Youtube Clipper
op7418/Youtube-clipper-skill
YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。
Capture frames from a YouTube video at a regular interval, produce a manifest mapping filenames to timestamps, and describe each frame with an LLM.
Install Capture Video Frames
$ npx skills add pamelafox/presentation-skills --skill capture-video-frames -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pamelafox/presentation-skills capture-video-frames --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/pamelafox/presentation-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/capture-video-frames .claude/skills/capture-video-frames && 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 "capture-video-frames" agent skill from https://github.com/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-frames into .claude/skills/capture-video-frames/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-video-frames", 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/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-framesType 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 pamelafox/presentation-skills --skill capture-video-frames -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pamelafox/presentation-skills capture-video-frames --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pamelafox/presentation-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/capture-video-frames .agents/skills/capture-video-frames && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "capture-video-frames" agent skill from https://github.com/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-frames into .agents/skills/capture-video-frames/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-video-frames", 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 pamelafox/presentation-skills --skill capture-video-frames -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pamelafox/presentation-skills capture-video-frames --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pamelafox/presentation-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/capture-video-frames .cursor/skills/capture-video-frames && 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 "capture-video-frames" agent skill from https://github.com/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-frames into .cursor/skills/capture-video-frames/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-video-frames", 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/pamelafox/presentation-skills.git --path .agents/skills/capture-video-frames--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 pamelafox/presentation-skills --skill capture-video-frames -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pamelafox/presentation-skills capture-video-frames --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pamelafox/presentation-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/capture-video-frames .gemini/skills/capture-video-frames && 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 "capture-video-frames" agent skill from https://github.com/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-frames into .gemini/skills/capture-video-frames/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-video-frames", 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 pamelafox/presentation-skills capture-video-framesInstalls 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 pamelafox/presentation-skills --skill capture-video-frames -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pamelafox/presentation-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/capture-video-frames .github/skills/capture-video-frames && 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 "capture-video-frames" agent skill from https://github.com/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-frames into .github/skills/capture-video-frames/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-video-frames", 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 pamelafox/presentation-skills --skill capture-video-frames -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pamelafox/presentation-skills capture-video-frames --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pamelafox/presentation-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/capture-video-frames .opencode/skills/capture-video-frames && 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 "capture-video-frames" agent skill from https://github.com/pamelafox/presentation-skills/tree/main/.agents/skills/capture-video-frames into .opencode/skills/capture-video-frames/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "capture-video-frames", 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.
Facts
- Skill name
capture-video-frames- GitHub stars
- 125
- Token cost
- ~1.7k tokens
- SKILL.md length
- 663 words
- Files
- 2
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Capture frames from a YouTube video at a regular interval, produce a manifest mapping filenames to timestamps, and describe each frame with an LLM.
- Works in 3 steps: Capture frames → Describe frames using the describe-frame… → Deduplicate frames and select best…
- : extract video frames
- SKILL.md covers Step 1: Capture frames, Step 2: Describe frames using… and Step 3: Deduplicate frames and…
- Runs Python scripts from its folder; calls brew, uv and yt-dlp
What it does
Capture Video Frames is an agent skill from pamelafox/presentation-skills. Capture frames from a YouTube video at a regular interval, produce a manifest mapping filenames to timestamps, and describe each frame with an LLM. USE FOR: extract video frames, capture screenshots from YouTube, describe video frames, video frame analysis, frame-by-frame summary.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `capture_video_frames.py`).
It sits in Agent Workflows. It works with YouTube and FFmpeg. The repository describes itself as: Skills for AI agents to process presentations - helpful for teachers and speakers. The licence is MIT.
When your agent uses it
- : extract video frames
- Capture screenshots from YouTube
- Describe video frames
- Video frame analysis
Example prompts
- “/capture-video-frames”
Requirements
- Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 2b809b3. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
brewuvyt-dlpffmpegpipapt-get
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv and pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Capture Video Frames loads about 1.7k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 663 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from pamelafox/presentation-skills at commit 2b809b3, republished under its MIT licence (© pamelafox). 663 words, ~1,689 tokens.
Download SKILL.mdSave it as
.claude/skills/capture-video-frames/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- capture-video-frames
- description
- Capture frames from a YouTube video at a regular interval, produce a manifest mapping filenames to timestamps, and describe each frame with an LLM. USE FOR: extract video frames, capture screenshots from YouTube, describe video frames, video frame analysis, frame-by-frame summary.
- argument-hint
- <youtube_url> <output_dir> [--interval SECONDS]
Capture and describe video frames
Step 1: Capture frames
Run the capture_video_frames.py script:
uv run .agents/skills/capture-video-frames/capture_video_frames.py <youtube_url> <output_dir> [--interval SECONDS]Arguments
youtube_url(required): YouTube video URL (same formats accepted by the extract-transcript skill).output_dir(required): Directory to save frames and the manifest file. Created if it doesn't exist.--interval(optional): Seconds between captured frames. Defaults to 30.
Outputs
- frame_0000.png, frame_0030.png, … — PNG images named by their timestamp in seconds (zero-padded to 4 digits).
- frames_manifest.md — A markdown file listing each frame with its timestamp and a placeholder for descriptions.
Example frames_manifest.md:
| File | Timestamp | Description |
|------|-----------|-------------|
| frame_0000.png | [00:00] | |
| frame_0030.png | [00:30] | |
| frame_0060.png | [01:00] | |Prerequisites
- yt-dlp:
brew install yt-dlporpip install yt-dlp - ffmpeg:
brew install ffmpegorapt-get install ffmpeg
Step 2: Describe frames using the describe-frame subagent
After capturing frames, describe each frame by running the describe-frame custom agent as a subagent. Each subagent invocation gets an isolated context, so frame images won't accumulate and exhaust the context window.
The describe-frame agent is defined in .github/agents/describe-frame.md.
Procedure
- Read frames_manifest.md from the output directory to get the full list of frames.
- For each frame, run the
describe-frameagent as a subagent with a prompt that includes:- The absolute path to the current frame image to view.
- The absolute path to the previous frame image to view (if one exists).
- The previous frame's description as text (if one exists).
- The subagent will return a plain-text description (or
(same as previous)if the frame is essentially identical to the previous one). - After each subagent returns, update the Description column for that row in frames_manifest.md immediately.
- Continue until all frames are described.
Subagent prompt template
Use this as the prompt when invoking the describe-frame subagent (fill in the bracketed values):
Describe the current frame image at: [CURRENT_FRAME_ABSOLUTE_PATH]
[If previous frame exists, include these two lines:]
The previous frame image is at: [PREVIOUS_FRAME_ABSOLUTE_PATH]
The previous frame was described as: "[PREVIOUS_DESCRIPTION]"Example output
After describing all frames, frames_manifest.md should look like:
| File | Timestamp | Description |
|------|-----------|-------------|
| frame_0000.png | [00:00] | Title slide introducing "Building RAG apps with Python" |
| frame_0030.png | [00:30] | Speaker showing the agenda with four main topics |
| frame_0060.png | [01:00] | (same as previous) |
| frame_0090.png | [01:30] | Architecture diagram of a retrieval-augmented generation pipeline |Step 3: Deduplicate frames and select best speaker faces
After all frames are described, groups of consecutive (same as previous) rows represent the same visual content captured at different moments. Within each group, speaker faces may differ — eyes open vs closed, mouth open vs closed, facing camera vs turned away.
Goal
For each group of duplicate frames, keep only one frame — the one with the best speaker face quality — and remove the rest.
Criteria for best face (in priority order)
- The current speaker's mouth should be open (mid-speech). If you know who is speaking at that timestamp (from a transcript), prioritize that speaker.
- Eyes open — no mid-blink frames.
- Facing camera — not turned sideways or looking down.
- If no speakers are visible (e.g., full-screen demo or slide without webcam feeds), all frames in the group are equivalent — keep the first one.
Show full SKILL.md (258 more words)Show less
Procedure
- Identify all groups of consecutive rows where the description is
(same as previous). Each group starts with the "anchor" frame (the one with an actual description) followed by one or more(same as previous)rows. - For each group, run the
describe-framesubagent to compare faces across the anchor frame and each duplicate. Use this prompt template:
Compare these two frames focusing ONLY on the speaker faces visible in webcam feeds. Which frame has better speaker faces — eyes open, facing camera, mouth open (mid-speech), not mid-blink or turned away?
Frame A: [ANCHOR_FRAME_ABSOLUTE_PATH]
Frame B: [DUPLICATE_FRAME_ABSOLUTE_PATH]
Reply with ONLY one of:
- "A BETTER" if the anchor frame has better speaker faces
- "B BETTER" if the duplicate frame has better speaker faces
- "EQUAL" if both are equivalent
- "NO SPEAKERS" if no speaker faces are visible in either frame
Then add a brief reason.- After comparing all duplicates in a group against the anchor (and the current best), determine the single best frame.
- If the best frame is NOT the anchor:
- Move the anchor's description to the best frame's row.
- Add a face-quality note to the description, e.g.,
(better speaker faces than frame_XXXX: eyes open, facing camera)
- Remove all other
(same as previous)rows from the manifest. - If the anchor was already the best, just remove the duplicate rows.
Recapturing frames for closed mouths
After deduplication, if the best frame in a group still has the speaking person's mouth closed (both speakers have mouths closed), try recapturing at nearby timestamps:
- Download the video if not already available:
bash yt-dlp -f "bestvideo[height<=720]" --no-playlist -o "<output_dir>/video.%(ext)s" "<youtube_url>" - Capture alternative frames at +2s, +5s, +8s, and +10s offsets from the frame's timestamp:
bash ffmpeg -ss <SECONDS> -i <output_dir>/video.mp4 -frames:v 1 -q:v 2 <output_dir>/alt_<FRAME>_<SECONDS>.png -y - Use the
describe-framesubagent to check if the speaker's mouth is open in any alternative, AND that the slide/demo content is still the same. - If a better alternative is found, replace the frame file (
cp alt_XXXX.png frame_XXXX.png). - Clean up:
rm -f <output_dir>/alt_*.png <output_dir>/video.mp4
© pamelafox, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/capture-video-frames of pamelafox/presentation-skills.
- SKILL.md
- capture_video_frames.py
Open the folder on GitHubat commit 2b809b3
Compare with similar skills
Capture Video Frames 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 |
|---|---|---|---|---|---|---|
| Capture Video Frames this skillpamelafox/presentation-skills | 125 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Youtube Clipperop7418/Youtube-clipper-skill | 2.2k | — | ~1.6k | Automated safety check: Notes | MIT | |
| Video Transcribewendy7756/AI-Video-Transcriber | 3.3k | — | ~937 | Automated safety check: Notes | Apache-2.0 | |
| Claude Real VideoHUANGCHIHHUNGLeo/claude-real-video | 2.2k | — | ~639 | Automated safety check: Pass | MIT | |
| Ffmpeg Skillkajisho5/ffmpeg-skill | 1.9k | — | ~7.4k | Automated safety check: Pass | MIT | |
| Video Perceptionjordanrendric/claude-video-vision | 1.4k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Video Transcribe
wendy7756/AI-Video-Transcriber
Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file.
Claude Real Video
HUANGCHIHHUNGLeo/claude-real-video
Watch a video for the user. An agent skill from HUANGCHIHHUNGLeo/claude-real-video.
Ffmpeg Skill
kajisho5/ffmpeg-skill
Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text…
Video Perception
jordanrendric/claude-video-vision
A skill your agent uses when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation
Explainroo
vincentsch/explainroo
Make an explainer video (MP4) with a voice-over using explainroo.
More from pamelafox/presentation-skills
All 14 skills in this repoGenerate Images Mai
pamelafox/presentation-skills
Generate or edit bitmap images with Microsoft MAI-Image-2.5 through the Azure AI image APIs.
Make Revealjs Presentation
pamelafox/presentation-skills
Create or update a RevealJS HTML presentation using the repository's bundled slide template.
Fetch Slides
pamelafox/presentation-skills
Fetch presentation slides from a URL and convert them to PDF.
Generate Writeup
pamelafox/presentation-skills
Generate an annotated blog-style write-up from a presentation's slides and video recording.
Outline Slides
pamelafox/presentation-skills
Generate a numbered outline of presentation slides with one-sentence summaries.
Thumbnail Of PPTX
pamelafox/presentation-skills
Capture a thumbnail image of a slide from a OneDrive/Office presentation link.
Related
Categories
Questions about Capture Video Frames
What does Capture Video Frames do?
Capture frames from a YouTube video at a regular interval, produce a manifest mapping filenames to timestamps, and describe each frame with an LLM. Capture Video Frames is an agent skill from pamelafox/presentation-skills. Capture frames from a YouTube video at a regular interval, produce a manifest mapping filenames to timestamps, and describe each frame with an LLM.
When should I use Capture Video Frames?
Capture Video Frames fits situations like: : extract video frames; capture screenshots from YouTube; describe video frames; video frame analysis.
How do I install Capture Video Frames in Claude Code?
Run `npx skills add pamelafox/presentation-skills --skill capture-video-frames -a claude-code`. Or copy the skill folder (.agents/skills/capture-video-frames in pamelafox/presentation-skills) into .claude/skills/capture-video-frames in your project. Claude Code loads it when a task matches its description.
How do I install Capture Video Frames in Codex?
Run `npx skills add pamelafox/presentation-skills --skill capture-video-frames -a codex`. Or copy the skill folder (.agents/skills/capture-video-frames in pamelafox/presentation-skills) into .agents/skills/capture-video-frames in your project. Codex loads it when a task matches its description.
Can I use Capture Video Frames in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pamelafox/presentation-skills --skill capture-video-frames -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/capture-video-frames, .gemini/skills/capture-video-frames, .github/skills/capture-video-frames and .opencode/skills/capture-video-frames in your project.
What does Capture Video Frames need to run?
Going by SKILL.md and its folder, Capture Video Frames needs Python for the scripts in its folder and the command-line tools its instructions call (brew, uv, yt-dlp, ffmpeg, pip and apt-get). Our summary lists: Python 3.
Does Capture Video Frames access the network?
SKILL.md contains no URLs. Its commands use uv and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Capture Video Frames safe to install?
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.
What licence does Capture Video Frames use?
Capture Video Frames is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Capture Video Frames use?
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Capture Video Frames?
Skills that share tags, products or a category with Capture Video Frames: Youtube Clipper (op7418/Youtube-clipper-skill, 2.2k stars), Video Transcribe (wendy7756/AI-Video-Transcriber, 3.3k stars), Claude Real Video (HUANGCHIHHUNGLeo/claude-real-video, 2.2k stars) and Ffmpeg Skill (kajisho5/ffmpeg-skill, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Capture Video Frames?
pamelafox (a GitHub user) maintains it in pamelafox/presentation-skills, which has 125 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 2, 2026.
Source: pamelafox/presentation-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.