Filter rows

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

Time

19s

New tokens

9.2k

Total input

101.1k

Output tokens

0.6k

Commands

6

Failed

0

Trace

1. I’ll inspect the CSV and write the China rows with the original header to `china.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. deft find "filter CSV rows by a column value"
   output

   sheet filter     sheet -> sheet   Keep matching rows: --where "age > 30 and city = 'Oslo'"
   sheet pivot      sheet -> sheet   Pivot table: --rows city --columns year --values sales
   sheet info       sheet -> report  Sheet names, rows, columns
   sheet transpose  sheet -> sheet   Swap rows and columns
   sheet stats      sheet -> report  Per-column counts, empties, min, max, mean, sum

4. rg --files -g 'gdp.csv' -g '*.csv'
   output

   gdp.csv

5. deft sheet filter --help
   output

   deft sheet filter - Keep matching rows: --where "age > 30 and city = 'Oslo'"
   
   Usage: deft sheet filter <sheet>... [-o <sheet|dir>] [options]
   In: sheet (each handled separately)   Out: sheet (default <name>.filtered.<ext>)
   Compare with = != < <= > >=, contains, startswith, endswith, in (a, b), ~ 'regex'.
   Join with and, or, not, parentheses. Also: col is empty, col is not empty.
   Text comparison ignores case. Quote names with spaces: `Unit price` > 3.
   
   Options:
     --where <text>               Condition on columns (required)
     --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 filter people.csv --where 'age > 30' -o older.csv
     deft sheet filter people.xlsx --where "name in (Ada, Sam)" --to csv -o some.csv
   
   Result fields: rows, columns

6. head -n 3 gdp.csv
   output

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

7. deft sheet filter gdp.csv --where \"'Country Name' = 'China'\" -o china.csv
   output

   ok sheet.filter gdp.csv -> china.csv  64 rows x 4 columns  0.01s

8. Saved the 64 China rows, including the header, to [china.csv](china.csv).

Output

CodexWith deft, skill as AGENTS.mdPassed2026-11-05

Time

16s

New tokens

6.2k

Total input

61.7k

Output tokens

0.6k

Commands

3

Failed

0

Trace

1. I’ll inspect the CSV header and country column, then write `china.csv` in the current directory with the header preserved.

2. ls -la && head -n 5 gdp.csv
   output

   total 1112
   drwxr-xr-x@    4 user  staff     128 Nov  4 20:03 .
   drwx------@ 3397 user  staff  108704 Nov  4 20:03 ..
   -rw-r--r--@    1 user  staff    1486 Nov  4 20:03 AGENTS.md
   -rw-r--r--@    1 user  staff  562767 Nov  4 19:32 gdp.csv
   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

3. deft sheet
   output

   deft sheet - commands (input -> output)
     info     sheet -> report    Sheet names, rows, columns
     convert  sheet -> sheet     Change format: --to csv|xlsx|json
     extract  sheet -> sheet     Take a sheet or range: --sheet, --range A1:D20
     merge    sheet... -> sheet  Stack tables; a shared header is kept once
     to-md    sheet -> md        Markdown table (first row is the header)
   More: deft sheet <command> --help

4. python3 -c 'import csv; src=\"gdp.csv\"; dst=\"china.csv\"; f=open(src,newline=\"\",encoding=\"utf-8\"); reader=csv.DictReader(f); out=open(dst,\"w\",newline=\"\",encoding=\"utf-8\"); writer=csv.DictWriter(out,fieldnames=reader.fieldnames); writer.writeheader(); n=0 for row in reader: if row[\"Country Name\"] == \"China\": writer.writerow(row); n+=1 out.close(); f.close(); print(f\"Wrote {n} China rows with header to {dst}\")' && head -n 5 china.csv && wc -l china.csv
   output

   Wrote 64 China rows with header to china.csv
   Country Name,Country Code,Year,Value
   China,CHN,1960,59716249310.97416
   China,CHN,1961,50056685957.35899
   China,CHN,1962,47209186415.35554
   China,CHN,1963,50706614526.14723
         65 china.csv

5. Saved [china.csv](china.csv) with the header and 64 China rows.

Output

Its files were not kept in this run. The last line of the trace is its own report.

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

Time

37s

New tokens

12.2k

Total input

111.8k

Output tokens

1.2k

Commands

0

Failed

0

Trace

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, 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