agentsclimarketplace

Spreadsheet analysis

Skill openagentskills/betterskills/skills/data/spreadsheet-analysis

Portable, open catalogue of agent skills for Cursor, Claude Code, Windsurf, Copilot, and other AI coding assistants.

Install
npx -y skills add openagentskills/betterskills --skill spreadsheet-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Analyzes tabular data in CSV, Excel, or pasted tables with summary stats, trends, and chart recommendations. Use for spreadsheet analysis, data exploration, pivot suggestions, or .xlsx and .csv files.

SKILL.md

1.6 KB, 318 tokens by cl100k_base, as published. Nobody here has run it

Spreadsheet Analysis

Workflow

  1. Profile — rows, columns, dtypes, null %, duplicates
  2. Clean — document assumptions (drops, fills, parsing)
  3. Analyze — aggregates, trends, outliers
  4. Recommend — charts and next questions

Profiling output

## Dataset profile
- Rows / columns:
- Key columns:
- Missing values:
- Duplicates:
- Date range (if applicable):

## Column summary
| Column | Type | Null% | Notes |
|--------|------|-------|-------|

Analysis patterns

Question typeApproach
ComparisonGroup by category, mean/median/count
TrendTime series, period-over-period
DistributionHistogram bins, percentiles
CorrelationNote strength; do not imply causation

Tool preference

When code is needed:

  • Python: pandas for exploration; mention openpyxl for xlsx
  • SQL: if data already in a warehouse

Show reproducible snippets, not one-off opaque steps.

Visualization suggestions

Data shapeChart
Category vs valueBar
Time vs valueLine
Part-to-wholeStacked bar or treemap (sparingly)
Two numericScatter

Rules

  • State limitations of sample size
  • Flag PII columns; avoid echoing sensitive values in summaries
  • Prefer aggregated outputs over dumping raw rows

What ships with it: 1 file

328 B alongside SKILL.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.