Anything2explainer
Vincentwei1021/anything2explainer
给一个主题，产出一条黑底 MG 风格（幕底可选星点或点阵波）、有配音字幕章节进度条的科普讲解视频（中文或英文；Remotion 代码动画；时长由用户定，常用 3–5 分钟）。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据，以及一条完整样片（《RAG 与知识库》）作为质量标尺。Turn any topic into a narrated…
Make a portrait speak, react or perform supplied audio with Magic Hour, or lip-sync an existing video to replacement speech.
Install Magic Hour Talking Video
$ npx skills add hashgraph-online/awesome-codex-plugins --skill magic-hour-talking-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-talking-video --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-talking-video .claude/skills/magic-hour-talking-video && 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-talking-video" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-talking-video into .claude/skills/magic-hour-talking-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-talking-video", 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-talking-videoType 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-talking-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-talking-video --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-talking-video .agents/skills/magic-hour-talking-video && 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-talking-video" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-talking-video into .agents/skills/magic-hour-talking-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-talking-video", 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-talking-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-talking-video --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-talking-video .cursor/skills/magic-hour-talking-video && 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-talking-video" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-talking-video into .cursor/skills/magic-hour-talking-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-talking-video", 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-talking-video--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-talking-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins magic-hour-talking-video --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-talking-video .gemini/skills/magic-hour-talking-video && 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-talking-video" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-talking-video into .gemini/skills/magic-hour-talking-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-talking-video", 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-talking-videoInstalls 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-talking-video -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-talking-video .github/skills/magic-hour-talking-video && 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-talking-video" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-talking-video into .github/skills/magic-hour-talking-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-talking-video", 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-talking-video -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-talking-video --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-talking-video .opencode/skills/magic-hour-talking-video && 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-talking-video" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/magichourhq/skills/skills/magic-hour-talking-video into .opencode/skills/magic-hour-talking-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "magic-hour-talking-video", 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-talking-video- GitHub stars
- 1.3k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 769 words
- Files
- 4 (incl. references)
- Skills in repo
- 716
- Repo updated
- First seen
- Licence
- MIT
At a glance
Make a portrait speak, react or perform supplied audio with Magic Hour, or lip-sync an existing video to replacement speech.
- Character dialogue
- SKILL.md covers Select the source and route, Lock speech and timing and Create, caption and inspect
- Reaches mcp.magichour.ai
- Presenters and language versions with audio-first timing
What it does
Magic Hour Talking Video is an agent skill from hashgraph-online/awesome-codex-plugins. Make a portrait speak, react or perform supplied audio with Magic Hour, or lip-sync an existing video to replacement speech. Use for character dialogue, talking photos, presenters and language versions with audio-first timing; not generic text-to-video.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml` and `references/localization.md`).
It sits in Media & Creative, covering AI video generation. It works with React. 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
- Character dialogue
- Presenters and language versions with audio-first timing
- Not generic text-to-video
Example prompts
- “/magic-hour-talking-video”
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 Talking Video loads about 1.6k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 769 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). 769 words, ~1,605 tokens.
Download SKILL.mdSave it as
.claude/skills/magic-hour-talking-video/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- magic-hour-talking-video
- description
- Make a portrait speak, react or perform supplied audio with Magic Hour, or lip-sync an existing video to replacement speech. Use for character dialogue, talking photos, presenters and language versions with audio-first timing; not generic text-to-video.
- license
- MIT
- metadata.author
- magichourhq
- metadata.version
- 1.2.0
Magic Hour talking video
Approve the spoken result before paying to animate a face. Lip sync cannot fix a mispronounced name or a sentence cut off by the timeline.
Use the supplied portrait, speech and language without asking for them again. Choose technical settings and perform delegated creative checks yourself; respect requested script/voice approvals and the existing total budget. Show the finished clip first, with an outstanding listening or language check made explicit. For recurring presenters or language versions, read speech and localization.
Select the source and route
| Input and intent | Route |
|---|---|
| Portrait plus speech | ai_talking_photo_create_talking_photo |
| Existing speaker video plus replacement speech | lip_sync_create_video |
| Script with no recording | ai_voice_generator_create_audio, review audio, then the relevant video route |
| Voiceover on unrelated footage, no visible speaker | Compose narration over footage; do not add lip-sync generation |
Use authorized portrait, video and voice material. A preset's availability does not establish a speaker's endorsement. Prefer supplied speech when its performance is already accepted. For a portrait, favor a visible, unobstructed mouth and an angle suitable for the requested result; a stylized face or extreme profile needs its own quality check.
Lock speech and timing
Preserve the exact script, language, names and claims. Obtain a supported voice_name from the live schema; do not invent a voice ID or pass voice-direction controls the endpoint lacks. Keep stage directions out of the spoken text unless the user wants them read aloud. Use punctuation for phrasing; if the take is too long, revise only with authorization rather than truncating it.
Listen to the completed audio for pronunciation, pacing, silence and the final word. Measure its actual duration. If a script exceeds current limits, divide at sentence boundaries and keep the same voice across segments; do not divide inside a word or assume independently generated segments join naturally.
For talking photo, pass assets.image_file_path and assets.audio_file_path. The interval describes the input audio. Select the current generation mode for the requirement: the schema distinguishes likeness-oriented and prompt-controlled modes, and scene prompts may be ignored in other modes. Check the mode's duration limit.
For a character reaction or punchline, infer the intended delivery from the supplied performance; preserve its pauses and final word. Choose realistic when likeness is the priority. Use prompted only when its scene/motion control is needed; its prompt is ignored in realistic mode. A singing portrait needs its own mouth/timing review on the actual sung audio. Do not claim singing quality from a spoken example or generate a new soundtrack when one was supplied.
For lip sync, provide assets.audio_file_path, assets.video_source and its corresponding video field. Check the selected interval and whether enough source video exists. Do not loop a speaking face or cut the last sentence to hide a mismatch. Inspect the resulting alignment rather than assuming audio and video offsets behave identically across endpoints.
Show full SKILL.md (306 more words)Show less
Create, caption and inspect
Use the creation MCP at https://mcp.magichour.ai/; setup. API routes are /v1/ai-voice-generator, /v1/ai-talking-photo, /v1/lip-sync and optionally /v1/auto-subtitle-generator; read the live schema. Budget speech, video and requested captions together before starting; do not add music, cloning or extra takes merely because available.
Upload local media with video_assets_generate_presigned_url, PUT raw bytes to its upload_url without the API bearer token, and use file_path. Submit each job once, retain its ID, then use wait_for_audio_project or wait_for_video_project. Resume retrieval after a timeout; never blindly retry a creation POST. Preserve exact download URLs and keep durable files.
Add captions only after the picture and speech are accepted. The subtitle endpoint needs a style template or valid custom configuration; inspect the current required fields. Check every proper noun and number against the actual speech, then inspect timing and face/CTA overlap. Do not promise an editable transcript or SRT unless the endpoint returns one. Keep the clean master separately.
Watch and listen to the whole result. Check mouth closures against audible consonants, sync after pauses, jaw/teeth artifacts, face stability during turns, audio continuity and the complete final word. Static frames cannot prove lip sync. If playback or hearing is unavailable, disclose that validation gap rather than declaring a pass.
Probe the downloaded file before captioning or assembly. Our Talking Photo and Lip Sync runs include the full-duration audio streams, but show changed dimensions, a frame-rate mismatch with project metadata and a Lip Sync video stream slightly shorter than its audio. Preserve the last word; do not use the shorter stream as an automatic trim boundary. Those examples have frame and stream checks, with listening and synchronization review still outstanding.
Deliver the video, approved audio/script, project IDs, and optional captioned version. Retain the accepted portrait, voice choice and pronunciation notes for the next clip. Caption and multilingual quality still need separate 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 3 other files (references) in plugins/magichourhq/skills/skills/magic-hour-talking-video of hashgraph-online/awesome-codex-plugins.
- SKILL.md
- LICENSE
- agents/openai.yaml
- references/localization.md
Open the folder on GitHubat commit 3e1456a
Compare with similar skills
Magic Hour Talking Video 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 Talking Video this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Anything2explainerVincentwei1021/anything2explainer | 2.4k | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Remotion Motion Graphicshaidrrrry/claude-remotion-skill | 340 | — | ~2k | Automated safety check: Pass | MIT | |
| Edit Timeline StudioMartinDelophy/ai-video-editor | 905 | — | ~7k | Automated safety check: Pass | MIT | |
| Develop Timeline Studio PluginMartinDelophy/ai-video-editor | 905 | — | ~989 | Automated safety check: Pass | MIT | |
| Varg Video GenerationvargHQ/sdk | 340 | — | ~788 | Automated safety check: Notes | MIT |
Similar skills
Remotion Motion Graphics
haidrrrry/claude-remotion-skill
Create and edit professional motion graphics videos with Remotion (React-based video).
Edit Timeline Studio
MartinDelophy/ai-video-editor
Analyze images, video, speech, motion, products, and websites; route local vision, audio, depth, tracking, matting, identity, and restoration models; auto-edit, replicate, enhance, caption, voice…
Develop Timeline Studio Plugin
MartinDelophy/ai-video-editor
Design, evaluate, implement, or review image and video generation connectors for Timeline Studio.
Varg Video Generation
vargHQ/sdk
Generate AI videos using varg SDK React engine. An agent skill from vargHQ/sdk.
Edit Timeline Studio Browser
MartinDelophy/ai-video-editor
Use native WebMCP tools to edit the project open in Timeline Studio.
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
Works with
Categories
Questions about Magic Hour Talking Video
What does Magic Hour Talking Video do?
Make a portrait speak, react or perform supplied audio with Magic Hour, or lip-sync an existing video to replacement speech. Magic Hour Talking Video is an agent skill from hashgraph-online/awesome-codex-plugins. Make a portrait speak, react or perform supplied audio with Magic Hour, or lip-sync an existing video to replacement speech.
When should I use Magic Hour Talking Video?
Magic Hour Talking Video fits situations like: character dialogue; presenters and language versions with audio-first timing; not generic text-to-video.
How do I install Magic Hour Talking Video in Claude Code?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill magic-hour-talking-video -a claude-code`. Or copy the skill folder (plugins/magichourhq/skills/skills/magic-hour-talking-video in hashgraph-online/awesome-codex-plugins) into .claude/skills/magic-hour-talking-video in your project. Claude Code loads it when a task matches its description.
How do I install Magic Hour Talking Video in Codex?
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill magic-hour-talking-video -a codex`. Or copy the skill folder (plugins/magichourhq/skills/skills/magic-hour-talking-video in hashgraph-online/awesome-codex-plugins) into .agents/skills/magic-hour-talking-video in your project. Codex loads it when a task matches its description.
Can I use Magic Hour Talking Video 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-talking-video -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-talking-video, .gemini/skills/magic-hour-talking-video, .github/skills/magic-hour-talking-video and .opencode/skills/magic-hour-talking-video in your project.
What does Magic Hour Talking Video need to run?
SKILL.md names no scripts, command-line tools or credentials: Magic Hour Talking Video is instructions for the agent only.
Does Magic Hour Talking Video 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 Talking Video 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 Talking Video use?
Magic Hour Talking Video 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 Talking Video use?
About 1.6k tokens (SKILL.md is roughly 6.4k 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 715 tokens, read only when the agent opens those files.
What are the alternatives to Magic Hour Talking Video?
Skills that share tags, products or a category with Magic Hour Talking Video: Anything2explainer (Vincentwei1021/anything2explainer, 2.4k stars), Remotion Motion Graphics (haidrrrry/claude-remotion-skill, 340 stars), Edit Timeline Studio (MartinDelophy/ai-video-editor, 905 stars) and Develop Timeline Studio Plugin (MartinDelophy/ai-video-editor, 905 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Magic Hour Talking Video?
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.