Evals / tables / Format conversion
Table for a report
Turn temperature.xlsx into a Markdown table in table.md.
The task
The reference answer shows the job can be done with deft. It is not an agent run.
deft sheet to-md temperature.xlsx -o table.md
Input
Reference output
| label | value | | --- | --- | | celsius | 22.2222 | | fahrenheit | 72 |
How a result is judged (1 check)
- text: file = "table.md", contains = ["|", "---"]
Runs
CodexWithout deftPassed2026-11-07
- Time
- 20s
- New tokens
- 6.3k
- Total input
- 54.1k
- Output tokens
- 0.5k
- Commands
- 3
- Failed
- 0
Trace
I’ll inspect the workbook sheets and contents, then write the Markdown table to `table.md` in the current directory.
ls -la && python - <<'PY' import importlib.util for x in ['openpyxl','pandas']: print(x, bool(importlib.util.find_spec(x))) PYoutput
total 8 drwxr-xr-x@ 3 user staff 96 Nov 6 17:27 . drwx------@ 1750 user staff 56000 Nov 6 17:27 .. -rw-r--r--@ 1 user staff 3599 Nov 5 21:11 temperature.xlsx openpyxl True pandas True
python - <<'PY' from openpyxl import load_workbook p='temperature.xlsx' w=load_workbook(p, data_only=True, read_only=True) print(w.sheetnames) for s in w: print('\\nSHEET',s.title,s.max_row,s.max_column) for row in s.iter_rows(values_only=True): print(row) PYoutput
['Sheet1'] SHEET Sheet1 None None ('label', 'value') ('celsius', 22.2222) ('fahrenheit', 72.0)python - <<'PY' from openpyxl import load_workbook from pathlib import Path w=load_workbook('temperature.xlsx', data_only=True, read_only=True) s=w.active rows=list(s.iter_rows(values_only=True)) def cell(v): if v is None: return '' return str(v).replace('|', r'\\|').replace('\\n','<br>') lines=['| '+' | '.join(map(cell, rows[0]))+' |','| '+' | '.join(['---']*len(rows[0]))+' |'] lines += ['| '+' | '.join(map(cell,row))+' |' for row in rows[1:]] Path('table.md').write_text('\\n'.join(lines)+'\\n') PY cat table.mdoutput
| label | value | | --- | --- | | celsius | 22.2222 | | fahrenheit | 72.0 |
Created [table.md](table.md) with the worksheet data as a Markdown table.
Output
| label | value | | --- | --- | | celsius | 22.2222 | | fahrenheit | 72.0 |
CodexWith deft, skill installedPassedRead the skillUsed deft2026-11-07
- Time
- 12s
- New tokens
- 4.6k
- Total input
- 56.7k
- Output tokens
- 0.3k
- Commands
- 3
- Failed
- 0
Trace
I’ll use the `deft` skill for this spreadsheet conversion and write the Markdown table to `table.md` in the current directory.
cat .agents/skills/deft/SKILL.md && pwd && rg --files -g 'temperature.xlsx' -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 … 746 more characters
deft sheet --helpoutput
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 to-md --help && deft sheet to-md temperature.xlsx -o table.mdoutput
deft sheet to-md - Markdown table (first row is the header) Same as: deft convert Usage: deft sheet to-md <sheet>... [-o <md|dir>] [options] In: sheet (each handled separately) Out: md (default <name>.<ext>) Options: --sheet <text> Sheet name or number (default: first) Common: -o --force --dry-run --json -j (deft help common) Examples: deft sheet to-md people.csv -o people.md deft sheet to-md people.xlsx -o - Result fields: rows, columns ok sheet.to-md temperature.xlsx -> table.md 3 rows x 2 columns 0.00s
Converted `temperature.xlsx` into [table.md](table.md). The Markdown table contains 3 rows and 2 columns.
Output
| label | value | | --- | --- | | celsius | 22.2222 | | fahrenheit | 72 |
CodexWith deft, skill as AGENTS.mdPassed2026-11-05
- Time
- 10s
- New tokens
- 5.3k
- Total input
- 60.8k
- Output tokens
- 0.2k
- Commands
- 3
- Failed
- 0
Trace
I’ll inspect the workbook and convert its sheet data into a Markdown table in `table.md` in the current directory.
deft sheet --helpoutput
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
deft sheet to-md --helpoutput
deft sheet to-md - Markdown table (first row is the header) Same as: deft convert Usage: deft sheet to-md <sheet>... [-o <md|dir>] [options] In: sheet (each handled separately) Out: md (default <name>.<ext>) Options: --sheet <text> Sheet name or number (default: first) Common: -o --force --dry-run --json -j (deft help common) Examples: deft sheet to-md people.csv -o people.md deft sheet to-md people.xlsx -o - Result fields: rows, columns
deft sheet to-md temperature.xlsx -o table.mdoutput
ok sheet.to-md temperature.xlsx -> table.md 3 rows x 2 columns 0.01s
Converted `temperature.xlsx` into a Markdown table at [table.md](table.md). It contains 3 rows and 2 columns.
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
- 26s
- New tokens
- 10.0k
- Total input
- 71.9k
- Output tokens
- 1.0k
- Commands
- 0
- Failed
- 0
Trace
Output
| label | value | | --- | ---: | | celsius | 22.2222 | | fahrenheit | 72 |
Claude Opus 5.5With deft, skill installedPassedRead the skillUsed deft2026-11-07
- Time
- 15s
- New tokens
- 9.3k
- Total input
- 43.6k
- Output tokens
- 0.3k
- 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
| label | value | | --- | --- | | celsius | 22.2222 | | fahrenheit | 72 |
Claude CodeWithout deftNot run yet
Claude CodeWith deftNot run yet
