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 video-frame-extractiongit 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/video-frame-extraction)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/video-frame-extraction"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/video-frame-extraction/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/video-frame-extraction"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/video-frame-extraction.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 | $0.00018 | $0.03190 |
| Opus 5 | $0.00009 | $0.01595 |
| Sonnet 5 | $0.00004 | $0.00638 |
| Haiku 4.5 | $0.00002 | $0.00319 |
Grade A, and why
video-frame-extraction 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:
- video-frame-extraction — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Frame Extraction Skill
Purpose
This skill enables extraction of individual frames from video files (MP4, AVI, MOV, etc.) using OpenCV. Extracted frames are saved as image files in a specified output directory. It is suitable for video analysis, creating training datasets, thumbnail generation, and preprocessing video content for further processing.
When to Use
- Extracting frames for machine learning training data
- Creating image sequences from video content
- Generating video thumbnails or preview images
- Preprocessing videos for object detection or tracking
- Converting video segments to image collections for analysis
- Sampling frames at specific intervals for time-lapse effects
Required Libraries
The following Python libraries are required:
import cv2
import os
import json
from pathlib import Path
Input Requirements
- File formats: MP4, AVI, MOV, MKV, WMV, FLV, WEBM
- Video codec: Must be readable by OpenCV (most common codecs supported)
- File access: Read permissions on source video
- Output directory: Write permissions on destination folder
- Disk space: Ensure sufficient space for extracted frames (uncompressed images)
Output Schema
All extraction results must be returned as valid JSON conforming to this schema:
{
"success": true,
"source_video": "sample.mp4",
"output_directory": "/path/to/frames",
"frames_extracted": 150,
"extraction_params": {
"interval": 1,
"start_frame": 0,
"end_frame": null,
"output_format": "jpg"
},
"video_metadata": {
"total_frames": 300,
"fps": 30.0,
"duration_seconds": 10.0,
"resolution": [1920, 1080]
},
"output_files": [
"frame_000001.jpg",
"frame_000002.jpg"
],
"warnings": []
}
Field Descriptions
success: Boolean indicating whether frame extraction completedsource_video: Original video filenameoutput_directory: Path where frames were savedframes_extracted: Total number of frames successfully savedextraction_params.interval: Frame sampling interval (1 = every frame, 2 = every other frame, etc.)extraction_params.start_frame: First frame index extractedextraction_params.end_frame: Last frame index extracted (null if extracted to end)extraction_params.output_format: Image format used for saving framesvideo_metadata.total_frames: Total frame count in source videovideo_metadata.fps: Frames per second of source videovideo_metadata.duration_seconds: Video duration in secondsvideo_metadata.resolution: Video dimensions as [width, height]output_files: List of generated frame filenameswarnings: Array of issues encountered during extraction
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 · 496 lines · 18 tokens per session scan A b8109889c9b7
video-frame-extraction is a skill published in the GitHub repository benchflow-ai/skillsbench (1,754 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 3,190 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 2026-08-30.
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.