CtrlK
BlogDocsLog inGet started
Tessl Logo

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

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./ruoyi-admin/src/main/resources/skills/xlsx/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 delivers strong, actionable domain guidance (financial-modeling color/number standards, formula-vs-hardcode rules, a validated recalc workflow) but is padded with introductory library tutorials Claude already knows and triplicate recalc.py --create examples. Progressive disclosure is weak: it is a monolithic file that references a recalc.py script which is not present in any bundle directory.

Suggestions

Move the introductory pandas/openpyxl tutorials and the recalc.py --create JSON-format reference into separate reference files (e.g. references/recalc.md, references/financial-modeling.md), keeping SKILL.md as a lean overview with one-level-deep links.

Actually include the referenced recalc.py in a scripts/ directory (or remove the invocation examples) so the 'python recalc.py ...' commands are executable rather than pointing at a missing file.

Trim over-explanation of basics Claude already knows (e.g. 'df.head() # Preview data', 'sheet["A1"] = "Hello"') and collapse the three repeated --create examples into one; remove the leaked 'ruoyi-ai-v3/' project-root path references that are irrelevant to the skill.

DimensionReasoningScore

Conciseness

Noticeably verbose with several padded sections — introductory pandas/openpyxl tutorials ('sheet["A1"] = "Hello"', 'df.head() # Preview data') explaining basics Claude already knows, plus the recalc.py --create command shown three times with overlapping examples and a redundant path table. Not score 3 because the padding is pervasive rather than 'some' over-explanation; not score 1 because the financial-modeling standards and formula-vs-hardcode guidance genuinely earn their tokens.

2 / 5

Actionability

Provides copy-paste-ready code (pandas, openpyxl create/edit), exact recalc.py invocation syntax with a fully specified --create JSON format, and concrete RGB values and format strings ('$#,##0;($#,##0);-'). Minor gap: recalc.py is referenced as a runnable script but is not present in any bundle directory, so the commands cannot actually be executed as-is.

4 / 5

Workflow Clarity

The 'Common Workflow' is a clear 6-step sequence with an explicit MANDATORY recalculation validation step and a fix-and-recalculate-again feedback loop, supplemented by a Formula Verification Checklist. Not score 5 because the material is scattered across separate 'Recalculating formulas', 'Creating workbooks with recalc.py', and 'Interpreting recalc.py Output' sections rather than integrated, and the --create workflow is not connected to the main workflow.

4 / 5

Progressive Disclosure

Has reasonable section headers and in-file navigation, but all content is inlined in one ~360-line file with no split into reference files, and the single referenced external file (recalc.py) is not actually bundled. Not score 2 because section structure is present (the score-2 anchor specifies 'no section headers'); not score 4 because there is no real one-level-deep file disclosure and the one referenced path is missing.

3 / 5

Total

13

/

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: third-person voice, concrete actions, natural trigger terms with file extensions, and an explicit 'When Claude needs to work with...' clause enumerating five use cases. It matches the structurally identical presentation-skill good example almost exactly.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'creation, editing, and analysis', 'formulas, formatting, data analysis, and visualization', 'Modify existing spreadsheets while preserving formulas', 'Recalculating formulas' — with comprehensive coverage across five enumerated use cases, matching the score-5 anchor.

5 / 5

Completeness

Explicitly states what ('Comprehensive spreadsheet creation, editing, and analysis...') and when ('When Claude needs to work with spreadsheets... for: (1)... (5)...') with concrete enumerated trigger phrases; the explicit 'When Claude needs to work with...' clause satisfies the trigger-guidance requirement so completeness is not capped at 3.

5 / 5

Trigger Term Quality

Covers natural terms and synonyms ('spreadsheets') plus file extensions ('.xlsx, .xlsm, .csv, .tsv, etc') and task phrases ('formulas', 'formatting', 'data analysis', 'visualization'), matching the comprehensive-coverage anchor including extensions.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear spreadsheet niche with distinct triggers (xlsx/xlsm/csv/tsv, formulas, recalculation) and minimal overlap risk with unrelated skills, matching the 'clear niche with distinct triggers' anchor.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ageerle/ruoyi-ai
Reviewed

Table of Contents

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.