xlsx

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Quality

81%

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

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

Quality

Content

70%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.

A highly actionable, well-sequenced skill body with strong validation feedback loops for formula recalculation. Its main weaknesses are moderate verbosity/padding and a missing referenced script (`recalc.py`) that the workflow depends on.

Suggestions

Ship the referenced `recalc.py` under scripts/ (or remove the dependency and inline the LibreOffice recalculation commands) so the mandatory workflow step is actually executable.

Collapse the three repetitive hardcoding 'Bad' examples into one and drop the toy 'Hello'/'World' creation example in favor of a realistic minimal model.

Move the detailed financial-model color-coding and number-formatting standards into a references/ file (e.g., FINANCIAL_MODELS.md) and link to it from the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but includes padded spots: 'pandas which provides powerful data manipulation capabilities', a toy 'Hello'/'World' creation example, and three repetitive 'Bad:' hardcoding examples that could collapse to one.	3 / 5
Actionability	Provides copy-paste-ready code for pandas read/write, openpyxl create/edit, and the `recalc.py` command with its JSON output schema and error-fix loop; minor gaps are the toy creation example and absence of a complete realistic end-to-end model.	4 / 5
Workflow Clarity	The 'Common Workflow' gives a numbered 6-step sequence with an explicit validation checkpoint (run recalc.py, inspect JSON error_summary, fix and recalculate) plus a Formula Verification Checklist — a clear feedback loop for error recovery.	5 / 5
Progressive Disclosure	Well-sectioned but monolithic at ~290 lines with detailed reference-grade material (financial-model color/number-formatting standards) inlined; more problematically, the body repeatedly references `recalc.py` yet no scripts/ directory exists in the bundle.	3 / 5
	Total	15 / 20 Passed

Description

92%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.

A strong, well-structured description that clearly states capabilities and explicit use-conditions with concrete trigger terms and file extensions. Its only gap is the missing colloquial synonym 'Excel', which users frequently say.

Suggestions

Add 'Excel' as a natural synonym (e.g., 'spreadsheets (Excel, .xlsx, .xlsm, .csv, .tsv)') so the description matches the term users most commonly say.

Consider adding 'pivot tables' or 'charts' as concrete trigger nouns if those are in-scope capabilities.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creation, editing, and analysis', 'formulas, formatting, data analysis, and visualization' — plus five enumerated tasks (creating, reading/analyzing, modifying while preserving formulas, data analysis/visualization, recalculating), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (spreadsheet creation/editing/analysis with formulas, formatting, visualization) and 'when' ('When Claude needs to work with spreadsheets ... for: (1)...(5)') with concrete trigger phrases, mirroring the anchor-5 example structure.	5 / 5
Trigger Term Quality	Strong coverage of natural terms and multiple file extensions ('spreadsheets', '.xlsx, .xlsm, .csv, .tsv', 'formulas', 'formatting'), but the very common synonym 'Excel' is absent, leaving a few natural user terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche keyed to spreadsheet files and extensions (.xlsx/.xlsm/.csv/.tsv) with distinct triggers, giving minimal conflict risk with other skills; the .csv/.tsv overlap is minor.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/xlsx/SKILL.md
Commit: 100d3f7

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.