Captions and Music Bed
Generate, style, preview, and burn captions, and build music/percussion beds with ducking, loop/tail selection, fade-outs, and final silence. Use when captions are requested, captions are out of sync, subtitle style needs approval, background music competes with voiceover, or music must start/end at exact moments.
Install
npx skills add saranambiar/hyperframes-video-agent-skills --skill captions-and-music-bedgit clone --depth 1 https://github.com/saranambiar/hyperframes-video-agent-skills.git /tmp/hyperframes-video-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/hyperframes-video-agent-skills/skills/captions-and-music-bed ~/.claude/skills/captions-and-music-bedPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Captions And Music Bed Use this skill after the narration timeline is stable. ## Captions Caption source rules: - Use the user's script as wording source. - Use the final narration-only master as timing source. - Preserve punctuation and capitalization. - Show one caption line at a time. - Start the caption when the first word is spoken. - Avoid captions over silent hooks or silent CTA holds unless requested. Preview style before burning the full video when style changes. Read `references/caption-rules.md` for timing and style guidance. ## Caption Style Defaults - Bottom center. - White text. - Translucent dark backing. - Generous bottom margin. - Font size small enough not to dominate UI. - One line only; split long sentences into natural phrase chunks. Use `templates/caption-style.ass` as a starter. ## Music Bed Music source rules: - Start from a chosen offset when the intro of the source track is weak. - Keep hook music audible if there is no voiceover. - Duck under narration. - Do not raise music during later narration pauses if the user says it is distracting. - End music at the requested time, including final silence if requested. - If the music source ends early, restart from a musically useful tail section. Read `references/music-ducking.md` for FFmpeg patterns. ## QA - Listen to start, middle, and final tail. - Check music is present and audible, not merely technically in the stream. - Confirm no clipped narration.
Details
- Skill name
captions-and-music-bed- Repository
- saranambiar/hyperframes-video-agent-skills
- Path
skills/captions-and-music-bed/SKILL.md- License
- Apache-2.0
- Repo updated
- 14 June 2026
FAQ
What does the Captions and Music Bed skill do?
Generate, style, preview, and burn captions, and build music/percussion beds with ducking, loop/tail selection, fade-outs, and final silence. Use when captions are requested, captions are out of sync, subtitle style needs approval, background music competes with voiceover, or music must start/end at exact moments.
How do I install the Captions and Music Bed skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add saranambiar/hyperframes-video-agent-skills --skill captions-and-music-bed. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Captions and Music Bed popular?
It lives in saranambiar/hyperframes-video-agent-skills, which has 48 GitHub stars and 0 forks.
Related skills
Audio Sync Assembly
48saranambiar/hyperframes-video-agent-skills
Build and revise FFmpeg-based video assemblies from scene renders and narration, including audio probing, scene retiming, pauses, trim/concat, setpts, atempo, phrase-to-visual cue alignment, and final timeline manifests. Use when narration length, visual beats, product moments, or scene boundaries must sync precisely.
End to End Video Playbook
48saranambiar/hyperframes-video-agent-skills
End-to-end video production workflow for coding agents using HyperFrames, FFmpeg, captions, audio sync, music beds, and render QA. Use when a user asks for a complete video, multi-scene edit, launch video, product/demo video, UGC-style edit, enterprise explainer, or final assembled MP4 from prompt/script/assets.
Hyperframes Scene Builder
48saranambiar/hyperframes-video-agent-skills
Create and revise HyperFrames HTML video compositions with CSS, GSAP timelines, composition IDs, reusable components, render commands, and proof-frame validation. Use when an agent needs to build a scene, edit a composition, render HyperFrames output, or debug HyperFrames-specific scene behavior.
Haizei Agnes Image Gen
43wuchubuzai2018/expert-skills-hub
图片生成技能,当用户需要生成图片、视觉信息图、创建图像、编辑已有图片时使用此技能。基于Agnes AI官方API的Agnes Image 2.1 Flash模型(agnes-image-2.1-flash)的图片生成服务
Apiyi Gpt Image 2 Gen
43wuchubuzai2018/expert-skills-hub
图片生成技能,当用户需要生成图片、视觉信息图、创建图像、编辑/修改/调整已有图片时使用此技能。基于API易平台(https://api.apiyi.com/)的ChatGPT Image 2模型(gpt-image-2)的官方正式版图片生成服务。该模型支持精确的尺寸/画质控制(含4K),按token计费。与gpt-image-2-all(官逆版)不同的关键点:使用/v1/images/generations和/v1/images/edits端点;有显式size参数;有quality参数;按token计费;使用multipart/form-data上传参考图;b64_json为纯base64无前缀。
Image Resizer
43wuchubuzai2018/expert-skills-hub
图片尺寸调整和压缩工具技能。用于按指定像素宽高、比例或最大尺寸限制调整图片大小,并支持智能压缩到指定文件大小。适用于需要批量处理图片、生成特定尺寸缩略图、压缩图片以满足文件大小限制等场景。
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.