only on conciseness (a few long caveat passages) and progressive disclosure (script paths in prose rather than a dedicated reference document).

Suggestions

Move the lengthy external-reference-link mechanics ('A workbook that links to another file...') into a short reference doc or a clearly delimited appendix so the main flow stays leaner.

Add a small 'Reference scripts' section near the top listing scripts/recalc.py and scripts/office/soffice.py as explicit links, making the bundle navigation pattern clearer.

Trim the LibreOffice function-coverage caveat list slightly; the _xlfn prefix rule and the banned-function list could be one combined table.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding about what Excel or openpyxl is, and commands/snippets are dense and useful ('sheet[\'B10\'] = \'=SUM(B2:B9)\''). It is not 5 because a few explanatory passages (external-reference link mechanics, LibreOffice function-coverage caveats) run long, though each earns its place; not 3 because there is no unnecessary concept explanation.	4 / 5
Actionability	Fully executable guidance throughout — 'python scripts/recalc.py output.xlsx [timeout_seconds]', exact formula syntax, prefix rules ('_xlfn.TEXTJOIN'), and concrete gotchas with precise fixes — copy-paste ready and covering common cases, matching the top anchor; not below because no key detail is missing.	5 / 5
Workflow Clarity	Clear sequence with explicit validation steps and feedback loops: recalc reports errors, 'Fix what it names and run it again', the 'write 2–3 formulas first and check they pull the values you expect' checkpoint, and the green-recalc-proves-evaluation-not-correctness caution, matching the validate→fix→retry anchor; destructive/batch validation is present so no cap applies.	5 / 5
Progressive Disclosure	Good structure with well-organized sections and references to real bundle files (scripts/recalc.py, scripts/office/soffice.py, both verified present), keeping detail one level deep. It is not 5 because references are script paths embedded in prose rather than a clear overview→reference-document navigation pattern, and there is no separate reference doc; not 3 because structure is strong and referenced paths are real and discoverable.	4 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is exemplary: it states concrete actions, names file extensions and synonyms as triggers, explicitly answers both what and when, and adds a strong negative-boundary clause to avoid mis-triggering. It matches the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx)' — alongside concrete use cases (formulas, formatting, financial models, multi-sheet workbooks), matching the comprehensive-coverage anchor; not below because coverage is broad and action-oriented rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both what ('Create, edit, analyze, or convert Excel spreadsheets... where the workbook file is the primary deliverable') and when ('Use for formulas, formatting, financial models... Also applies to .csv/.tsv when the user wants spreadsheet output') with concrete trigger phrases, matching the top anchor; not 4 because both halves are explicit and concrete.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural terms including synonyms and file extensions — 'Excel spreadsheets', 'formulas', 'formatting', 'financial models', '.xlsx', '.xlsm', '.xltx', '.csv/.tsv' — matching the anchor that lists synonyms and extensions; no common terms missing.	5 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers and an explicit negative boundary — 'Do NOT use for Word documents, HTML reports, standalone Python scripts, database pipelines, or Google Sheets API work' — minimizing conflict risk, matching the minimal-conflict anchor.	5 / 5
	Total	20 / 20 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: b2a92ba

Reviewed: 3 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.