Ask a table with SQL

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

Time

21s

New tokens

9.9k

Total input

102.9k

Output tokens

0.7k

Commands

9

Failed

0

Trace

1. I’ll inspect `gdp.csv`, identify the 2015 values, and write the ten highest rows to `top.csv` in the current directory.

2. cat .agents/skills/deft/SKILL.md
   output

   ---
   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, 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, downlo
   … 849 more characters

3. pwd && rg --files -g 'gdp.csv'
   output

   gdp.csv

4. deft find "sort CSV rows by a column and select top 10 columns"
   output

   sheet sort     sheet -> sheet  Sort rows: --columns age,name --descending
   sheet select   sheet -> sheet  Keep, reorder or --drop columns
   sheet extract  sheet -> sheet  Take a sheet or range: --sheet, --range A1:D20

5. head -n 4 gdp.csv
   output

   Country Name,Country Code,Year,Value
   Afghanistan,AFG,2000,3521418059.923445
   Afghanistan,AFG,2001,2813571753.8725324
   Afghanistan,AFG,2002,3825701438.9996333

6. deft sheet select --help
   output

   deft sheet select - Keep, reorder or --drop columns
   
   Usage: deft sheet select <sheet>... [-o <sheet|dir>] [options]
   In: sheet (each handled separately)   Out: sheet (default <name>.selected.<ext>)
   
   Options:
     --columns <text>             Columns to keep, in this order
     --drop <text>                Columns to remove
     --sheet <text>               Sheet name or number (default: first)
     --to <csv|xlsx|json>         Output format (default: like the input)
   Common: -o --force --dry-run --json -j   (deft help common)
   
   Examples:
     deft sheet select people.csv --columns age,name -o swapped.csv
     deft sheet select people.csv --drop age -o names.csv
   
   Result fields: rows, columns

7. deft sheet sort --help
   output

   deft sheet sort - Sort rows: --columns age,name --descending
   
   Usage: deft sheet sort <sheet>... [-o <sheet|dir>] [options]
   In: sheet (each handled separately)   Out: sheet (default <name>.sorted.<ext>)
   Numbers sort as numbers; empty cells go last.
   
   Options:
     --columns <text>             Column names or numbers, comma-separated (required)
     --descending                 Largest first
     --sheet <text>               Sheet name or number (default: first)
     --to <csv|xlsx|json>         Output format (default: like the input)
   Common: -o --force --dry-run --json -j   (deft help common)
   
   Examples:
     deft sheet sort people.csv --columns age --descending -o ranked.csv
   
   Result fields: rows, columns

8. deft find "filter CSV rows where a column equals a value"
   output

   sheet filter  sheet -> sheet  Keep matching rows: --where "age > 30 and city = 'Oslo'"

9. The file has a `Year` column and numeric `Value` data. I’m filtering to 2015, sorting by `Value` descending, then selecting the requested two columns for the output.

10. deft sheet filter gdp.csv --where "Year = 2015" -o <tmp> && deft sheet sort <tmp> --columns Value --descending -o <tmp> && deft sheet extract <tmp> --range A1:D11 -o <tmp> && deft sheet select <tmp> --columns "Country Name,Value" -o top.csv
    output

    ok sheet.filter gdp.csv -> <tmp>  258 rows x 4 columns  0.01s
    ok sheet.sort <tmp> -> <tmp>  258 rows x 4 columns  0.00s
    ok sheet.extract <tmp> -> <tmp>  11 rows x 4 columns  0.00s
    ok sheet.select <tmp> -> top.csv  10 rows x 2 columns  0.00s

11. cat top.csv
    output

    Country Name,Value
    World,75359657218242.52
    High income,49773105280474.15
    OECD members,47536673280840.75
    Post-demographic dividend,44669765037594.52
    IDA & IBRD total,27987288576613.15
    IBRD only,25838353087075.664
    Low & middle income,25326526306958.895
    Middle income,24911694910932.1
    East Asia & Pacific,21995274219766.668
    Europe & Central Asia,20481460301210.54

12. Created [top.csv](top.csv) with the ten highest 2015 `Value` rows and the requested columns.

Output

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

Time

16s

New tokens

13.3k

Total input

79.7k

Output tokens

1.3k

Commands

0

Failed

0

Trace

Output

---
name: deft
description: "Use deft first for any simple, direct operation on local files, whatever the type: create, convert, read, query, 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