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-video-filtersgit 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-video-filters)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/ffmpeg-video-filters"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-video-filters/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-video-filters"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/ffmpeg-video-filters.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 | $0.00023 | $0.01152 |
| Opus 5 | $0.00012 | $0.00576 |
| Sonnet 5 | $0.00005 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
ffmpeg-video-filters 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 9d 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 Video Filters — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFmpeg Video Filters Skill
Apply video filters for scaling, cropping, watermarks, speed changes, and visual effects.
When to Use
- Resize videos
- Crop video frames
- Add watermarks or overlays
- Change playback speed
- Apply blur or other effects
- Adjust brightness/contrast
Scaling
# Scale to 720p (maintain aspect ratio)
ffmpeg -i input.mp4 -vf scale=-2:720 output.mp4
# Scale to specific width (maintain aspect ratio)
ffmpeg -i input.mp4 -vf scale=1280:-2 output.mp4
# Scale to exact dimensions (may distort)
ffmpeg -i input.mp4 -vf scale=1920:1080 output.mp4
# Scale with algorithm
ffmpeg -i input.mp4 -vf scale=1280:720:flags=lanczos output.mp4
Cropping
# Crop to 16:9 from center
ffmpeg -i input.mp4 -vf "crop=1920:1080" output.mp4
# Crop with offset (x:y:width:height)
ffmpeg -i input.mp4 -vf "crop=1920:1080:0:0" output.mp4
# Crop from specific position
ffmpeg -i input.mp4 -vf "crop=800:600:100:50" output.mp4
Watermarks and Overlays
# Add image watermark (top-left)
ffmpeg -i input.mp4 -i logo.png \
-filter_complex "overlay=10:10" output.mp4
# Bottom-right watermark
ffmpeg -i input.mp4 -i logo.png \
-filter_complex "overlay=W-w-10:H-h-10" output.mp4
# Center watermark
ffmpeg -i input.mp4 -i logo.png \
-filter_complex "overlay=(W-w)/2:(H-h)/2" output.mp4
Speed Changes
# Speed up 2x
ffmpeg -i input.mp4 -vf "setpts=0.5*PTS" -af "atempo=2.0" output.mp4
# Slow down 0.5x
ffmpeg -i input.mp4 -vf "setpts=2.0*PTS" -af "atempo=0.5" output.mp4
# Speed up video only (no audio)
ffmpeg -i input.mp4 -vf "setpts=0.5*PTS" -an output.mp4
Blur Effects
# Blur entire video
ffmpeg -i input.mp4 -vf "boxblur=10:5" output.mp4
# Blur specific region (coordinates x:y:w:h)
ffmpeg -i input.mp4 -vf "boxblur=10:5:x=100:y=100:w=200:h=200" output.mp4
# Gaussian blur
ffmpeg -i input.mp4 -vf "gblur=sigma=5" output.mp4
Brightness and Contrast
# Adjust brightness and contrast
ffmpeg -i input.mp4 -vf "eq=brightness=0.1:contrast=1.2" output.mp4
# Increase brightness
ffmpeg -i input.mp4 -vf "eq=brightness=0.2" output.mp4
# Adjust saturation
ffmpeg -i input.mp4 -vf "eq=saturation=1.5" output.mp4
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.
- 9d ago First seen · 148 lines · 23 tokens per session scan A 8881bfa5b935
ffmpeg-video-filters is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,152 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
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
llm-council
Query multiple LLM models in parallel from CodeAct and cross-reference their responses.
environment-discovery
Systematic exploration of unknown environments before starting work.
performant-code
Writing efficient code that handles large data and tight constraints.
rag-eval
NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.