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

85%

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

77%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, exact commands, and a well-validated recalculate-and-fix workflow. Its weaknesses are token redundancy (repeated error lists and triplicated recalc.py documentation) and a monolithic structure that inlines financial-modeling standards that belong in one-level-deep reference files.

Suggestions

Split the financial-model conventions (Color Coding Standards, Number Formatting Standards, formula documentation requirements) into a separate reference file (e.g. financial-modeling.md) and link to it from SKILL.md.

Deduplicate the Excel error documentation: #REF!/#DIV/0!/#VALUE!/#NAME? appear in 'Zero Formula Errors', the workflow's 'Common errors to fix', the pitfalls checklist, and the recalc.py feature list — keep one canonical list.

Consolidate the three recalc.py sections ('Recalculating formulas', 'Creating workbooks with recalc.py', and its workflow step) into one section, give the script an explicit bundle path, and remove the project-specific 'ruoyi-ai-v3/' default-path leakage.

Dimension	Reasoning	Score
Conciseness	Mostly operational, but noticeably padded: Excel error types (#REF!, #DIV/0!, #NAME?) are repeated across four sections, recalc.py usage is documented three times, and filler like 'pandas which provides powerful data manipulation capabilities' appears. Fits anchor 3 ('mostly efficient but could be tightened'), not 4 because the redundancy is more than minor.	3 / 5
Actionability	Fully executable throughout: runnable openpyxl/pandas snippets, exact commands ('python recalc.py output.xlsx 30', '--create' with JSON payloads), and concrete output-format examples. Copy-paste ready, matching the anchor-5 example.	5 / 5
Workflow Clarity	A numbered 6-step Common Workflow marks recalculation as 'MANDATORY IF USING FORMULAS', interprets the script's JSON error output, and closes an explicit feedback loop ('Fix the identified errors and recalculate again'), plus a verification checklist. Matches anchor 5; not 4 because validation checkpoints and error recovery are fully explicit.	5 / 5
Progressive Disclosure	Section headers give navigation, but the ~360-line body is monolithic: financial-model color/number-format standards and recalc.py --create documentation are inlined where a reference file belongs, and 'recalc.py' is cited with no path and no bundle file (the skill directory contains only SKILL.md). Anchor 3 ('content that should be separate is inline'), not 2 since structure and section headers do exist.	3 / 5
	Total	16 / 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 description: it states what the skill does and when to use it with an explicit trigger list and concrete enumerated capabilities, closely matching the rubric's good examples. The only meaningful gap is missing the ubiquitous 'Excel'/'workbook' trigger terms users naturally say.

Dimension	Reasoning	Score
Specificity	Enumerates concrete actions — 'spreadsheet creation, editing, and analysis' plus five numbered tasks ('Creating new spreadsheets with formulas and formatting', 'Modify existing spreadsheets while preserving formulas', 'Recalculating formulas') — giving comprehensive, anchor-5 coverage with no notable gaps, so not 4.	5 / 5
Completeness	Explicitly answers both: 'Comprehensive spreadsheet creation, editing, and analysis...' (what) and 'When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1)...(5)' (when) — a near-exact match to the anchor-5 good example; not 4 because the 'when' clause is fully explicit with concrete triggers.	5 / 5
Trigger Term Quality	Good natural coverage ('spreadsheets, .xlsx, .xlsm, .csv, .tsv, formulas, formatting') but omits the most common user phrasings 'Excel' and 'workbook', fitting anchor 4 ('good keyword coverage; a few natural terms missing') rather than 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Clear spreadsheet niche with distinct file-extension triggers; 'in spreadsheets' scopes the analysis/visualization claims so overlap with generic data-analysis skills is minimal. Not 4 because no closely-related skill conflict is identifiable.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ageerle/ruoyi-ai
Path: ruoyi-admin/src/main/resources/skills/xlsx/SKILL.md
Commit: 7c7e643

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.