All skills
heygen-com avatar

/embedded-captions

@0a5e3c7
by HeyGenheygen-com/hyperframes55k stars
4,998

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

Requires /hyperframes

Use this Skill: https://skilld.dev/gh/heygen-com/hyperframes/embedded-captions

This session only. Nothing lands on disk.

referencesreference-bar.md

≈673 tokens on demand. Your agent reads this file only when SKILL.md points to it.

The reference bar — what world-class looks like

Self-review without an external bar always passes. Before shipping, hold the render against these references — not "is anything broken" (the gates did that) but "would a designer at these houses sign it".

Per register

premium-warm / editorial (cream, editorial) — the bar is a Vogue cover and the A24 title card: type interacts with the subject (masthead behind the head), one or two sizes feel chosen not defaulted, the frame would work printed as a poster. Check: does the climax frame, screenshotted alone, look like a designed cover — or like a subtitle that grew?

tech-premium (keynote, ink) — the bar is an Apple keynote slide over footage: opaque, weighty, dead-center confidence; negative space is doing the work; nothing decorating. Check: would this frame look at home in a WWDC sizzle?

formal (documentary) — the bar is Errol Morris / PBS Frontline: the type has the restraint of a court document; stillness reads as authority. Check: does ANY motion call attention to itself? If yes, cut it.

loud — the bar is a k-pop lyric video / Nike spot: type fights the subject and wins on purpose, color is saturated and scene-true, the beat hits WITH the word. Check: does the hero frame make you want to replay it?

The five positive checks (run on the preview sheet, after the failure checks)

  1. Poster test — screenshot the climax frame alone. Would you post it as a still? If it needs the motion to excuse the composition, the composition isn't done.
  2. Timid test — is any body caption apologizing (tiny, corner-parked, far from the silhouette)? Small is a choice; timid is a default. Hug the subject or commit to the margin as a designed column.
  3. One-glance hierarchy — at thumbnail size (shrink the sheet), can you still tell opener / body / hero apart? If the tiers blur together, the contrast ratios are off.
  4. Scene handshake — name three ways the type acknowledges THIS footage (accent sampled from the scene, occlusion crossing, shadow direction, depth blur, palette temperature). Fewer than two = it's a sticker, not an embed.
  5. Dead-air audit — scrub the no-caption stretches. Are they composed rests (subject carries the frame) or gaps (the design just stopped)? Rests are earned by rhythm; gaps are bugs in pacing.

How to use with fresh-eyes review

Give the sub-agent the preview sheet + the 5 failure checks (SKILL.md § Visual QA) + these 5 positive checks, and ask for verdicts on both lists. A render ships when it passes the failure checks AND at least 4/5 positive checks with specific evidence.

Source: SKILL.md on GitHub

No alerts3d3 checks · Risk SAFE
  • Gen Agent Trust Hub3d

    The skill is a professional video production tool for embedding cinematic captions into videos. It utilizes industry-standard tools like FFmpeg for audio/video processing, WhisperX for transcription, and Puppeteer for rendering. The skill includes built-in security features such as HTML sanitization of transcript data and Subresource Integrity (SRI) for external scripts.

  • Socket3d

    No alerts

  • Snyk3d

    Risk: LOW · No issues

Signed by skilld at 0a5e3c7. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 17 hours ago.

Activeupdated 4 days ago

README badge

README badge for heygen-com/hyperframes/embedded-captions