xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

1.54x

Quality

88%

Does it follow best practices?

Impact

91%

1.54x

Average score across 8 eval scenarios

Securityby

Passed

No findings from the security scan

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

Quality

Content

77%

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

Highly actionable content with a clear, validated multi-step workflow and executable code throughout. Its weakness is token efficiency and progressive disclosure: recalc material is repeated across sections and reference-grade detail sits inline rather than in separate files.

Suggestions

Consolidate the recalc instructions and error-JSON documentation into a single section (or a references/ file) to remove the triple repetition across Common Workflow, 'Recalculating formulas', and 'Interpreting scripts/recalc.py Output'.

Move the financial-model color/number-formatting rules and the four source-citation examples into a separate references/ file (e.g. references/financial-modeling.md) and link to it from SKILL.md to improve progressive disclosure.

Tighten inline reference-style detail (full JSON output schema) into a short example plus a pointer to the script, keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept padding, but the recalc workflow and its JSON output are restated in three places and reference-style detail (full error JSON schema, four source-citation examples, lengthy financial formatting rules) lives inline and could be tightened or offloaded.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance — pandas read/write snippets, openpyxl create/edit examples, explicit wrong-vs-correct formula pairs ("sheet['B10'] = '=SUM(B2:B9)'") and exact commands ("python scripts/recalc.py output.xlsx").	3 / 3
Workflow Clarity	A numbered Common Workflow (1–6) with a mandatory recalc step and an explicit validate→fix→recalculate feedback loop ("If status is errors_found... Fix the identified errors and recalculate again"), plus a Formula Verification Checklist — explicit checkpoints rather than implicit ones.	3 / 3
Progressive Disclosure	Real bundle scripts are referenced one level deep and exist (scripts/recalc.py, scripts/office/soffice.py), but there is no references/ directory and substantial reference-style content (financial formatting rules, recalc JSON schema, source-citation examples) remains inline in SKILL.md instead of being split into separate navigable files.	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.

A strong, specific description with explicit triggers, casual-term coverage, and a clear negative-trigger boundary that sharply distinguishes it from adjacent skills. It fully answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across create/edit/analyze/convert ("open, read, edit, or fix... adding columns, computing formulas, formatting, charting, cleaning messy data; create... convert between tabular file formats"), matching the 'lists multiple specific concrete actions' anchor rather than the partial coverage of a 2.	3 / 3
Completeness	Explicitly answers both what (open/read/edit/create/convert) and when ("Trigger especially when the user references a spreadsheet file by name or path — even casually", "Also trigger for cleaning or restructuring messy tabular data files"), plus a negative-trigger clause, so the 'when' is explicit rather than implied.	3 / 3
Trigger Term Quality	Covers natural user phrasings including casual ones — "spreadsheet file", ".xlsx, .xlsm, .csv, or .tsv", "the xlsx in my downloads", "messy tabular data files (malformed rows, misplaced headers, junk data)" — well beyond the 'missing common variations' of a 2.	3 / 3
Distinctiveness Conflict Risk	Clear niche with explicit disambiguation — "The deliverable must be a spreadsheet file" and "Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration" — making conflict with sibling 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: eigent-ai/eigent
Path: resources/example-skills/xlsx/SKILL.md
Commit: 9d0a169

Reviewed: about 9 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.