Embedded Video Captions
heygen-com/hyperframes
Adds captions to a single-subject talking-head video without editing the footage, from plain subtitles to cinematic text placed behind the speaker.
Cleans up a raw talking-head recording by cutting slips, filler and silences after your review, then assembles the cut into a finished MP4 with subtitles and a timeline preview.
SKILL.md written in Chinese; this summary is our English description.
Install Talking-Head Video Editor
$ npx skills add SpaceZephyr/creator-buddy --skill space-video-edit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SpaceZephyr/creator-buddy space-video-edit --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/SpaceZephyr/creator-buddy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/video-Skills/space-video-edit .claude/skills/space-video-edit && 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 "space-video-edit" agent skill from https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-edit into .claude/skills/space-video-edit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-video-edit", 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/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-editType 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 SpaceZephyr/creator-buddy --skill space-video-edit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SpaceZephyr/creator-buddy space-video-edit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/creator-buddy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/video-Skills/space-video-edit .agents/skills/space-video-edit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "space-video-edit" agent skill from https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-edit into .agents/skills/space-video-edit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-video-edit", 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 SpaceZephyr/creator-buddy --skill space-video-edit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SpaceZephyr/creator-buddy space-video-edit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/creator-buddy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/video-Skills/space-video-edit .cursor/skills/space-video-edit && 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 "space-video-edit" agent skill from https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-edit into .cursor/skills/space-video-edit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-video-edit", 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/SpaceZephyr/creator-buddy.git --path video-Skills/space-video-edit--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 SpaceZephyr/creator-buddy --skill space-video-edit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SpaceZephyr/creator-buddy space-video-edit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/creator-buddy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/video-Skills/space-video-edit .gemini/skills/space-video-edit && 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 "space-video-edit" agent skill from https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-edit into .gemini/skills/space-video-edit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-video-edit", 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 SpaceZephyr/creator-buddy space-video-editInstalls 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 SpaceZephyr/creator-buddy --skill space-video-edit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/SpaceZephyr/creator-buddy.git skills-src && mkdir -p .github/skills && cp -r skills-src/video-Skills/space-video-edit .github/skills/space-video-edit && 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 "space-video-edit" agent skill from https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-edit into .github/skills/space-video-edit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-video-edit", 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 SpaceZephyr/creator-buddy --skill space-video-edit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install SpaceZephyr/creator-buddy space-video-edit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/creator-buddy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/video-Skills/space-video-edit .opencode/skills/space-video-edit && 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 "space-video-edit" agent skill from https://github.com/SpaceZephyr/creator-buddy/tree/main/video-Skills/space-video-edit into .opencode/skills/space-video-edit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-video-edit", 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
space-video-edit- GitHub stars
- 1.6k
- Token cost
- ~484 tokens
- SKILL.md length
- 60 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- None found
At a glance
Cleans up a raw talking-head recording by cutting slips, filler and silences after your review, then assembles the cut into a finished MP4 with subtitles and a timeline preview.
- Works in 2 steps: 删前保后：后说的通常更完整 →… → 风险分层复核：「删字」安全、「删意思」危险。复核只砸在高风险处（整句删除、开头撞结…
- Removing slips, filler words and dead air from a recorded talking-head video
- SKILL.md covers 阶段一：剪口播（出干净素材）, 阶段二：口播成片, 交接 and 依赖, plus 1 more section
- Runs Shell scripts from its folder; calls bash
What it does
The work runs in two stages. First the agent transcribes the recording with word-level timing, scans it for verbal slips, filler words, repeated words, stutters, unfinished sentences and silent gaps, and builds a web page where you review the proposed deletions. When a slip is repeated, the earlier attempt is removed and the later, fuller one kept. After you confirm, a shell script cuts the video from a list of ranges to keep, so errors do not pile up from deleting piece by piece.
The trimmed video is transcribed a second time and the subtitles are proofread by the AI, instead of reusing the original subtitles. The second stage turns the cut video, subtitles and extra footage into a storyboard, an HTML timeline preview aligned to the speech and an exported MP4, reading aspect ratio and animation style from a small user config. It needs ffmpeg, ffprobe, node and a speech-recognition backend, and passes B-roll, subtitle polishing and cover images to sibling skills.
When your agent uses it
- Removing slips, filler words and dead air from a recorded talking-head video
- Producing clean, proofread subtitles from an already trimmed recording
- Turning a trimmed video plus subtitles into a finished vertical MP4
- Building a timeline preview that lines visuals up with the narration
Example prompts
- “Cut the mistakes and filler words out of ./raw/product-intro.mp4 and show me a review page before deleting anything.”
- “Re-transcribe the trimmed video and proofread the subtitles against what is actually said.”
- “Assemble the cut video, subtitles and screenshots into a timeline preview, then export a vertical MP4.”
Requirements
- ffmpeg and ffprobe
- node, to run the review and preview pages
- A speech-recognition backend for transcription
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- 删前保后：后说的通常更完整 → 删前面的口误/残句/重复第一次，保后面完整的。详见 references/删前保后.md。
- 风险分层复核：「删字」安全、「删意思」危险。复核只砸在高风险处（整句删除、开头撞结尾岔、长重复），低风险交末端人工审核页兜底。详见 references/删除风险分层.md。
What it can do on your machine
Read from SKILL.md and the folder at commit edf46c5. 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 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Talking-Head Video Editor loads about 484 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 60 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 60 words (~484 tokens).
- name
- space-video-edit
Files
SKILL.md and 4 other files (scripts, references) in video-Skills/space-video-edit of SpaceZephyr/creator-buddy.
- SKILL.md
- references/删前保后.md
- references/删除检测规则.md
- references/删除风险分层.md
- scripts/cut_by_ranges.sh
Open the folder on GitHubat commit edf46c5
Compare with similar skills
Talking-Head Video Editor 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 |
|---|---|---|---|---|---|---|
| Talking-Head Video Editor this skillSpaceZephyr/creator-buddy | 1.6k | — | ~484 | Automated safety check: Pass | None | |
| Embedded Video Captionsheygen-com/hyperframes | 59k | 3 repos | ~8.6k | Automated safety check: Pass | Apache-2.0 | |
| Video Understandcalesthio/OpenMontage | 66k | — | ~841 | Automated safety check: Pass | AGPL-3.0 | |
| VideoCaptioner SubtitlesWEIFENG2333/VideoCaptioner | 16k | — | ~1.7k | Automated safety check: Pass | GPL-3.0 | |
| Conversational Video Editingbrowser-use/video-use | 28k | 2 repos | ~6.4k | Automated safety check: Warn | MIT | |
| Ffmpeg Skillkajisho5/ffmpeg-skill | 1.9k | — | ~7.4k | Automated safety check: Pass | MIT |
Similar skills
Video Understand
calesthio/OpenMontage
Understand video content locally using ffmpeg frame extraction and Whisper transcription.
VideoCaptioner Subtitles
WEIFENG2333/VideoCaptioner
Adds subtitles to video with the videocaptioner CLI: transcribes speech, tidies and translates the text, and burns styled subtitles into the video or exports SRT and ASS files.
Conversational Video Editing
browser-use/video-use
Edits video through conversation: transcribes speech, proposes cuts, color grades, adds overlay animations and burns in subtitles, confirming the plan before each edit.
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…
Shorts
AgriciDaniel/claude-shorts
Interactive longform-to-shortform video creator. An agent skill from AgriciDaniel/claude-shorts.
More from SpaceZephyr/creator-buddy
All 31 skills in this repoWeChat Hot Article Analysis
SpaceZephyr/creator-buddy
Fetches hot WeChat Official Account articles by sector or keywords and produces a data file and an HTML report with rankings, style patterns and writing references.
Xiaohongshu Multi-Page HTML Cards
SpaceZephyr/creator-buddy
Turns an article, SOP, or tutorial into a self-contained, multi-page 3:4 HTML deck of image cards meant to be screenshotted page by page.
WeChat Viral Article Finder
SpaceZephyr/creator-buddy
Finds recent viral WeChat official account articles for a niche keyword and shows up to ten picks as cards, for topic research and benchmarking.
Chart Image Generator for WeChat Articles
SpaceZephyr/creator-buddy
Draws chart images such as flowcharts, architecture diagrams, ER diagrams and SWOT boards for WeChat official account articles, in one of six visual styles.
WeChat Article Cover Maker
SpaceZephyr/creator-buddy
Creates a 2.35:1 header cover for a WeChat official account article with image generation, keeping the headline inside the area that survives sharing crops.
Video Voiceover and Music Mixer
SpaceZephyr/creator-buddy
Adds sound to a finished video: generates narration from a script with TTS, finds royalty-free background music, and mixes everything together with ffmpeg.
Related
Works with
Categories
Questions about Talking-Head Video Editor
What does Talking-Head Video Editor do?
Cleans up a raw talking-head recording by cutting slips, filler and silences after your review, then assembles the cut into a finished MP4 with subtitles and a timeline preview. The work runs in two stages. First the agent transcribes the recording with word-level timing, scans it for verbal slips, filler words, repeated words, stutters, unfinished sentences and silent gaps, and builds a web page where you review the proposed deletions.
When should I use Talking-Head Video Editor?
Talking-Head Video Editor fits situations like: removing slips, filler words and dead air from a recorded talking-head video; producing clean, proofread subtitles from an already trimmed recording; turning a trimmed video plus subtitles into a finished vertical MP4; building a timeline preview that lines visuals up with the narration.
How do I install Talking-Head Video Editor in Claude Code?
Run `npx skills add SpaceZephyr/creator-buddy --skill space-video-edit -a claude-code`. Or copy the skill folder (video-Skills/space-video-edit in SpaceZephyr/creator-buddy) into .claude/skills/space-video-edit in your project. Claude Code loads it when a task matches its description.
How do I install Talking-Head Video Editor in Codex?
Run `npx skills add SpaceZephyr/creator-buddy --skill space-video-edit -a codex`. Or copy the skill folder (video-Skills/space-video-edit in SpaceZephyr/creator-buddy) into .agents/skills/space-video-edit in your project. Codex loads it when a task matches its description.
Can I use Talking-Head Video Editor 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 SpaceZephyr/creator-buddy --skill space-video-edit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/space-video-edit, .gemini/skills/space-video-edit, .github/skills/space-video-edit and .opencode/skills/space-video-edit in your project.
What does Talking-Head Video Editor need to run?
Going by SKILL.md and its folder, Talking-Head Video Editor needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: ffmpeg and ffprobe; node, to run the review and preview pages; A speech-recognition backend for transcription.
Does Talking-Head Video Editor access the network?
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.
Is Talking-Head Video Editor 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Talking-Head Video Editor use?
No licence was found for Talking-Head Video Editor or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Talking-Head Video Editor use?
About 484 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.
What are the alternatives to Talking-Head Video Editor?
Skills that share tags, products or a category with Talking-Head Video Editor: Embedded Video Captions (heygen-com/hyperframes, 59k stars), Video Understand (calesthio/OpenMontage, 66k stars), VideoCaptioner Subtitles (WEIFENG2333/VideoCaptioner, 16k stars) and Conversational Video Editing (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Talking-Head Video Editor?
SpaceZephyr (a GitHub user) maintains it in SpaceZephyr/creator-buddy, which has 1,601 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on August 26, 2026.
Source: SpaceZephyr/creator-buddy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.