Profile a table

How many rows does gdp.csv have and what is the largest Value? Save the column statistics as stats.json.

The task

The reference answer shows the job can be done with deft. It is not an agent run.

deft sheet stats gdp.csv --json > stats.json

Input

gdp.csv 549.6 KB

Country Name	Country Code	Year	Value
Afghanistan	AFG	2000	3521418059.923445
Afghanistan	AFG	2001	2813571753.8725324
Afghanistan	AFG	2002	3825701438.9996333
Afghanistan	AFG	2003	4520946818.545814
Afghanistan	AFG	2004	5224896718.67782
Afghanistan	AFG	2005	6203256538.709669
Afghanistan	AFG	2006	6971758282.293506
Afghanistan	AFG	2007	9747886187.393929
Afghanistan	AFG	2008	10109297047.543194
Afghanistan	AFG	2009	12416152732.056717
Afghanistan	AFG	2010	15856668555.833595
Afghanistan	AFG	2011	17805098206.314083
Afghanistan	AFG	2012	19907329777.587166
Afghanistan	AFG	2013	20146416757.598675
Afghanistan	AFG	2014	20497128555.69723
Afghanistan	AFG	2015	19134221644.732494
Afghanistan	AFG	2016	18116572395.077213
Afghanistan	AFG	2017	18753456497.815865
Afghanistan	AFG	2018	18053222687.412624
Afghanistan	AFG	2019	18799444490.11278
Afghanistan	AFG	2020	19955929052.149597
Afghanistan	AFG	2021	14266499429.874573
Afghanistan	AFG	2022	14502158192.090395

Showing 24 of 4985 rows.

Reference output

stats.json 654 B

{"v":1,"ok":true,"op":"sheet.stats","items":[{"ok":true,"inputs":["gdp.csv"],"outputs":[],"facts":{"rows":13979,"columns":[{"name":"Country Name","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Country Code","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Year","filled":13979,"empty":0,"unique":64,"min":1960.0,"max":2023.0,"mean":1994.672866442521,"sum":27883532.0},{"name":"Value","filled":13979,"empty":0,"unique":13903,"min":11502.632644795465,"max":105435039507024.1,"mean":1207379525661.7568,"sum":1.6877958389225698e+16}]},"warnings":[]}],"elapsed_ms":25}

How a result is judged (1 check)

python: code = "import json; t = open('stats.json').read(); assert 'Value' in t and 'max' in t"

Runs

CodexWithout deftPassed2026-11-07

Time: 21s
New tokens: 7.3k
Total input: 54.4k
Output tokens: 0.9k
Commands: 3
Failed: 0

Trace

I’ll inspect `gdp.csv`, compute the row count and largest `Value`, and write per-column statistics to `stats.json` in the current directory.
pwd && rg --files -g 'gdp.csv' -g 'stats.json' -g '*.py' -g 'README*' | head -60
output
```
gdp.csv
```

head -5 gdp.csv && wc -l gdp.csv && ls -l gdp.csv

output

Country Name,Country Code,Year,Value
Afghanistan,AFG,2000,3521418059.923445
Afghanistan,AFG,2001,2813571753.8725324
Afghanistan,AFG,2002,3825701438.9996333
Afghanistan,AFG,2003,4520946818.545814
   13979 gdp.csv
-rw-r--r--@ 1 user  staff  562767 Nov  5 21:11 gdp.csv

python3 - <<'PY' import csv, json, math, statistics from collections import Counter from pathlib import Path path = Path('gdp.csv') with path.open(newline='', encoding='utf-8-sig') as f: reader = csv.DictReader(f) rows = list(reader) columns = reader.fieldnames result = {'row_count': len(rows), 'columns': {}} for col in columns: vals = [row[col] for row in rows] present = [v for v in vals if v not in (None, '')] info = {'count': len(present), 'null_count': len(vals) - len(present), 'unique': len(set(present))} nums = [] try: nums = [float(v) for v in present] except ValueError: pass if len(nums) == len(present) and nums: info.update({ 'min': min(nums), 'max': max(nums), 'mean': statistics.mean(nums), 'median': statistics.median(nums), 'std': statistics.stdev(nums) if len(nums) > 1 else 0.0, }) else: freq = Counter(present) info['top'] = [{'value': v, 'count': c} for v, c in freq.most_common(1)] result['columns'][col] = info with path.open(newline='', encoding='utf-8-sig') as f: reader = csv.DictReader(f) largest = max(float(row['Value']) for row in reader if row['Value'] not in ('', None)) result['largest_value'] = largest Path('stats.json').write_text(json.dumps(result, indent=2, ensure_ascii=False) + '\\n', encoding='utf-8') print(json.dumps({'row_count': len(rows), 'largest_value': largest, 'stats_file': str(Path('stats.json').resolve())}, indent=2)) PY
output
```
{
  "row_count": 13979,
  "largest_value": 105435039507024.1,
  "stats_file": "stats.json"
}
```
`gdp.csv` has **13,979 data rows**. The largest `Value` is **105,435,039,507,024.1**. I saved the column statistics in [stats.json](stats.json).

Output

stats.json 951 B

{
  "row_count": 13979,
  "columns": {
    "Country Name": {
      "count": 13979,
      "null_count": 0,
      "unique": 262,
      "top": [
        {
          "value": "Africa Eastern and Southern",
          "count": 64
        }
      ]
    },
    "Country Code": {
      "count": 13979,
      "null_count": 0,
      "unique": 262,
      "top": [
        {
          "value": "AFE",
          "count": 64
        }
      ]
    },
    "Year": {
      "count": 13979,
      "null_count": 0,
      "unique": 64,
      "min": 1960.0,
      "max": 2023.0,
      "mean": 1994.672866442521,
      "median": 1996.0,
      "std": 17.731412569745608
    },
    "Value": {
      "count": 13979,
      "null_count": 0,
      "unique": 13903,
      "min": 11502.632644795465,
      "max": 105435039507024.1,
      "mean": 1207379525661.7576,
      "median": 16725908148.548136,
      "std": 5537517274228.241
    }
  },
  "largest_value": 105435039507024.1
}

CodexWith deft, skill installedPassedRead the skillUsed deft2026-11-07

Time: 18s
New tokens: 14.7k
Total input: 88.2k
Output tokens: 0.6k
Commands: 5
Failed: 0

Trace

I’ll inspect `gdp.csv`, calculate the row count and column statistics, then save the statistics to `stats.json` in the current directory.

cat .agents/skills/deft/SKILL.md && rg --files -g 'gdp.csv' -g 'AGENTS.md'

output

---
name: deft
description: "Use deft instead of writing a script for file jobs: PDF merge/split/compress/watermark, image resize/convert/compress, video and audio trim/convert/compress, spreadsheets, Markdown to PDF/HTML, and YouTube downloads and subtitles."
---

# deft

One local command for file jobs. Prefer it over writing Python or shell scripts.

Syntax: `deft <group> <command> [inputs] [-o output] [--options]`

Groups:
- `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert
- `image`: Resize, crop, convert, compress, filters, montage, OCR
- `video`: Trim, crop, speed, convert, compress, GIF, frames (ffmpeg)
- `audio`: Convert, trim, merge, fade, speed, tag, normalize (ffmpeg)
- `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace
- `slides`: PowerPoint: extract text, Markdown outline, PDF handout
- `data`: JSON/YAML/TOML/XML: convert, query with jq syntax, merge, diff
- `sheet`: Excel/CSV/ODS tables: filter, sort, join, pivot, convert
- `md`: Markdown to PDF, HTML, Word, EPUB; table of contents
- `html`: HTML to Markdown, text, Word, PDF; screenshots
- `epub`: E-books: info, to text, Markdown and PDF
- `email`: EML files: headers, text, attachments
- `contact`: VCF address books: to and from CSV
- `calendar`: ICS calendars: to and from CSV
- `gps`: GPX and KML tracks: convert, distance and time
- `youtube`: Info, download, audio, subtitles, thumbnail (yt-dlp)
- `file`: Any file: hash, duplicates, batch rename, base64, encoding
- `qr`: Cre
… 736 more characters

deft sheet

output

deft sheet - commands (input -> output)
  info       sheet -> report           Sheet names, rows, columns
  convert    sheet -> sheet            Change format: --to csv|xlsx|json
  dedupe     sheet -> sheet            Drop repeated rows, by whole row or --columns
  extract    sheet -> sheet            Take a sheet or range: --sheet, --range A1:D20
  filter     sheet -> sheet            Keep matching rows: --where "age > 30 and city = 'Oslo'"
  from-pdf   pdf -> sheet              All text as one table [beta]
  group      sheet -> sheet            Group and total: --columns city --values sales --agg sum
  join       sheet... -> sheet         Join two tables on a key: --on id --how left
  merge      sheet... -> sheet         Stack tables; a shared header is kept once
  pivot      sheet -> sheet            Pivot table: --rows city --columns year --values sales
  query      sheet|sqlite... -> sheet  Run SQL over tables or a SQLite file: --sql 'select ...'
  select     sheet -> sheet            Keep, reorder or --drop columns
  sort       sheet -> sheet            Sort rows: --columns age,name --descending
  split      sheet -> sheet...         Split up: --sheets, --columns city or --every 1000
  stats      sheet -> report           Per-column counts, empties, min, max, mean, sum
  to-md      sheet -> md               Markdown table (first row is the header)
  transpose  sheet -> sheet            Swap rows and columns
More: deft sheet <command> --help

deft sheet info gdp.csv --json && deft sheet stats gdp.csv --help && deft sheet stats gdp.csv --json

output

{"v":1,"ok":true,"op":"sheet.info","items":[{"ok":true,"inputs":["gdp.csv"],"outputs":[],"facts":{"sheets":[{"name":"gdp","rows":13980,"columns":4}]},"warnings":[]}],"elapsed_ms":10}
deft sheet stats - Per-column counts, empties, min, max, mean, sum

Usage: deft sheet stats <sheet>... [options]
In: sheet (each handled separately)   Out: printed result

Options:
  --sheet <text>               Sheet name or number (default: first)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft sheet stats people.csv

Result fields: rows, columns
{"v":1,"ok":true,"op":"sheet.stats","items":[{"ok":true,"inputs":["gdp.csv"],"outputs":[],"facts":{"rows":13979,"columns":[{"name":"Country Name","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Country Code","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Year","filled":13979,"empty":0,"unique":64,"min":1960.0,"max":2023.0,"mean":1994.672866442521,"sum":27883532.0},{"name":"Value","filled":13979,"empty":0,"unique":13903,"min":11502.632644795465,"max":105435039507024.1,"mean":1207379525661.7568,"sum":1.6877958389225698e+16}]},"warnings":[]}],"elapsed_ms":18}

deft sheet stats gdp.csv -o stats.json --force --json

output

{"v":1,"ok":true,"op":"sheet.stats","items":[{"ok":true,"inputs":["gdp.csv"],"outputs":[],"facts":{"rows":13979,"columns":[{"name":"Country Name","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Country Code","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Year","filled":13979,"empty":0,"unique":64,"min":1960.0,"max":2023.0,"mean":1994.672866442521,"sum":27883532.0},{"name":"Value","filled":13979,"empty":0,"unique":13903,"min":11502.632644795465,"max":105435039507024.1,"mean":1207379525661.7568,"sum":1.6877958389225698e+16}]},"warnings":[]}],"elapsed_ms":18}

deft sheet stats gdp.csv --json > stats.json && cat stats.json

output

{"v":1,"ok":true,"op":"sheet.stats","items":[{"ok":true,"inputs":["gdp.csv"],"outputs":[],"facts":{"rows":13979,"columns":[{"name":"Country Name","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Country Code","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Year","filled":13979,"empty":0,"unique":64,"min":1960.0,"max":2023.0,"mean":1994.672866442521,"sum":27883532.0},{"name":"Value","filled":13979,"empty":0,"unique":13903,"min":11502.632644795465,"max":105435039507024.1,"mean":1207379525661.7568,"sum":1.6877958389225698e+16}]},"warnings":[]}],"elapsed_ms":18}

`gdp.csv` has **13,979 data rows** (13,980 including the header). The largest `Value` is **105,435,039,507,024.1**. I saved the per-column statistics in [stats.json](stats.json).

Output

stats.json 654 B

{"v":1,"ok":true,"op":"sheet.stats","items":[{"ok":true,"inputs":["gdp.csv"],"outputs":[],"facts":{"rows":13979,"columns":[{"name":"Country Name","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Country Code","filled":13979,"empty":0,"unique":262,"min":null,"max":null,"mean":null,"sum":null},{"name":"Year","filled":13979,"empty":0,"unique":64,"min":1960.0,"max":2023.0,"mean":1994.672866442521,"sum":27883532.0},{"name":"Value","filled":13979,"empty":0,"unique":13903,"min":11502.632644795465,"max":105435039507024.1,"mean":1207379525661.7568,"sum":1.6877958389225698e+16}]},"warnings":[]}],"elapsed_ms":18}

Claude Opus 5.5Without deftPassed2026-11-07

Time: 21s
New tokens: 10.1k
Total input: 42.9k
Output tokens: 1.0k
Commands: 0
Failed: 0

Trace

Output

stats.json 790 B

{
  "row_count": 13979,
  "columns": {
    "Country Name": {
      "count": 13979,
      "missing": 0,
      "unique": 262,
      "type": "string"
    },
    "Country Code": {
      "count": 13979,
      "missing": 0,
      "unique": 262,
      "type": "string"
    },
    "Year": {
      "count": 13979,
      "missing": 0,
      "unique": 64,
      "type": "numeric",
      "min": 1960.0,
      "max": 2023.0,
      "mean": 1994.672866442521,
      "median": 1996.0,
      "std": 17.731412569745608
    },
    "Value": {
      "count": 13979,
      "missing": 0,
      "unique": 13903,
      "type": "numeric",
      "min": 11502.632644795465,
      "max": 105435039507024.1,
      "mean": 1207379525661.7576,
      "median": 16725908148.548136,
      "std": 5537517274228.241
    }
  }
}

Claude Opus 5.5With deft, skill installedPassedRead the skillUsed deft2026-11-07

Time: 17s
New tokens: 10.9k
Total input: 76.1k
Output tokens: 0.7k
Commands: 0
Failed: 0

Trace

Output

.claude/skills/deft/SKILL.md 2.1 KB

---
name: deft
description: "Use deft first for any simple, direct operation on local files, whatever the type: convert, read, extract, edit, compress, merge, split, compare or inspect. Try it before writing a script or one-liner. If unsure, run deft find; if it says no command does this, use another tool. Not for programming work: to read, write or change source code, skip it."
---

# deft

One local command for file jobs. Prefer it over writing Python or shell scripts.

Syntax: `deft <group> <command> [inputs] [-o output] [--options]`

Groups:
- `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert
- `image`: Resize, crop, convert, compress, adjust, montage, OCR
- `video`: Trim, merge, convert, compress, subtitles, GIF, frames (ffmpeg)
- `audio`: Convert, trim, normalize, denoise, cut silence (ffmpeg)
- `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace
- `slides`: PowerPoint: extract text, Markdown outline
- `sheet`: Excel/CSV/ODS tables: SQL query, pivot, merge, split, convert
- `json`: JSON: convert, format, merge, diff, validate
- `toml`: TOML: convert, format, merge, diff, validate
- `xml`: XML: convert, format, merge, diff, validate
- `yaml`: YAML: convert, format, merge, diff, validate
- `md`: Markdown to PDF, HTML, Word, EPUB; table of contents
- `html`: HTML to Markdown, text, Word and PDF
- `epub`: E-books: info, to text, Markdown and PDF
- `gps`: GPX and KML tracks: convert, distance and time
- `qr`: Create QR codes and barcodes; read QR codes

How to use it:
1. Run `deft <group>` to list commands, or `deft find "<what you want>"` to search. If it says `no command does this`, use another tool.
2. Run `deft <group> <command> --help` for options and examples.
3. `deft convert <in> -o <out.ext>` converts between formats by extension.
4. Results are one line starting with `ok`, `partial` or `error`; add `--json` to parse them. Errors include a `hint:` with the fix.

Inputs are never overwritten; pass `--force` or `--in-place` to allow it. Globs and directories work as inputs; several inputs run in parallel.

If `deft` is not installed, ask the user, then follow https://github.com/firstprayer/deft/blob/main/docs/INSTALL.md

stats.json 831 B

{
  "rows": 13979,
  "columns": [
    {
      "name": "Country Name",
      "filled": 13979,
      "empty": 0,
      "unique": 262,
      "min": null,
      "max": null,
      "mean": null,
      "sum": null
    },
    {
      "name": "Country Code",
      "filled": 13979,
      "empty": 0,
      "unique": 262,
      "min": null,
      "max": null,
      "mean": null,
      "sum": null
    },
    {
      "name": "Year",
      "filled": 13979,
      "empty": 0,
      "unique": 64,
      "min": 1960.0,
      "max": 2023.0,
      "mean": 1994.672866442521,
      "sum": 27883532.0
    },
    {
      "name": "Value",
      "filled": 13979,
      "empty": 0,
      "unique": 13903,
      "min": 11502.632644795465,
      "max": 105435039507024.1,
      "mean": 1207379525661.7568,
      "sum": 1.6877958389225698e+16
    }
  ]
}

Claude CodeWithout deftNot run yet

Claude CodeWith deftNot run yet