Capcut Edit
renezander030/capcut-cli
Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts.
Edit or repurpose existing footage with Magic Hour, choosing between generative visual edits, subtitles, and precise local trim, crop or composition.
Install Magic Hour Video Editing
$ npx skills add hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-video-editing --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/magichourhq/skills/skills/magic-hour-video-editing .claude/skills/magic-hour-video-editing && 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 "magic-hour-video-editing" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editing into .claude/skills/magic-hour-video-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-video-editing", 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/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editingType 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 hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-video-editing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/magichourhq/skills/skills/magic-hour-video-editing .agents/skills/magic-hour-video-editing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "magic-hour-video-editing" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editing into .agents/skills/magic-hour-video-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-video-editing", 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 hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-video-editing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/magichourhq/skills/skills/magic-hour-video-editing .cursor/skills/magic-hour-video-editing && 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 "magic-hour-video-editing" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editing into .cursor/skills/magic-hour-video-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-video-editing", 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/hashgraph-online/awesome-codex-plugins.git --path plugins/magichourhq/skills/skills/magic-hour-video-editing--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 hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-video-editing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/magichourhq/skills/skills/magic-hour-video-editing .gemini/skills/magic-hour-video-editing && 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 "magic-hour-video-editing" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editing into .gemini/skills/magic-hour-video-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-video-editing", 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 hashgraph-online/awesome-codex-plugins magic-hour-video-editingInstalls 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 hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/magichourhq/skills/skills/magic-hour-video-editing .github/skills/magic-hour-video-editing && 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 "magic-hour-video-editing" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editing into .github/skills/magic-hour-video-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-video-editing", 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 hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-video-editing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/magichourhq/skills/skills/magic-hour-video-editing .opencode/skills/magic-hour-video-editing && 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 "magic-hour-video-editing" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-video-editing into .opencode/skills/magic-hour-video-editing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-video-editing", 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
magic-hour-video-editing- GitHub stars
- 1.3k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 812 words
- Files
- 6 (incl. references)
- Skills in repo
- 716
- Repo updated
- First seen
- Licence
- MIT
At a glance
Edit or repurpose existing footage with Magic Hour, choosing between generative visual edits, subtitles, and precise local trim, crop or composition.
- A source video that needs changes
- SKILL.md covers Inspect before choosing, Apply one purposeful edit, Preserve audio and caption last and Execute and hand off
- Reaches mcp.magichour.ai
- Social versions
What it does
Magic Hour Video Editing is an agent skill from hashgraph-online/awesome-codex-plugins. Edit or repurpose existing footage with Magic Hour, choosing between generative visual edits, subtitles, and precise local trim, crop or composition. Use for a source video that needs changes or social versions, not a new video from scratch.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/extend-upscale.md` and `references/repurpose.md`).
It sits in Media & Creative, covering Video production, Content repurposing and Transcription. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is MIT.
When your agent uses it
- A source video that needs changes
- Social versions
- Not a new video from scratch
Example prompts
- “/magic-hour-video-editing”
What it can do on your machine
Read from SKILL.md and the folder at commit 3e1456a. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
mcp.magichour.ai
Also links to:
github.comdocs.magichour.ai
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
Magic Hour Video Editing loads about 1.7k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 812 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 hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its MIT licence (© hashgraph-online). 812 words, ~1,670 tokens.
Download SKILL.mdSave it as
.claude/skills/magic-hour-video-editing/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- magic-hour-video-editing
- description
- Edit or repurpose existing footage with Magic Hour, choosing between generative visual edits, subtitles, and precise local trim, crop or composition. Use for a source video that needs changes or social versions, not a new video from scratch.
- license
- MIT
- metadata.author
- magichourhq
- metadata.version
- 1.3.0
Magic Hour video editing
Start from the requested change and inspect the existing master. Choose editing settings and a suitable layout yourself when delegated; reuse the current budget and respect requested draft approvals. Show the exported video first and keep technical records with the project. For shorter cuts, alternate placements and copy/audio revisions, read repurpose a master.
For a stylized reinterpretation, read Video-to-Video controls. For a longer ending or higher-resolution final video, read extension and upscaling, including the current web handoffs and continuity checks.
Keep the footage the user already likes. Choose the operation that changes the requested property without unnecessarily regenerating motion, identity or speech.
Inspect before choosing
Read the source's actual duration, dimensions, frame rate and audio streams. Watch the relevant interval. Record the requested change and what must survive: subject identity, actions, timing, dialogue, original sound, frame shape or a specific object. A short clip with several cuts may need separate edits; do not assume the model maintains continuity through every cut.
| Requested change | Operation |
|---|---|
| Change scene appearance, materials or visual style | ai_video_editor_create_video using the original footage |
| Apply a supported animation/art style to the source | video_to_video_create_video with deliberate prompt/FPS mode |
| Put another face into the same performance | Face Swap with deliberate cast mapping |
| Replace the body/character or transfer its performance | Character Replace with the appropriate replace/animate mode |
| Add speech captions | auto_subtitle_generator_create_video after picture edits |
| Trim, resize, reframe, add exact copy/logo, or assemble | Available compositor such as FFmpeg or an existing video editor |
| Change a visible speaker's speech | Lip-sync route, not a generic visual-edit prompt |
Do not use a generative edit to perform a lossless requirement. It can redraw unrequested regions and does not guarantee pixel-preserved backgrounds, logos or faces. Do not claim tracking, masks or object-isolated controls unless the chosen tool exposes them.
Apply one purposeful edit
Select an interval within the current model's minimum and maximum length. Describe the visual change, then protected action and camera behavior:
Change only the room's appearance to a warm, sunlit illustration. Preserve the person's action of placing the cup on the table, the camera position, shot timing, cup count and framing. No cuts, new characters or added text.
That prompt is a requested constraint, not a guarantee. Inspect cup contact, hands, occlusion, faces and cuts in the output. If the model changes required action or identity, return to the original source and narrow the change or choose a live-supported alternative within budget. Do not chain unreviewed edited clips.
For an alternate-world remix, separate the effect from the action: change the setting to moonlit ruins while preserving the original walk, camera and timing. Keep a strong reference moment visible before the payoff. Do not add a new face or costume to a background-only request. Split distinct shots only when needed for controlled edits, and inspect the reconstructed joins and sound.
For a vertical version, check the entire motion path before cropping. If a tracked subject or important context will leave the crop, use a designed contained layout when the brief permits, or use an editor that actually supports the required tracking. Do not stretch, invent missing edge content, or assume one crop works across camera cuts.
Show full SKILL.md (287 more words)Show less
Preserve audio and caption last
Verify whether the edited output retains the desired audio; do not infer it from a successful video job. Keep the source master, choose the intended soundtrack explicitly, and align any replacement to the exact edited interval. Never use -shortest blindly when it could cut off speech. Check the first and last audible words.
Apply subtitles to the final cut so timing and coordinates refer to the delivered picture. Check the live style template/custom fields. Inspect names, numbers, language support, line breaks and platform overlays. If editable caption text is required but the API only returns a rendered video, use a suitable local caption workflow or report the missing deliverable.
Execute and hand off
Use the creation MCP at https://mcp.magichour.ai/; setup. For API use, consult the OpenAPI: /v1/ai-video-editor, /v1/auto-subtitle-generator, and GET /v1/video-projects/{id}. Respect current models, intervals, resolution, tier and the total authorized cost.
For local footage, obtain video_assets_generate_presigned_url, PUT raw bytes to upload_url without the API bearer token, then use file_path. Submit once, retain the ID and wait_for_video_project. Resume the same job after a wait timeout; do not repeat an ambiguous creation. Preserve signed URLs exactly and download durable files.
Decode the final export, verify its actual dimensions/duration/audio, and inspect full playback including transitions. Compare against the original, not just the last intermediate. Our illustrated video-edit example changes the visual style but also shifts the opening head turn. Use the original as the timing reference; a pleasing style is not proof of faithful action.
Deliver the clean master, requested derivatives, edit decisions and unresolved defects. Reuse accepted edits for future crops/copy changes; regenerate only when the visual brief changes. Caption quality and preservation of supplied source audio still require their own output validation.
© hashgraph-online, 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 5 other files (references) in plugins/magichourhq/skills/skills/magic-hour-video-editing of hashgraph-online/awesome-codex-plugins.
- SKILL.md
- LICENSE
- agents/openai.yaml
- references/extend-upscale.md
- references/repurpose.md
- references/restyle.md
Open the folder on GitHubat commit 3e1456a
Compare with similar skills
Magic Hour Video Editing 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 |
|---|---|---|---|---|---|---|
| Magic Hour Video Editing this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Capcut Editrenezander030/capcut-cli | 854 | — | ~1.4k | Automated safety check: Pass | MIT | |
| AutoshortsUpload-Post/skill-autoshorts | 151 | — | ~5.3k | Automated safety check: Notes | MIT | |
| Stage EditOrkas-AI/Orkas-VideoStudio | 499 | — | ~2.4k | Automated safety check: Pass | MIT | |
| KinocutKyaniteLabs/kinocut | 198 | — | ~5.7k | Automated safety check: Pass | Apache-2.0 | |
| Kinocut RepurposeKyaniteLabs/kinocut | 198 | — | ~1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Autoshorts
Upload-Post/skill-autoshorts
Daily pipeline that picks one long video from a folder, transcribes it with Whisper, uses Gemini 3 Flash multimodal to find every viral short-form moment, cuts each candidate with FFmpeg, adds a…
Stage Edit
Orkas-AI/Orkas-VideoStudio
Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained…
Kinocut
KyaniteLabs/kinocut
Use Kinocut for guarded video editing, source-backed planning, FFmpeg operations, media analysis, subtitles, audio workflows, Hyperframes or Revideo rendering, repurposing packages, and release…
Kinocut Repurpose
KyaniteLabs/kinocut
Use the current Kinocut tools to turn one local video path into a short platform-ready clip package with manifests, review artifacts, and human approval gates.
Video Clipper
gooseworks-ai/goose-skills
Repurposes long-form video (podcasts, interviews, talks) into short-form vertical clips for Instagram Reels, TikTok, and YouTube Shorts.
More from hashgraph-online/awesome-codex-plugins
All 716 skills in this repoAnime Reaction Gif
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
Calibredb
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
Rust API Test Harness
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
Art
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
Calle
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
Game Balance Economy
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Related
Categories
Questions about Magic Hour Video Editing
What does Magic Hour Video Editing do?
Edit or repurpose existing footage with Magic Hour, choosing between generative visual edits, subtitles, and precise local trim, crop or composition. Magic Hour Video Editing is an agent skill from hashgraph-online/awesome-codex-plugins. Edit or repurpose existing footage with Magic Hour, choosing between generative visual edits, subtitles, and precise local trim, crop or composition.
When should I use Magic Hour Video Editing?
Magic Hour Video Editing fits situations like: A source video that needs changes; social versions; not a new video from scratch.
How do I install Magic Hour Video Editing in Claude Code?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a claude-code`. Or copy the skill folder (plugins/magichourhq/skills/skills/magic-hour-video-editing in hashgraph-online/awesome-codex-plugins) into .claude/skills/magic-hour-video-editing in your project. Claude Code loads it when a task matches its description.
How do I install Magic Hour Video Editing in Codex?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a codex`. Or copy the skill folder (plugins/magichourhq/skills/skills/magic-hour-video-editing in hashgraph-online/awesome-codex-plugins) into .agents/skills/magic-hour-video-editing in your project. Codex loads it when a task matches its description.
Can I use Magic Hour Video Editing 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 hashgraph-online/awesome-codex-plugins --skill magic-hour-video-editing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/magic-hour-video-editing, .gemini/skills/magic-hour-video-editing, .github/skills/magic-hour-video-editing and .opencode/skills/magic-hour-video-editing in your project.
What does Magic Hour Video Editing need to run?
SKILL.md names no scripts, command-line tools or credentials: Magic Hour Video Editing is instructions for the agent only.
Does Magic Hour Video Editing access the network?
SKILL.md names 3 domains. In commands or code: mcp.magichour.ai; the agent is likely to contact it when it follows the instructions. As links in the text: github.com and docs.magichour.ai. This is read from the text; nothing was executed.
Is Magic Hour Video Editing 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 Magic Hour Video Editing use?
Magic Hour Video Editing is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Magic Hour Video Editing use?
About 1.7k tokens (SKILL.md is roughly 6.7k 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 2.1k tokens, read only when the agent opens those files.
What are the alternatives to Magic Hour Video Editing?
Skills that share tags, products or a category with Magic Hour Video Editing: Capcut Edit (renezander030/capcut-cli, 854 stars), Autoshorts (Upload-Post/skill-autoshorts, 151 stars), Stage Edit (Orkas-AI/Orkas-VideoStudio, 499 stars) and Kinocut (KyaniteLabs/kinocut, 198 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Magic Hour Video Editing?
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.