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

77

1.35x
Quality

82%

Does it follow best practices?

Impact

76%

1.35x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

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

SKILL.md
Quality
Evals
Security

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.

Highly actionable content with an exemplary validation-and-recovery workflow centered on the recalc.py feedback loop. Its weaknesses are token efficiency (boilerplate library usage and triple-listed error types) and structure — everything is inline with no reference files, and the invoked recalc.py script is not actually present in the bundle.

Suggestions

Trim the elementary pandas/openpyxl usage examples and consolidate the three repeated lists of Excel error types (#REF!, #DIV/0!, #VALUE!, #NAME?) into one location, e.g. the recalc.py output section.

Move the financial-model standards (color coding, number formatting, hardcode documentation) into a separate references/ file (e.g. references/financial-modeling.md) linked from a short section, keeping SKILL.md as an overview.

Ship the recalc.py script in the bundle (e.g. scripts/recalc.py) and reference it by its actual path — the body invokes it as mandatory in every formula workflow, but no such file exists alongside SKILL.md.

DimensionReasoningScore

Conciseness

Includes basic library boilerplate Claude already knows (elementary pd.read_excel/Workbook usage, pandas dtype and parse_dates hints), and the four Excel error types (#REF!, #DIV/0!, #VALUE!, #NAME?) are repeated in three separate sections. Anchored at 3 ('mostly efficient but some unnecessary explanation or could be tightened') — the redundancy exceeds anchor 4's 'minor instances', but there is no anchor-2-style conceptual padding.

3 / 5

Actionability

Fully executable, copy-paste-ready code for creating, editing, and analyzing files; exact commands ('python recalc.py output.xlsx 30'); a concrete JSON output schema; and paired wrong/right formula examples ('=B5*(1+$B$6)' instead of '=B5*1.05'). Matches the top anchor — common cases are covered with specific runnable guidance.

5 / 5

Workflow Clarity

A numbered 6-step workflow marks recalculation as MANDATORY, includes a feedback loop ('Fix the identified errors and recalculate again'), documents the JSON error output for diagnosis, and adds a verification checklist. Validation checkpoints are explicit, so the missing-validation cap does not apply; matches the top anchor including error-recovery loops.

5 / 5

Progressive Disclosure

The body is a monolithic ~285-line document with no bundle files at all — the financial-model color/numbering standards and the verification checklists are inline material that belongs in separate reference files, and the repeatedly referenced 'recalc.py' script does not exist in the bundle (no scripts/ directory). Anchor 3 fits ('some structure but... content that should be separate is inline'); not 2 because section headers make it navigable, not 4 because nothing is actually split out.

3 / 5

Total

16

/

20

Passed

Description

87%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 that explicitly states what the skill does and gives a well-enumerated 'when' trigger clause with concrete file extensions. The main gap is keyword coverage: the everyday term 'Excel' is absent, and a couple of capabilities (visualization, data analysis) are named only generically.

DimensionReasoningScore

Specificity

Lists several specific actions ('Creating new spreadsheets with formulas and formatting', 'Modify existing spreadsheets while preserving formulas', 'Recalculating formulas') with minor coverage gaps — 'visualization' and 'data analysis' are named but never concretized, and 'Comprehensive' is a buzzword. Not a 5 because the actions are less concrete than the top anchor's specific verbs; clearly above a 3 since multiple distinct actions are enumerated.

4 / 5

Completeness

Explicitly answers both 'what' (creation, editing, analysis, formulas, formatting, visualization) and 'when' via the enumerated 'When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1)...(5)' clause with concrete trigger scenarios. Matches the top anchor and the presentation-skill good example; anchor 4's weaker 'when' does not apply.

5 / 5

Trigger Term Quality

Good keyword coverage with 'spreadsheets' plus four file extensions (.xlsx, .xlsm, .csv, .tsv), but the single most natural user term 'Excel' is missing. Fits anchor 4 ('good keyword coverage; a few natural terms missing') rather than 5's comprehensive synonym coverage; well above anchor 3 because extensions and format variations are present.

4 / 5

Distinctiveness Conflict Risk

Clear spreadsheet-processing niche anchored by distinct file extensions (.xlsx, .xlsm), making confusion with other skills unlikely. Matches the top anchor's 'clear niche with distinct triggers; minimal conflict risk'; anchor 4's 'minor overlap risk' would require ambiguity with a closely related skill that isn't present.

5 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ThinkInAIXYZ/deepchat
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.