Lyric Video Director
Use when creating a stylized lyric video from a song file, lyrics, and rough lyric timings. Directs the complete workflow: normalize timings, analyze musical gaps and song structure, establish a visual bible, use GPT Image 2 to design creative final typography compositions and reference assets, animate words and graphic elements with Gemini Omni Flash reference-to-video, preserve exact lyrics through adaptive text-safety, assemble against the untouched master song, and verify synchronization, legibility, spelling, coverage, and audiovisual quality. Also use for kinetic-typography and instrumen
Install
npx skills add ShadoW-Shinigami/lyric-video-director --skill lyric-video-directorgit clone --depth 1 https://github.com/ShadoW-Shinigami/lyric-video-director.git /tmp/lyric-video-director
mkdir -p ~/.claude/skills
cp -r /tmp/lyric-video-director/. ~/.claude/skills/lyric-video-directorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Lyric Video Director ## Overview Create a lyric video as a coherent piece of music direction, not a slideshow of unrelated captions. The lyric must remain correct, the edit must serve the song, and every flourish must earn its place. The expected minimum input is: 1. A song file. 2. Lyrics. 3. Rough start/end timing for each lyric line. The pipeline analyzes the entire song, accounts for every instrumental gap, locks a visual language, uses **GPT Image 2** to design creative final typography compositions and reusable reference assets, animates words and graphic systems with **Gemini Omni Flash reference-to-video**, discards generated audio, and composites the visuals against the user's untouched song. **Default visual grammar for typography-led work:** the lyric is the protagonist. Build rapid composition resets, word-object metaphors, mixed-media graphic systems, spatial typography, illustration, and recurring visual motifs. Do not default to portrait-led cinematic scenes with captions laid beside them. **Default generation route:** use `mcp__fal_omni__omni_reference_to_video` with an ordered set of uploaded GPT Image 2 references and bind them explicitly as `<IMAGE_REF_0>`, `<IMAGE_REF_1>`, and so on. Use image-to-video only when the user asks for a single-keyframe animation or when a shot genuinely requires one fixed composition.
Details
- Skill name
lyric-video-director- Repository
- ShadoW-Shinigami/lyric-video-director
- License
- MIT
- Repo updated
- 11 July 2026
FAQ
What does the Lyric Video Director skill do?
Use when creating a stylized lyric video from a song file, lyrics, and rough lyric timings. Directs the complete workflow: normalize timings, analyze musical gaps and song structure, establish a visual bible, use GPT Image 2 to design creative final typography compositions and reference assets, animate words and graphic elements with Gemini Omni Flash reference-to-video, preserve exact lyrics through adaptive text-safety, assemble against the untouched master song, and verify synchronization, legibility, spelling, coverage, and audiovisual quality. Also use for kinetic-typography and instrumen
How do I install the Lyric Video Director skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ShadoW-Shinigami/lyric-video-director --skill lyric-video-director. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Lyric Video Director popular?
It lives in ShadoW-Shinigami/lyric-video-director, which has 47 GitHub stars and 8 forks.
Related skills
Motion Video
48farhan-syah/motion-video-skill
Turn a short brief, plus optional screenshots, design references, logo, music, footage or voiceover, into a directed motion-graphics MP4. Works from the user's material and researches only the gaps, directs a concept, builds HTML/CSS/SVG scenes and renders them frame-exact with headless Chromium and ffmpeg, with synthesized motion sound effects. Use for product teasers and launches, feature explainers, app demos, tutorials and lessons, data stories, event and announcement videos, social reels and ads, kinetic typography, isometric or keynote-style videos, and music-synced edits. Not for static
Call Me
27radres/call-me
Call or text your human's actual phone (iPhone or Android) and handle replies from the /call-me app. Use when the user says "call me", "ring me", "phone me if something comes up", "text my phone", asks the agent to stay reachable, wants something read out loud (an update, a summary of the day ahead), or sends an inbound /call-me message or voicemail. The phone rings through CallKit, spoken answers return as transcripts, and channel-enabled hosts deliver later messages directly into the active agent session.
Podcast Transcript Txt
47KingJing1/podcast-transcript-txt-skill
Deterministic workflow to find and export full podcast transcripts as cleaned TXT files from YouTube URLs, episode webpages (including Xiaoyuzhou), Apple Podcasts title search, X/Twitter links, direct audio URLs, or plain episode titles. Use when users ask for 逐字稿/文字版/transcript/txt and want minimal trial-and-error.
Package Talking Head Video
48zhouyuechuan2025-ui/ai-self-media-video-packaging-skill
Use when packaging center-presenter talking-head video plus SRT into an MP4, or SRT into a transparent overlay, with source-based copy and verified delivery.
Music Mv
56Win-Hao/music-mv
用代码给一首歌做一支音乐 MV（不用视频生成模型）：先把歌听懂（歌词时间轴、节拍、情绪起落、别人怎么理解这首歌），再定画风、画角色、写剧本和分镜、先出草图再做整片，最后照清单看片修改；也能先拆一支参考视频的风格再照着做。画面用 Canvas / p5.js / p5.brush 一帧一帧画，HyperFrames 合成歌词和歌。用户说「给这首歌做个 MV」「做一支音乐 MV / 歌词 MV / 动画 MV」「学这个视频的风格做一支 MV」，或 make a music video / lyric video for this song 时使用。不限模型，能读写文件、跑命令的 agent 都能照做。
Drawing Analyzer
50hamzaabduljabbar/construction-drawing-analyzer
Pre-process construction drawing PDF sets into structured text indexes so Claude can answer questions faster, cheaper, and more accurately. Use this skill whenever a user mentions construction drawings, PDF drawings, takeoffs, drawing sets, plans, or wants to extract information from construction documents. Trigger on phrases like "analyze my drawings", "run drawing analyzer", "process these drawings", "how many footings", "what is the slab area", or any question about quantities, elements, or scope from a set of construction drawings. This skill runs once on a drawing set and creates lightwei
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.