← All skills
video-understand
40 / 100 · High risk
Only if you trust the author. Some of what it can do is expected: a media skill usually calls an AI service over the internet.
By ajoslin/dot (GitHub) · media · 24 stars · scanned at commit 8aa8e87
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps, summaries, or answering questions about video content. Automatically selects the best available provider based on configured API keys - prefers full video understanding (Gemini/OpenRoute…
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 29 places.
Show 17 more
- config/opencode/skills/video-understand/SKILL.md, line 147
pip install google-generativeai # Gemini - config/opencode/skills/video-understand/SKILL.md, line 153
brew install yt-dlp ffmpeg # Video tools - config/opencode/skills/video-understand/references/asr-providers.md, line 219
subprocess.run([ - config/opencode/skills/video-understand/references/openrouter.md, line 79
subprocess.run([ - config/opencode/skills/video-understand/references/video-sources.md, line 78
subprocess.run(cmd, check=True, capture_output=True) - config/opencode/skills/video-understand/references/video-sources.md, line 108
subprocess.run(cmd, check=True, capture_output=True) - config/opencode/skills/video-understand/references/video-sources.md, line 128
result = subprocess.run(cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/references/video-sources.md, line 188
subprocess.run(cmd, check=True, capture_output=True) - config/opencode/skills/video-understand/references/video-sources.md, line 215
subprocess.run(cmd, check=True, capture_output=True) - config/opencode/skills/video-understand/references/video-sources.md, line 238
result = subprocess.run(cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/references/video-sources.md, line 267
subprocess.run(cmd, check=True, capture_output=True) - config/opencode/skills/video-understand/scripts/process_video.py, line 214
result = subprocess.run(cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/scripts/process_video.py, line 250
result = subprocess.run(cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/scripts/process_video.py, line 281
result = subprocess.run(duration_cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/scripts/process_video.py, line 319
result = subprocess.run(cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/scripts/process_video.py, line 343
result = subprocess.run(cmd, capture_output=True, text=True) - config/opencode/skills/video-understand/scripts/process_video.py, line 367
result = subprocess.run(cmd, capture_output=True, text=True)
and 9 more places
Downloads and installs other software
The author does not mention this.
Found in 46 places.
Show 17 more
- config/opencode/skills/video-understand/SKILL.md, line 154
pip install openai # OpenAI Whisper - config/opencode/skills/video-understand/SKILL.md, line 155
pip install groq # Groq Whisper - config/opencode/skills/video-understand/SKILL.md, line 156
pip install assemblyai # AssemblyAI - config/opencode/skills/video-understand/SKILL.md, line 157
pip install deepgram-sdk # Deepgram - config/opencode/skills/video-understand/SKILL.md, line 158
pip install openai-whisper # Local Whisper - config/opencode/skills/video-understand/references/asr-providers.md, line 20
pip install openai - config/opencode/skills/video-understand/references/asr-providers.md, line 50
pip install groq - config/opencode/skills/video-understand/references/asr-providers.md, line 80
pip install assemblyai - config/opencode/skills/video-understand/references/asr-providers.md, line 123
pip install deepgram-sdk - config/opencode/skills/video-understand/references/asr-providers.md, line 165
pip install openai-whisper - config/opencode/skills/video-understand/references/asr-providers.md, line 168
brew install whisper-cpp # macOS - config/opencode/skills/video-understand/references/ffmpeg-frames.md, line 17
brew install ffmpeg - config/opencode/skills/video-understand/references/ffmpeg-frames.md, line 20
pip install openai-whisper - config/opencode/skills/video-understand/references/gemini.md, line 8
pip install google-generativeai - config/opencode/skills/video-understand/references/openrouter.md, line 8
pip install openai - config/opencode/skills/video-understand/references/setup-guide.md, line 11
brew install ffmpeg yt-dlp - config/opencode/skills/video-understand/references/setup-guide.md, line 12
pip install openai
and 26 more places
Can call paid AI services billed to you
This is disclosed by the author in the skill's SKILL.md or README. Expected for a media skill.
Found in 12 places.
Show 9 more
- config/opencode/skills/video-understand/references/openrouter.md, line 27
from openai import OpenAI - config/opencode/skills/video-understand/references/openrouter.md, line 30
base_url="https://openrouter.ai/api/v1", - config/opencode/skills/video-understand/references/openrouter.md, line 114
from openai import APIError, RateLimitError - config/opencode/skills/video-understand/references/openrouter.md, line 131
base_url="https://openrouter.ai/api/v1", - config/opencode/skills/video-understand/references/video-sources.md, line 38
import google.generativeai as genai - config/opencode/skills/video-understand/scripts/process_video.py, line 788
import google.generativeai as genai - config/opencode/skills/video-understand/scripts/process_video.py, line 834
from openai import OpenAI - config/opencode/skills/video-understand/scripts/process_video.py, line 846
base_url="https://openrouter.ai/api/v1", - config/opencode/skills/video-understand/scripts/process_video.py, line 926
from openai import OpenAI
Sends data to these websites: api.openai.com, generativelanguage.googleapis.com
The author does not mention this. Expected for a media skill.
Found in 10 places.
Show 7 more
Changes files outside its own folder
The author does not mention this.
Found in 2 places.
Reads your saved credentials, such as SSH keys or .env files
The author does not mention this.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (media) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'video-understand' ] || [ -L ~/.agents/skills/'video-understand' ]; then echo 'A skill folder named video-understand already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ajoslin/dot' "$d" && git -C "$d" checkout --quiet '8aa8e87ab2fed38a42acefb4a2d9a3a557f0b1ed' -- 'config/opencode/skills/video-understand' && mkdir -p ~/.agents/skills && cp -R "$d"/'config/opencode/skills/video-understand' ~/.agents/skills/'video-understand' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'video-understand' ~/.claude/skills/'video-understand' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for ajoslin/dot shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/ajoslin/dot/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 8aa8e87 | 40 |
| 2026-11-06 | 8aa8e87 | 40 |