Video Understand
calesthio/OpenMontage
Understand video content locally using ffmpeg frame extraction and Whisper transcription.
Analyze media file properties - duration, resolution, bitrate, codecs, and stream information
$ npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install benchflow-ai/skillsbench ffmpeg-media-info --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info .claude/skills/ffmpeg-media-info && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ffmpeg-media-info" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info into .claude/skills/ffmpeg-media-info/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-media-info", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-infoType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install benchflow-ai/skillsbench ffmpeg-media-info --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info .agents/skills/ffmpeg-media-info && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ffmpeg-media-info" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info into .agents/skills/ffmpeg-media-info/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-media-info", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install benchflow-ai/skillsbench ffmpeg-media-info --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info .cursor/skills/ffmpeg-media-info && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ffmpeg-media-info" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info into .cursor/skills/ffmpeg-media-info/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-media-info", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/benchflow-ai/skillsbench.git --path tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install benchflow-ai/skillsbench ffmpeg-media-info --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info .gemini/skills/ffmpeg-media-info && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ffmpeg-media-info" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info into .gemini/skills/ffmpeg-media-info/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-media-info", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install benchflow-ai/skillsbench ffmpeg-media-infoInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .github/skills && cp -r skills-src/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info .github/skills/ffmpeg-media-info && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ffmpeg-media-info" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info into .github/skills/ffmpeg-media-info/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-media-info", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install benchflow-ai/skillsbench ffmpeg-media-info --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info .opencode/skills/ffmpeg-media-info && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ffmpeg-media-info" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info into .opencode/skills/ffmpeg-media-info/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ffmpeg-media-info", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ffmpeg-media-infoAnalyze media file properties - duration, resolution, bitrate, codecs, and stream information
Ffmpeg Media Info is an agent skill from benchflow-ai/skillsbench. Analyze media file properties - duration, resolution, bitrate, codecs, and stream information
Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Video production. It works with FFmpeg. The repository describes itself as: SkillsBench evaluates how well skills work and how effective agents are at using them. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 9a1f4dd. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
ffprobeffmpegFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ffmpeg Media Info loads about 699 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 76 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from benchflow-ai/skillsbench at commit 9a1f4dd, republished under its Apache-2.0 licence (© benchflow-ai). 76 words, ~699 tokens.
.claude/skills/ffmpeg-media-info/SKILL.md (or your agent's skills folder).Extract and analyze media file metadata using ffprobe and ffmpeg.
# Show all file info
ffmpeg -i input.mp4
# JSON format (detailed)
ffprobe -v quiet -print_format json -show_format -show_streams input.mp4
# Simple format
ffprobe -v quiet -print_format json -show_format input.mp4# Get duration in seconds
ffprobe -v error -show_entries format=duration \
-of default=noprint_wrappers=1:nokey=1 input.mp4
# Duration with timestamp format
ffprobe -v error -show_entries format=duration \
-of default=noprint_wrappers=1:nokey=1 -sexagesimal input.mp4# Get video resolution
ffprobe -v error -select_streams v:0 \
-show_entries stream=width,height \
-of csv=s=x:p=0 input.mp4
# Get resolution as JSON
ffprobe -v error -select_streams v:0 \
-show_entries stream=width,height \
-of json input.mp4# Get overall bitrate
ffprobe -v error -show_entries format=bit_rate \
-of default=noprint_wrappers=1:nokey=1 input.mp4
# Get video bitrate
ffprobe -v error -select_streams v:0 \
-show_entries stream=bit_rate \
-of default=noprint_wrappers=1:nokey=1 input.mp4# Video codec
ffprobe -v error -select_streams v:0 \
-show_entries stream=codec_name,codec_long_name \
-of default=noprint_wrappers=1 input.mp4
# Audio codec
ffprobe -v error -select_streams a:0 \
-show_entries stream=codec_name,codec_long_name \
-of default=noprint_wrappers=1 input.mp4# Audio sample rate
ffprobe -v error -select_streams a:0 \
-show_entries stream=sample_rate \
-of default=noprint_wrappers=1:nokey=1 input.mp4
# Audio channels
ffprobe -v error -select_streams a:0 \
-show_entries stream=channels \
-of default=noprint_wrappers=1:nokey=1 input.mp4# Count video streams
ffprobe -v error -select_streams v -show_entries stream=index \
-of csv=p=0 input.mp4 | wc -l
# Count audio streams
ffprobe -v error -select_streams a -show_entries stream=index \
-of csv=p=0 input.mp4 | wc -l# Get frame rate
ffprobe -v error -select_streams v:0 \
-show_entries stream=r_frame_rate \
-of default=noprint_wrappers=1:nokey=1 input.mp4-v error to suppress warnings-of json for structured output-select_streams to target specific streams (v:0 for first video, a:0 for first audio)© benchflow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info of benchflow-ai/skillsbench.
Open the folder on GitHubat commit 9a1f4dd
Ffmpeg Media Info next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ffmpeg Media Info this skillbenchflow-ai/skillsbench | 1.8k | — | ~699 | Automated safety check: Pass | Apache-2.0 | |
| Video Understandcalesthio/OpenMontage | 66k | — | ~841 | Automated safety check: Pass | AGPL-3.0 | |
| HyperFrames Video Entry Pointheygen-com/hyperframes | 60k | 3 repos | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Video Shotseternityspring/reelbench-skills | 878 | 1 repos | ~1.8k | Automated safety check: Notes | Apache-2.0 | |
| Mobile Demo Film Editorsuperset-sh/superset | 15k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Video Editcalesthio/OpenMontage | 66k | — | ~855 | Automated safety check: Notes | AGPL-3.0 |
calesthio/OpenMontage
Understand video content locally using ffmpeg frame extraction and Whisper transcription.
heygen-com/hyperframes
Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.
eternityspring/reelbench-skills
拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面. An agent skill from eternityspring/reelbench-skills.
superset-sh/superset
Edits real mobile screen recordings into a configurable demo video with phone framing, title cards, cutaways and an end card, using a bundled renderer.
calesthio/OpenMontage
Edit videos locally using ffmpeg. An agent skill from calesthio/OpenMontage.
lemomo-ai/lemo-opuscar
Directs a short film made entirely in code in one of the Lemo-Opuscar library's named visual styles, from fetching the library through production and delivery.
benchflow-ai/skillsbench
This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences…
benchflow-ai/skillsbench
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure.
benchflow-ai/skillsbench
AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching acopf-math-model.md and MATPOWER branch fields.
benchflow-ai/skillsbench
Civilization 6 district mechanics library. An agent skill from benchflow-ai/skillsbench.
benchflow-ai/skillsbench
Build deterministic, verifiable data visualizations with D3.js (v6).
benchflow-ai/skillsbench
DC power flow analysis for power systems. An agent skill from benchflow-ai/skillsbench.
Works with
Categories
Analyze media file properties - duration, resolution, bitrate, codecs, and stream information. Ffmpeg Media Info is an agent skill from benchflow-ai/skillsbench.
Ffmpeg Media Info fits situations like: tasks that involve Video production.
Run `npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a claude-code`. Or copy the skill folder (tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info in benchflow-ai/skillsbench) into .claude/skills/ffmpeg-media-info in your project. Claude Code loads it when a task matches its description.
Run `npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a codex`. Or copy the skill folder (tasks/multilingual-video-dubbing/environment/skills/ffmpeg-media-info in benchflow-ai/skillsbench) into .agents/skills/ffmpeg-media-info in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add benchflow-ai/skillsbench --skill ffmpeg-media-info -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ffmpeg-media-info, .gemini/skills/ffmpeg-media-info, .github/skills/ffmpeg-media-info and .opencode/skills/ffmpeg-media-info in your project.
Going by SKILL.md and its folder, Ffmpeg Media Info needs the command-line tools its instructions call (ffprobe and ffmpeg).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Ffmpeg Media Info is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 699 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ffmpeg Media Info: Video Understand (calesthio/OpenMontage, 66k stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars), Video Shots (eternityspring/reelbench-skills, 878 stars) and Mobile Demo Film Editor (superset-sh/superset, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
benchflow-ai (a GitHub organization) maintains it in benchflow-ai/skillsbench, which has 1,835 GitHub stars. The repository holds 189 skills in this directory. The repository was last updated on July 23, 2026.
Source: benchflow-ai/skillsbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.