SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add benchflow-ai/skillsbench --skill ffmpeg-format-conversiongit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-format-conversion)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-format-conversion"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-format-conversion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-format-conversion"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-format-conversion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00921 |
| Opus 5 | $0.00011 | $0.00461 |
| Sonnet 5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
ffmpeg-format-conversion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- FFmpeg Format Conversion — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFmpeg Format Conversion Skill
Convert media files between different formats and containers.
When to Use
- Convert video containers (MP4, MKV, AVI, etc.)
- Convert audio formats (MP3, AAC, WAV, etc.)
- Transcode to different codecs
- Copy streams without re-encoding (fast)
Basic Conversion
# Convert container format (re-encode)
ffmpeg -i input.avi output.mp4
# Copy streams without re-encoding (fast, no quality loss)
ffmpeg -i input.mp4 -c copy output.mkv
# Convert with specific codec
ffmpeg -i input.mp4 -c:v libx264 -c:a aac output.mp4
Video Codec Conversion
# H.264
ffmpeg -i input.mp4 -c:v libx264 output.mp4
# H.265 (better compression)
ffmpeg -i input.mp4 -c:v libx265 output.mp4
# VP9 (web optimized)
ffmpeg -i input.mp4 -c:v libvpx-vp9 output.webm
# AV1 (modern codec)
ffmpeg -i input.mp4 -c:v libaom-av1 output.mp4
Audio Format Conversion
# MP3
ffmpeg -i input.wav -acodec libmp3lame -q:a 2 output.mp3
# AAC
ffmpeg -i input.wav -c:a aac -b:a 192k output.m4a
# Opus (best quality/bitrate)
ffmpeg -i input.wav -c:a libopus -b:a 128k output.opus
# FLAC (lossless)
ffmpeg -i input.wav -c:a flac output.flac
Quality Settings
# CRF (Constant Rate Factor) - lower is better quality
ffmpeg -i input.mp4 -c:v libx264 -crf 23 output.mp4
# Bitrate
ffmpeg -i input.mp4 -b:v 2M -b:a 192k output.mp4
# Two-pass encoding (best quality)
ffmpeg -i input.mp4 -c:v libx264 -b:v 2M -pass 1 -f null /dev/null
ffmpeg -i input.mp4 -c:v libx264 -b:v 2M -pass 2 output.mp4
Presets
# Encoding speed presets (faster = larger file)
ffmpeg -i input.mp4 -c:v libx264 -preset fast output.mp4
# Options: ultrafast, superfast, veryfast, faster, fast, medium, slow, slower, veryslow
# Quality presets
ffmpeg -i input.mp4 -c:v libx264 -preset slow -crf 18 output.mp4
Batch Conversion
# Convert all MKV to MP4
for f in *.mkv; do
ffmpeg -i "$f" -c copy "${f%.mkv}.mp4"
done
# Convert with re-encoding
for f in *.avi; do
ffmpeg -i "$f" -c:v libx264 -c:a aac "${f%.avi}.mp4"
done
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 121 lines · 22 tokens per session scan A 6fcdc408c24f
ffmpeg-format-conversion is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 921 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
opencv-template-matching
Use OpenCV for image processing, grayscale conversion, and template matching to detect objects in images.
exploded-view-illustration
Techniques for drawing isometric or orthographic exploded-view hardware diagrams programmatically using Pillow, with annotation leader lines and layer separation.
python-pillow-graphics
Create technical graphics, diagrams, and posters using Python Pillow library with precise color control and typography.
chinese-classical-poetry
A guide to writing a seven-character regulated poem in Classical Chinese, a traditional form with eight lines of seven Chinese characters each. It explains the required couplets, tone patterns, and rhymes.
image-generation-pillow
Technical image generation using Python's Pillow library. Use this when you need to programmatically create diagrams, posters, or technical drawings.
pillow-technical-drawing
Creating technical diagrams and exploded-view illustrations using Python Pillow with geometric primitives and text annotations.