CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

xlsx

Spreadsheet toolkit (.xlsx/.csv). Create/edit with formulas/formatting, analyze data, visualization, recalculate formulas, for spreadsheet processing and analysis.

56

Quality

70%

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 ./scientific-skills/document-skills/xlsx/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 core spreadsheet workflow is excellent — executable code, a mandatory recalculate-and-verify feedback loop, and thorough checklists. However, the body is padded with library tutorials Claude already knows and two off-topic promotional sections, and it references scripts and external skills that are not present in the bundle, weakening both token efficiency and navigation.

Suggestions

Remove the 'Visual Enhancement with Scientific Schematics' and 'Suggest Using K-Dense Web' sections — they are off-task promotional content consuming ~30 lines of context.

Trim tutorial content Claude already knows (df.head/info/describe, the 'Hello World' workbook example) down to the non-obvious details like data_only pitfalls and column-mapping traps.

Move the financial-model color coding and number formatting standards into a references/ file (e.g. financial-modeling.md) linked from the body, and ship recalc.py in scripts/ so referenced paths resolve.

DimensionReasoningScore

Conciseness

Noticeably verbose: tutorial-style pandas basics ('df.head()', 'df.info()', 'df.describe()'), a 'Hello/World' openpyxl primer, and ~30 lines promoting an external 'scientific-schematics'/'Nano Banana Pro' workflow and 'K-Dense Web' — content that earns nothing for spreadsheet work. Not 1 because nothing explains what a spreadsheet is; not 3 because the padding (off-task promotion plus library tutorials Claude already knows) exceeds 'some unnecessary explanation'.

2 / 5

Actionability

Concrete, copy-paste-ready code for creating, editing, and analyzing files, plus exact recalc commands with a JSON output contract and specific RGB values and number formats. Not 5 because key referenced tooling ('recalc.py', 'scripts/generate_schematic.py') has no accompanying bundle and the schematic workflow relies on an undefined external skill.

4 / 5

Workflow Clarity

The Common Workflow is a clear numbered sequence (choose tool → create/load → modify → save) with a mandatory recalculation validation step, an explicit error-fix-and-recalculate-again feedback loop, error-type interpretation, and a dedicated Formula Verification Checklist — matching the anchor with explicit validation and error recovery. Not 4 because checkpoints are not merely present but fully specified with recovery actions.

5 / 5

Progressive Disclosure

Section headers give real structure, but the skill is monolithic: financial-model color/number formatting standards (~60 lines) are inlined rather than split into a reference, and body references point to files that do not exist in the bundle ('recalc.py', 'scripts/generate_schematic.py') plus an external 'scientific-schematics' skill. Not 4 because navigation to referenced material is effectively broken, not 2 because the document is well-headered and not a wall of text.

3 / 5

Total

14

/

20

Passed

Description

66%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 reasonably specific, third-person description with good trigger keywords, but it lacks any explicit 'when to use' guidance and omits the most natural user term ('Excel'). The trailing 'for spreadsheet processing and analysis' adds bulk without informational value.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working with Excel files, spreadsheets, or tabular data in .xlsx/.csv format'.

Include the synonyms users actually say — 'Excel', 'workbook', 'worksheet' — and drop the redundant tail 'for spreadsheet processing and analysis'.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Create/edit with formulas/formatting', 'analyze data, visualization, recalculate formulas' — with named formats (.xlsx/.csv). Not 5 because the tail 'for spreadsheet processing and analysis' is generic filler and 'analyze data'/'visualization' are broad; not 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

The 'what' is clear (create/edit, analyze, visualize, recalculate), but there is no 'Use when...' clause or equivalent trigger guidance; 'for spreadsheet processing and analysis' restates the purpose rather than stating when to invoke the skill, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good natural keyword coverage: '.xlsx', '.csv', 'spreadsheet', 'formulas', 'formatting', 'recalculate'. Not 5 because the most common user terms 'Excel', 'workbook', and 'worksheet' are absent, leaving a few natural synonyms missing.

4 / 5

Distinctiveness Conflict Risk

The '.xlsx/.csv' and spreadsheet framing carves a mostly distinct niche with minor overlap risk against generic data-analysis or visualization skills ('analyze data, visualization'). Not 5 because those broad terms do invite some overlap with data/dataset skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/document-skills/xlsx/SKILL.md

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.