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

90%

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

81%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 is highly actionable with executable code, a clearly sequenced workflow that includes mandatory recalculation and error-recovery feedback loops, and a real bundle of scripts it correctly defers to. Its main weakness is conciseness: several padded explanations and overlapping sections could be trimmed to respect the context budget.

Suggestions

Tighten the WRONG/CORRECT formula section by collapsing the three paired examples into one and removing comments that restate the obvious, cutting roughly a third of that block's tokens.

Merge the overlapping "Recalculating formulas" and "Interpreting scripts/recalc.py Output" sections so the recalc command and its JSON schema appear once rather than twice.

Drop generic filler like "pandas which provides powerful data manipulation capabilities" and the Best Practices prose that restates what the code already shows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code, but padded in places: restating-the-obvious comments in the WRONG/CORRECT blocks, "pandas which provides powerful data manipulation capabilities", and overlap between the Common Workflow, Recalculating formulas, and recalc output sections that could be tightened.	3 / 5
Actionability	Copy-paste-ready executable code for pandas read/write, openpyxl create/edit/formatting, and a concrete recalc.py command with the full JSON output schema, covering the common cases specifically.	5 / 5
Workflow Clarity	A numbered 6-step Common Workflow includes a MANDATORY recalculation step and an explicit feedback loop (verify errors -> fix -> recalculate again), with a Formula Verification Checklist reinforcing validation for these file-mutating operations.	5 / 5
Progressive Disclosure	Well-organized sections and the heavy machinery (recalc.py, office validate/pack/unpack/soffice) is appropriately externalized as real bundle scripts referenced inline, though some reference-like material (the full recalc JSON schema, verbose openpyxl examples) is inlined rather than split into one-level-deep reference files.	4 / 5
	Total	17 / 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 exceptional: it explicitly states concrete capabilities, provides comprehensive natural trigger terms and file extensions, and includes explicit positive and negative triggering guidance that sharply delineates the skill from adjacent ones.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full lifecycle (open/read/edit/fix, adding columns, computing formulas, formatting, charting, cleaning, creating, converting) with examples, giving comprehensive coverage rather than a minor-gap list.	5 / 5
Completeness	Explicitly answers both what (open/read/edit/fix/create/convert spreadsheet files) and when ("Trigger especially when...", "Also trigger for...", plus explicit "Do NOT trigger when..." anti-triggers) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural terms users say plus synonyms and file extensions (.xlsx, .xlsm, .csv, .tsv), and even casual phrasing like "the xlsx in my downloads", matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Clear spreadsheet niche with explicit anti-triggers that distinguish it from Word documents, HTML reports, Python scripts, database pipelines, and Google Sheets, giving minimal conflict risk.	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: eigent-ai/eigent
Path: resources/example-skills/xlsx/SKILL.md
Commit: d308955

Reviewed: 2 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.