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

Low

Low-risk findings worth noting

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, concrete commands, and a validation-backed workflow including a recalculation feedback loop. It is slightly let down by verbosity in the standards/checklist sections and some inline content that would benefit from being split into a reference file.

Suggestions

Move the detailed financial-modeling color/number-format/formula standards (Requirements for Outputs) into a separate reference file (e.g., references/financial_models.md) and keep a concise summary in SKILL.md, tightening progressive disclosure and conciseness.

Trim the Formula Verification Checklist by removing error-type explanations already produced by scripts/recalc.py's JSON output, keeping only the non-redundant pitfalls (column mapping, row offset, far-right columns).

Consolidate the repeated formula-error enumerations (#REF!, #DIV/0!, etc.) that appear in multiple sections into one authoritative list referenced where needed.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but the "Requirements for Outputs" section and multi-part Formula Verification Checklist include padded detail (e.g., exhaustive color-coding RGB values, repeated error-type lists already covered by recalc.py output) that could be tightened or deferred to a reference.	3 / 5
Actionability	Provides copy-paste ready, fully executable pandas and openpyxl snippets plus a concrete recalc command (`python scripts/recalc.py output.xlsx 30`) and JSON output schema, covering the common create/edit/analyze cases.	5 / 5
Workflow Clarity	The Common Workflow is a clearly sequenced 6-step process with an explicit mandatory recalculation checkpoint (step 5) and a validate→fix→recalculate feedback loop (step 6), satisfying the checkpoint and feedback-loop requirements for batch/spreadsheet operations.	5 / 5
Progressive Disclosure	Good structure with a real one-level-deep bundle reference (scripts/recalc.py and scripts/office/, both present) and well-organized sections, but the financial-modeling standards and verification checklists are largely inlined in SKILL.md rather than split into a reference file, leaving minor organization gaps.	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 exemplary: concrete capabilities, natural trigger terms with synonyms and file extensions, explicit what/when guidance, and clear negative boundaries that prevent mis-triggering. It follows the good-example patterns closely with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "open, read, edit, or fix", "adding columns, computing formulas, formatting, charting, cleaning messy data", "create a new spreadsheet", "convert between tabular file formats" — giving comprehensive coverage of spreadsheet capabilities.	5 / 5
Completeness	Explicitly answers both what (create/edit/fix/convert spreadsheets) and when ("Use this skill any time a spreadsheet file is the primary input or output", "Trigger especially when the user references a spreadsheet file by name or path") with concrete trigger phrases, plus negative boundary guidance.	5 / 5
Trigger Term Quality	Covers natural terms and synonyms users would say ("spreadsheet", "xlsx in my downloads", "messy tabular data", "malformed rows") plus file extensions (.xlsx, .xlsm, .csv, .tsv), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche — deliverable must be a spreadsheet file — reinforced by explicit exclusions ("Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script..."), minimizing 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: tsinghua-fib-lab/AgentSociety
Path: extension/skills/xlsx/SKILL.md
Commit: 13e28b5

Reviewed: 1 day 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.