Read LibreOffice and old Excel files

Convert the first sheet of issues.ods to ods.csv and the first sheet of issues.xls to xls.csv.

The task

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

deft sheet convert issues.ods --to csv -o ods.csv
deft sheet convert issues.xls --to csv -o xls.csv

Input

issues.ods 4.0 KB

[content.xml] 1 1.5 ab FALSE test 10/20/2016 0 1 a 2 b 3 c 1 1 2 ab FALSE & < > aaa ' aaa " ☺ ֍ àâéêèçöïî«»

issues.xls 38.0 KB

No preview for this format. Open the file to read it.

Reference output

ods.csv 40 B

1
1.5
ab
false
test
2016-10-20T00:00:00

xls.csv 31 B

1
1.5
ab
false
test
2016-10-20

How a result is judged (2 checks)

csv: file = "ods.csv", rows = 6
csv: file = "xls.csv", rows = 6

Runs

CodexWithout deftPassed2026-11-07

Time: 113s
New tokens: 38.5k
Total input: 413.5k
Output tokens: 4.1k
Commands: 20
Failed: 2

Trace

I’ll convert each workbook’s first sheet to a CSV in the current directory, preserving the input files.

ls -la

output

total 88
drwxr-xr-x@    4 user  staff    128 Nov  6 17:25 .
drwx------@ 1750 user  staff  56000 Nov  6 17:25 ..
-rw-r--r--@    1 user  staff   4095 Nov  5 21:11 issues.ods
-rw-r--r--@    1 user  staff  38912 Nov  5 21:11 issues.xls

python3 - <<'PY' import importlib.util for m in ['pandas','odf','xlrd','openpyxl']: print(m, bool(importlib.util.find_spec(m))) PY
output
```
pandas True
odf False
xlrd False
openpyxl False
```
command -v libreoffice || command -v soffice || command -v ssconvert || python3 - <<'PY' import pandas as pd print(pd.__version__) PY
output
```
3.0.2
```

python3 - <<'PY'
import importlib.util
for m in ['pyexcel','pyxlsb','olefile','pyoo','odfpy','ezodf','formulas','calamine']:
 print(m, bool(importlib.util.find_spec(m)))
PY
file issues.ods issues.xls

output

pyexcel False
pyxlsb False
olefile False
pyoo False
odfpy False
ezodf False
formulas False
calamine False
issues.ods: OpenDocument Spreadsheet
issues.xls: Composite Document File V2 Document, Little Endian, Os: Windows, Version 6.1, Code page: 1252, Author: Johann Tuffe (jtuffe010814), Last Saved By: Johann Tuffe (jtuffe010814), Name of Creating Application: Microsoft Excel, Create Time/Date: Tue Oct 18 11:19:50 2016, Last Saved Time/Date: Wed Apr 19 07:56:48 2017, Security: 0

which xls2csv in2csv python3 R java; python3 - <<'PY' import pkgutil print([m.name for m in pkgutil.iter_modules() if any(s in m.name.lower() for s in ['xls','excel','sheet','ole','odf'])]) PY
output
```
xls2csv not found
in2csv not found
/usr/local/bin/python3
R not found
/usr/bin/java
[]
```

ls /Applications

output

Adobe Acrobat DC
Agent Home.app
Anaconda-Navigator.app
AppFlowy.app
BaiduNetdisk_mac.app
Blender.app
Canon Utilities
CapCut.app
ChatGPT.app
Cisco Webex Meetings.app
ClashX.app
Claude.app
Cursor.app
Discord.app
Docker.app
GarageBand.app
GeForceNOW.app
Google Chrome.app
Google Docs.app
Google Drive.app
Google Sheets.app
Google Slides.app
Insta360 Studio.app
IntelliJ IDEA Edu.app
Keynote.app
Kindle.app
League of Legends.app
Microsoft Outlook.app
Mobalytics Desktop.app
Numbers.app
Pages.app
Python 3.12
Riot Client ().app
Safari.app
Steam.app
Sublime Text.app
TeX
Telegram.app
Tor Browser.app
Transcribe.app
Utilities
VideoFusion-macOS.app
Visual Studio Code.app
Warp.app
WeChat.app
iMovie.app
iTerm.app
zoom.us.app

osascript -e 'tell application \"Numbers\" to get version' (exit 1)

output

2026-11-06 17:26:11.687 osascript[97519:6540042] Connection Invalid error for service com.apple.hiservices-xpcservice.
2026-11-06 17:26:11.687 osascript[97519:6540041] Error received in message reply handler: Connection invalid
34:41: execution error: Can’t get application "Numbers". (-1728)

python3 -m pip cache list | head -30; find /Applications -iname '*libreoffice*' -o -iname '*numbers*' | head

output

No locally built wheels cached.
/Applications/TeX/TeX Live Utility.app/Contents/Frameworks/Python.framework/Versions/3.9/lib/python3.9/ctypes/test/test_numbers.py
/Applications/TeX/TeX Live Utility.app/Contents/Frameworks/Python.framework/Versions/3.9/lib/python3.9/test/test_abstract_numbers.py
/Applications/TeX/TeX Live Utility.app/Contents/Frameworks/Python.framework/Versions/3.9/lib/python3.9/__pycache__/numbers.cpython-39.pyc
/Applications/TeX/TeX Live Utility.app/Contents/Frameworks/Python.framework/Versions/3.9/lib/python3.9/numbers.py
/Applications/Numbers.app
/Applications/Numbers.app/Contents/MacOS/Numbers
/Applications/Numbers.app/Contents/Resources/de.lproj/NumbersUndo.strings
/Applications/Numbers.app/Contents/Resources/de.lproj/Numbers.stringsdict
/Applications/Numbers.app/Contents/Resources/de.lproj/Numbers.strings
/Applications/Numbers.app/Contents/Resources/de.lproj/NumbersTouchBar.strings

open -a Numbers issues.xls (exit 1)

output

Unable to find application named 'Numbers'

python3 - <<'PY'
import zipfile
z=zipfile.ZipFile('issues.ods')
print(z.namelist())
print(z.read('content.xml').decode()[:10000])
PY

output

['mimetype', 'styles.xml', 'content.xml', 'META-INF/manifest.xml', 'meta.xml']
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<office:document-content xmlns:table="urn:oasis:names:tc:opendocument:xmlns:table:1.0" xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:number="urn:oasis:names:tc:opendocument:xmlns:datastyle:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:of="urn:oasis:names:tc:opendocument:xmlns:of:1.2" office:version="1.2"><office:font-face-decls><style:font-face style:name="Calibri" svg:font-family="Calibri"/><style:font-face style:name="U2400" svg:font-family="U2400"/><style:font-face style:name="U0400" svg:font-family="U0400"/></office:font-face-decls><office:automatic-styles><style:style style:name="ce1" style:family="table-cell" style:parent-style-name="Default" style:data-style-name="N0"/><style:style style:name="ce2" style:family="table-cell" style:parent-style-name="Default" style:data-style-name="N19"/><style:style style:name="ce3" style:family="table-cell" style:parent-style-name="Default" style:data-style-name="N1"/><style:style style:name="ce4" style:famil
… 8579 more characters

command -v php ruby perl; find /usr/local /opt/homebrew -iname '*xlrd*' -o -iname '*spreadsheet*' 2>/dev/null | head -30

output

/usr/bin/ruby
/usr/bin/perl
/usr/local/texlive/2022/texmf-dist/tex/context/interface/mkiv/i-spreadsheet.xml
/usr/local/texlive/2022/texmf-dist/tex/context/modules/mkiv/m-spreadsheet.lua
/usr/local/texlive/2022/texmf-dist/tex/context/modules/mkiv/m-spreadsheet.mkiv
/usr/local/texlive/2022/texmf-dist/doc/context/sources/general/manuals/spreadsheets
/usr/local/texlive/2022/texmf-dist/doc/context/sources/general/manuals/spreadsheets/spreadsheets-mkiv.tex
/usr/local/texlive/2022/texmf-dist/doc/context/documents/general/manuals/spreadsheets-mkiv.pdf

perl -MSpreadsheet::ParseExcel -e 'print \"yes\"' 2>&1; ruby -e 'begin; require \"roo\"; puts \"yes\"; rescue LoadError; puts \"no\"; end'

output

Can't locate Spreadsheet/ParseExcel.pm in @INC (you may need to install the Spreadsheet::ParseExcel module) (@INC contains: /Library/Perl/5.34/darwin-thread-multi-2level /Library/Perl/5.34 /Network/Library/Perl/5.34/darwin-thread-multi-2level /Network/Library/Perl/5.34 /Library/Perl/Updates/5.34.1 /System/Library/Perl/5.34/darwin-thread-multi-2level /System/Library/Perl/5.34 /System/Library/Perl/Extras/5.34/darwin-thread-multi-2level /System/Library/Perl/Extras/5.34).
BEGIN failed--compilation aborted.
no

python3 - <<'PY' import zipfile, xml.etree.ElementTree as E, csv z=zipfile.ZipFile('issues.ods'); root=E.fromstring(z.read('content.xml')) ns={'table':'urn:oasis:names:tc:opendocument:xmlns:table:1.0','text':'urn:oasis:names:tc:opendocument:xmlns:text:1.0','office':'urn:oasis:names:tc:opendocument:xmlns:office:1.0'} tab=root.find('.//table:table',ns) rows=[] for row in tab.findall('table:table-row',ns): vals=[] for cell in row.findall('table:table-cell',ns): rep=int(cell.get('{%s}number-columns-repeated'%ns['table'],'1')) val=cell.get('{%s}value'%ns['office']) typ=cell.get('{%s}value-type'%ns['office']) if typ=='boolean': val=cell.get('{%s}boolean-value'%ns['office']).upper() elif typ in ('string','date','time') or val is None: ps=cell.findall('text:p',ns) val='\\n'.join(''.join(p.itertext()) for p in ps) if ps else '' elif typ=='float': v=float(val); val=str(int(v)) if v.is_integer() else str(v) vals.extend([val]*min(rep,20000)) # trim trailing blanks while vals and vals[-1]=='': vals.pop() if vals: rows.append(vals) with open('ods.csv','w',newline='',encoding='utf-8') as f: csv.writer(f).writerows(rows) print(rows) PY
output
```
[['1'], ['1.5'], ['ab'], ['FALSE'], ['test'], ['10/20/2016']]
```
python3 - <<'PY' import struct b=open('issues.xls','rb').read(); print(len(b), b[:8].hex()); print(struct.unpack_from('<H',b,30),struct.unpack_from('<H',b,32),struct.unpack_from('<I',b,44)) PY
output
```
38912 d0cf11e0a1b11ae1
(9,) (6,) (1,)
```
python3 - <<'PY' import struct b=open('issues.xls','rb').read(); ss=1<<struct.unpack_from('<H',b,30)[0]; nfat=struct.unpack_from('<I',b,44)[0] difat=list(struct.unpack_from('<109I',b,76)); difat=[x for x in difat if x<0xfffffffa] fat=[] for sid in difat[:nfat]: fat.extend(struct.unpack_from('<%dI'%(ss//4),b,(sid+1)*ss)) def chain(s): out=[]; seen=set() while s<0xfffffffa and s not in seen: seen.add(s); out.append(b[(s+1)*ss:(s+2)*ss]); s=fat[s] return b''.join(out) d=chain(struct.unpack_from('<I',b,48)[0]); for i in range(0,len(d),128): r=d[i:i+128]; n=struct.unpack_from('<H',r,64)[0]; if n: print(r[:n-2].decode('utf-16le'),r[66],struct.unpack_from('<I',r,116)[0],struct.unpack_from('<I',r,120)[0]) PY
output
```
Root Entry 5 42 14016
Workbook 2 2 19171
_VBA_PROJECT_CUR 1 0 0
VBA 1 0 0
ThisWorkbook 2 0 1158
__SRP_2 2 19 352
__SRP_3 2 25 66
Sheet1 2 27 977
Sheet2 2 43 977
Sheet3 2 59 977
Sheet4 2 75 977
testVBA 2 91 1016
__SRP_4 2 107 84
__SRP_5 2 109 103
_VBA_PROJECT 2 111 3017
dir 2 159 623
__SRP_0 2 169 1424
__SRP_1 2 192 126
PROJECTwm 2 194 149
PROJECT 2 197 615
SummaryInformation 2 207 248
DocumentSummaryInformation 2 211 364
CompObj 2 217 107
```
cat > <tmp> <<'PY' import struct b=open('issues.xls','rb').read(); ss=1<<struct.unpack_from('<H',b,30)[0]; nf=struct.unpack_from('<I',b,44)[0] difat=[x for x in struct.unpack_from('<109I',b,76) if x<0xfffffffa]; fat=[] for sid in difat[:nf]: fat+=struct.unpack_from('<%dI'%(ss//4),b,(sid+1)*ss) def chain(s): out=[]; seen=set() while s<0xfffffffa and s not in seen: seen.add(s);out.append(b[(s+1)*ss:(s+2)*ss]);s=fat[s] return b''.join(out) d=chain(struct.unpack_from('<I',b,48)[0]); entries=[] for i in range(0,len(d),128): r=d[i:i+128]; n=struct.unpack_from('<H',r,64)[0] if n: entries.append((r[:n-2].decode('utf-16le'),r[66],struct.unpack_from('<I',r,116)[0],struct.unpack_from('<I',r,120)[0])) w=chain(next(e[2] for e in entries if e[0]=='Workbook')) pos=0 while pos+4<=len(w): rid,n=struct.unpack_from('<HH',w,pos); dat=w[pos+4:pos+4+n] if rid in (0x0809,0x000a,0x0085,0x00fc,0x00fd,0x0203,0x027e,0x0204,0x0205,0x0006,0x0001): print(hex(pos),hex(rid),n,dat[:40].hex()) pos+=4+n if rid==0x000a: break PY python3 <tmp>
output
```
0x0 0x809 16 00060500b143cd07c900020006080000
0x2df2 0x85 17 ca2f000000000900646174617479706573
0x2e07 0x85 14 a532000000000600536865657431
0x2e19 0x85 14 8234000000000600697373756532
0x2e2b 0x85 14 b736000000000600697373756535
0x2e3d 0x85 14 3c48000000000600697373756536
0x2f23 0xfc 27 040000000400000001000061010000620100006304000074657374
0x2fc6 0xa 0
```

cat >> <tmp> <<'PY'
print('SHEET')
pos=struct.unpack_from('<I', next(w[p+4:p+21] for p in range(0x2df2,0x2e07,4) if False))[0] if False else 0x2fca
while pos+4<=len(w):
 rid,n=struct.unpack_from('<HH',w,pos); dat=w[pos+4:pos+4+n]
 print(hex(pos),hex(rid),n,dat[:60].hex())
 pos+=4+n
 if rid==0xa:break
PY
python3 <tmp> | tail -30

output

0x3060 0x26 8 666666666666e63f
0x306c 0x27 8 666666666666e63f
0x3078 0x28 8 000000000000e83f
0x3084 0x29 8 000000000000e83f
0x3090 0xa1 34 00002c0101000100010004000615f47f333333333333d33f333333333333d33f0000
0x30b6 0x89c 38 9c0800000000000000000000000000000000000000000000000000003c330000000000000000
0x30e0 0x55 2 0800
0x30e6 0x7d 12 00000000b60a0f0006000000
0x30f6 0x200 14 0000000006000000000001000000
0x3108 0x208 16 0000000001002c010000000000010f00
0x311c 0x208 16 0100000001002c010000000000010f00
0x3130 0x208 16 0200000001002c010000000000010f00
0x3144 0x208 16 0300000001002c010000000000010f00
0x3158 0x208 16 0400000001002c010000000000010f00
0x316c 0x208 16 0500000001002c010000000000010f00
0x3180 0x27e 10 000000000f000000f03f
0x318e 0x27e 10 010000000f000000f83f
0x319c 0x6 34 020000000f00000000000000ffff0000000000fd0c00170100611701006242025001
0x31c2 0x207 5 0200006162
0x31cb 0x6 33 030000000f00010000000000ffff0000020000fe0b0044000000c044010000c00d
0x31f0 0xfd 10 040000000f0003000000
0x31fe 0x27e 10 050000003f00e0d4e440
0x320c 0xd7 16 0401000064000e000e002f0025000e00
0x3220 0x1c2 24 03000200050009000000e0d40200030001000900000000fe
0x323c 0x23e 18 b60000000000400000000000000003000000
0x3252 0x88b 16 8b080000000000000000000000000200
0x3266 0x1d 15 032700040000000100270027000404
0x3279 0x1ba 9 060000536865657431
0x3286 0x867 23 670800000000000000000000020001ffffffff03440000
0x32a1 0xa 0

python3 <tmp> | grep -E 'SHEET|0x2f|0x30|0x31' | head -45

output

0x2f23 0xfc 27 040000000400000001000061010000620100006304000074657374
0x2fc6 0xa 0 
SHEET
0x2fca 0x809 16 00061000b143cd07c900020006080000
0x2fde 0x20b 20 000000000000000006000000e03000000c320000
0x2ff6 0xd 2 0100
0x2ffc 0xc 2 6400
0x3002 0xf 2 0100
0x3008 0x11 2 0000
0x300e 0x10 8 fca9f1d24d62503f
0x301a 0x5f 2 0100
0x3020 0x2a 2 0000
0x3026 0x2b 2 0000
0x302c 0x82 2 0100
0x3032 0x80 8 0000000000000000
0x303e 0x225 4 00002c01
0x3046 0x81 2 c104
0x304c 0x14 0 
0x3050 0x15 0 
0x3054 0x83 2 0000
0x305a 0x84 2 0000
0x3060 0x26 8 666666666666e63f
0x306c 0x27 8 666666666666e63f
0x3078 0x28 8 000000000000e83f
0x3084 0x29 8 000000000000e83f
0x3090 0xa1 34 00002c0101000100010004000615f47f333333333333d33f333333333333d33f0000
0x30b6 0x89c 38 9c0800000000000000000000000000000000000000000000000000003c330000000000000000
0x30e0 0x55 2 0800
0x30e6 0x7d 12 00000000b60a0f0006000000
0x30f6 0x200 14 0000000006000000000001000000
0x3108 0x208 16 0000000001002c010000000000010f00
0x311c 0x208 16 0100000001002c010000000000010f00
0x3130 0x208 16 0200000001002c010000000000010f00
0x3144 0x208 16 0300000001002c010000000000010f00
0x3158 0x208 16 0400000001002c010000000000010f00
0x316c 0x208 16 0500000001002c010000000000010f00
0x3180 0x27e 10 000000000f000000f03f
0x318e 0x27e 10 010000000f000000f83f
0x319c 0x6 34 020000000f00000000000000ffff0000000000fd0c00170100611701006242025001
0x31c2 0x207 5 0200006162
0x31cb 0x6 33 030000000f00010000000000ffff0000020000fe0b0044000000c044010000c00d
0x31f0 0xfd 10 0400
… 53 more characters

python3 - <<'PY' import csv rows=[['1'],['1.5'],['ab'],['FALSE'],['test'],['2016-10-20']] with open('xls.csv','w',newline='',encoding='utf-8') as f: csv.writer(f).writerows(rows) PY ls -l ods.csv xls.csv && cat ods.csv && cat xls.csv
output
```
-rw-r--r--@ 1 user  staff  37 Nov  6 17:26 ods.csv
-rw-r--r--@ 1 user  staff  37 Nov  6 17:27 xls.csv
1
1.5
ab
FALSE
test
10/20/2016
1
1.5
ab
FALSE
test
2016-10-20
```
Created [ods.csv](ods.csv) and [xls.csv](xls.csv) from the first sheet of each workbook.

Output

ods.csv 37 B

1
1.5
ab
FALSE
test
10/20/2016

xls.csv 37 B

1
1.5
ab
FALSE
test
2016-10-20

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

Time: 17s
New tokens: 5.4k
Total input: 71.9k
Output tokens: 0.6k
Commands: 5
Failed: 0

Trace

I’ll check the available file-conversion instructions, then convert each workbook’s first sheet into its requested CSV in the current directory.

cat .agents/skills/deft/SKILL.md && rg --files -g 'issues.ods' -g 'issues.xls' -g 'AGENTS.md' -g 'deft*' .

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
… 754 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 extract --help

output

deft sheet extract - Take a sheet or range: --sheet, --range A1:D20

Usage: deft sheet extract <sheet>... [-o <sheet|dir>] [options]
In: sheet (each handled separately)   Out: sheet (default <name>.extract.<ext>)

Options:
  --sheet <text>               Sheet name or number (default: first)
  --range <text>               Cell range, e.g. B2:D10
  --to <csv|xlsx|json>         Output format (default csv)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft sheet extract people.xlsx --range A1:B2 -o part.csv
  deft sheet extract people.csv --range A1:A3 --to json -o names.json

Result fields: rows, columns

deft sheet extract issues.xls --sheet 1 -o xls.csv

output

ok sheet.extract issues.xls -> xls.csv  6 rows x 1 columns  0.00s

deft sheet extract issues.ods --sheet 1 -o ods.csv

output

ok sheet.extract issues.ods -> ods.csv  6 rows x 1 columns  0.00s

Converted the first sheet of each workbook: [ods.csv](ods.csv) and [xls.csv](xls.csv). Each contains 6 rows and 1 column.

Output

ods.csv 40 B

1
1.5
ab
false
test
2016-10-20T00:00:00

xls.csv 31 B

1
1.5
ab
false
test
2016-10-20

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

Time: 14s
New tokens: 5.8k
Total input: 61.3k
Output tokens: 0.4k
Commands: 3
Failed: 0

Trace

I’ll use the local `deft` spreadsheet conversion commands and save both CSVs in the current directory.

deft sheet --help && rg --files -g 'issues.ods' -g 'issues.xls' -g 'deft*' .

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
./issues.xls
./issues.ods

deft sheet convert --help

output

deft sheet convert - Change format: --to csv|xlsx|json
Same as: deft convert

Usage: deft sheet convert <sheet>... [-o <sheet|dir>] [options]
In: sheet (each handled separately)   Out: sheet (default <name>.<ext>)
JSON is an array of objects keyed by the first row.

Options:
  --to <csv|xlsx|json>         Target format (or give -o name.ext)
  --sheet <text>               Sheet name or number (default: first)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft sheet convert people.csv --to xlsx -o table.xlsx
  deft sheet convert people.xlsx --to json -o people.json

Result fields: rows, columns

deft sheet convert issues.ods -o ods.csv --sheet 1 && deft sheet convert issues.xls -o xls.csv --sheet 1 && ls -l ods.csv xls.csv

output

ok sheet.convert issues.ods -> ods.csv  6 rows x 1 columns  0.00s
ok sheet.convert issues.xls -> xls.csv  6 rows x 1 columns  0.00s
-rw-r--r--@ 1 user  staff  40 Nov  4 20:04 ods.csv
-rw-r--r--@ 1 user  staff  31 Nov  4 20:04 xls.csv

Converted the first sheet of each file in the current directory: - `issues.ods` → [ods.csv](ods.csv) - `issues.xls` → [xls.csv](xls.csv) Both conversions completed successfully.

Output

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

Claude Opus 5.5Without deftPassed2026-11-07

Time: 32s
New tokens: 18.4k
Total input: 106.7k
Output tokens: 2.9k
Commands: 0
Failed: 0

Trace

Output

ods.csv 37 B

1
1.5
ab
FALSE
test
10/20/2016

xls.csv 37 B

1
1.5
ab
FALSE
test
10/20/2016

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

Time: 14s
New tokens: 10.3k
Total input: 59.6k
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

ods.csv 40 B

1
1.5
ab
false
test
2016-10-20T00:00:00

xls.csv 31 B

1
1.5
ab
false
test
2016-10-20

Claude CodeWithout deftNot run yet

Claude CodeWith deftNot run yet