Sample frames from a point

Starting at 4 seconds into bunny.mp4, save one frame every 2 seconds into a folder called frames.

The task

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

deft video frames bunny.mp4 --from 4 --interval 2 -o frames/

Input

bunny.mp4 946.5 KB · h264 1280x720, 10.0s

Reference output

frames/bunny-0001.jpg 234.8 KB · 1280x720

frames/bunny-0002.jpg 235.9 KB · 1280x720

frames/bunny-0003.jpg 239.4 KB · 1280x720

How a result is judged (1 check)

count_files: glob = "frames/*", min = 3, max = 4

Runs

CodexWithout deftPassed2026-11-07

Time: 12s
New tokens: 6.0k
Total input: 53.9k
Output tokens: 0.4k
Commands: 3
Failed: 0

Trace

I’ll inspect the video and available frame extraction tools, then save frames from 4 seconds onward at 2 second intervals in `frames/`.

ls -la && command -v ffmpeg || true && command -v python3 || true

output

total 1896
drwxr-xr-x@    3 user  staff      96 Nov  6 17:29 .
drwx------@ 1750 user  staff   56000 Nov  6 17:29 ..
-rw-r--r--@    1 user  staff  969201 Nov  5 21:11 bunny.mp4
/opt/homebrew/bin/ffmpeg
/usr/local/bin/python3

ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 bunny.mp4
output
```
10.000000
```
The video is 10 seconds long, so I’m extracting at 4, 6, 8, and 10 seconds (the final timestamp resolves to the last available frame).

mkdir -p frames && ffmpeg -hide_banner -loglevel error -i bunny.mp4 -vf \"select='gte(t,4)*not(mod(t-4,2))'\" -vsync 0 frames/frame_%03d.jpg && ls -lh frames

output

total 1112
-rw-r--r--@ 1 user  staff   130K Nov  6 17:29 frame_001.jpg
-rw-r--r--@ 1 user  staff   182K Nov  6 17:29 frame_002.jpg
-rw-r--r--@ 1 user  staff   239K Nov  6 17:29 frame_003.jpg

Saved three frames to [frames](<frames>) from the 10-second video. Extraction begins at 4 seconds and continues every 2 seconds; the final available frame is before 10 seconds.

Output

frames/frame_001.jpg 129.6 KB · 1280x720

frames/frame_002.jpg 182.3 KB · 1280x720

frames/frame_003.jpg 239.4 KB · 1280x720

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

Time: 11s
New tokens: 4.4k
Total input: 56.4k
Output tokens: 0.3k
Commands: 3
Failed: 0

Trace

I’ll use the `deft` skill for video frame extraction, then save the frames under `./frames`.

cat .agents/skills/deft/SKILL.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
… 728 more characters

deft video frames --help

output

deft video frames - Save frames as images: --fps 1 or --at 0:05,0:10

Usage: deft video frames <video>... [-o <dir>] [options]
In: video (each handled separately)   Out: png|jpg files in <name>-frames/

Options:
  --fps <number>               Frames per second
  --interval <time>            Time between frames, such as 2 or 0:30
  --from <time>                Start time for --fps or --interval (default 0)
  --at <times>                 Exact times
  --to <png|jpg>               Image format (default jpg)
Common: -o --force --dry-run --json -j   (deft help common)

Examples:
  deft video frames clip.mp4 --at 0:01 -o shots/
  deft video frames clip.mp4 --fps 1 --to png -o frames/
  deft video frames clip.mp4 --from 1 --interval 2 -o frames/

Result fields: files
Needs: ffmpeg, ffprobe

deft video frames bunny.mp4 --from 4 --interval 2 -o frames
output
```
ok video.frames bunny.mp4 -> frames/  3 frames  0.19s
```
Saved 3 frames from `bunny.mp4` to the `frames` folder, starting at 4 seconds and spaced 2 seconds apart.

Output

frames/bunny-0001.jpg 101.8 KB · 1280x720

frames/bunny-0002.jpg 130.9 KB · 1280x720

frames/bunny-0003.jpg 245.3 KB · 1280x720

Claude Opus 5.5Without deftPassed2026-11-07

Time: 15s
New tokens: 8.9k
Total input: 42.0k
Output tokens: 0.7k
Commands: 0
Failed: 0

Trace

Output

frames/frame_001.png 2.0 MB · 1280x720

frames/frame_002.png 2.0 MB · 1280x720

frames/frame_003.png 2.0 MB · 1280x720

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

Time: 17s
New tokens: 10.3k
Total input: 75.3k
Output tokens: 0.6k
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

frames/bunny-0001.jpg 234.8 KB · 1280x720

frames/bunny-0002.jpg 235.9 KB · 1280x720

frames/bunny-0003.jpg 239.4 KB · 1280x720

Claude CodeWithout deftNot run yet

Claude CodeWith deftNot run yet