New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Captions Overlay Rules

by heygen-com in heygen-com/hyperframes

Rules for captioning talking-head and launch videos: classify each phrase as drop, rail or embed, and composite captions over the film instead of reserving space.

Apache-2.0Auto-check passedMedia & Creative

Install Captions Overlay Rules

skills CLI
$ npx skills add heygen-com/hyperframes --skill captions-overlay -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install heygen-com/hyperframes captions-overlay --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/heygen-com/hyperframes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/captions-overlay .claude/skills/captions-overlay && rm -rf skills-src

Use ~/.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/

Facts

Skill name
captions-overlay
GitHub stars
59k
Used in
1 other repo
Token cost
~1.5k tokens
SKILL.md length
693 words
Files
1
Skills in repo
32
Repo updated
First seen
Licence
Apache-2.0

At a glance

Rules for captioning talking-head and launch videos: classify each phrase as drop, rail or embed, and composite captions over the film instead of reserving space.

  • Adding captions or subtitles to a talking-head or launch video
  • SKILL.md covers The caption model — drop /…, The overlay law — captions are… and Why these two rules are one…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Deciding whether a phrase is dropped, shown on the rail or embedded

What it does

Every spoken phrase gets one of three fates. Filler such as um and stutters is dropped. Ordinary speech goes on the rail, a readable verbatim lower-third subtitle in front of the footage, where a punch word may get an accent highlight. A phrase promoted to embed becomes one large word composited behind the subject using matte occlusion, with a designed entrance and exit.

Embeds are meant to be scarce: at most one per beat, never two visible together, and spaced at least a beat apart, so a short clip usually carries one and a long explainer roughly one per section. The overlay rule says captions are composited on top of the frame, so you never move content up or leave an empty band for them, and compositions stay centered on the true frame center. It supplements the embedded-captions skill and describes Standard mode, while Cinematic mode drops the rail.

When your agent uses it

  • Adding captions or subtitles to a talking-head or launch video
  • Deciding whether a phrase is dropped, shown on the rail or embedded
  • Laying out a composition that will carry captions without a keep-out band
  • Centering a composition on the true frame center under captions

Example prompts

  • “Caption this launch video: show spoken lines on the rail and pick one phrase to embed behind the speaker.”
  • “Lay out the title scene so captions overlay it, with no reserved bottom band.”
  • “Go through this transcript and mark each phrase as drop, rail or embed.”

Requirements

  • The upstream embedded-captions skill

What it can do on your machine

Read from SKILL.md and the folder at commit 0c76e52. 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

    No URLs in SKILL.md.

    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

Captions Overlay Rules loads about 1.5k tokens when it runs. Until then it costs about 165 tokens; SKILL.md has 693 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~165
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 heygen-com/hyperframes at commit 0c76e52, republished under its Apache-2.0 licence (© heygen-com). 693 words, ~1,512 tokens.

Download SKILL.mdSave it as .claude/skills/captions-overlay/SKILL.md (or your agent's skills folder).
name
captions-overlay
description
Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether a phrase should be dropped, ride the verbatim rail, or be promoted to a scarce embedded climax, when laying out a composition that will carry captions (do NOT reserve a keep-out band), or when centering a composition on the true frame center under captions. Quotes the rail+embed model from embedded-captions and constraint
metadata.internal
true

Captions Overlay Doctrine

Overlay doctrine — supplements the upstream embedded-captions skill. Applies ON TOP of it; do not expect it folded into the upstream skill.

Two ideas combine here. First, the caption model — every spoken phrase is drop, rail, or embed, and embed is the scarce earned peak, not the default. Second, the overlay law — a caption line is composited ON TOP of the film as an overlay; it is NOT a reserved zone, so you never shift content up or leave a dead band to "make room" for it. The two reinforce each other: because captions ride as an overlay (the verbatim rail in front, the occasional embed behind the subject), the composition keeps its full frame and centers on the true vertical center.

The caption model — drop / rail / embed

Every spoken phrase is one of three things (verbatim from embedded-captions):

WhatHow it's shown
dropfiller — um/uh, stutters, self-correctionsnot shown
railthe default — ordinary spoken content (verbatim)clean lower-third subtitle, in front, readable. A punch word can get an inline emphasis highlight (accent colour / active-word pop) — it stays on the rail.
embeda promoted peak — the headline beatone big word composited behind the subject (matte occlusion), designed entrance + exit

The rail carries most of the text; embed is the scarce, earned peak — ≤1 per beat, never two adjacent/co-visible, spaced ≥ a beat apart. A short clip → usually one embed; a long explainer → ~one per section. Embedding every word is the common mistake.

This is the Standard mode shape (rail = the verbatim lower-third; embed = the climax composited behind the subject). Cinematic mode drops the rail and makes everything embed-style — use it only for pure-cinematic asks, never for explainer / voiceover where the words must read.

Rail-first, embed-scarce (the load-bearing rules)

Quoted from the embedded-captions non-negotiables:

  • Rail-first for talking-head / explainer. Don't embed the whole transcript — most text is the rail; embed only peaks. Embedding everything is the default mistake.
  • Embed is scarce + spaced. ≤1 embed per sentence/beat, never two adjacent or co-visible, ≥ a beat apart, at most one apex. climax = per-beat peak, not "the single payoff of the entire clip."
Show full SKILL.md (344 more words)Show less

The overlay law — captions are NOT a reserved band

In a generated launch composition, when captions are enabled, finalize composites a small, minimal word-by-word caption line as an overlay layer ON TOP of the whole film (a single text line, bottom-centered, roughly the bottom ~5-8% of canvas height). It is an overlay, not a reserved zone (verbatim from constraint #13 of the product-launch-video scene agent):

  • Center the composition on the TRUE vertical center — y = H / 2 (landscape 540, portrait 960). Do not shift content up to "make room" for captions; a composition centered at 0.42 × H with a dead lower band is the bug, not the fix.
  • Content may extend to the canvas bottom. Full-bleed subjects, rails, and backgrounds all welcome.
  • One soft courtesy rule: avoid parking critical small readable text (a URL line, a legal line, a sub-caption) exactly in the bottom ~80px center span where the caption line sits — the overlay would fight it. Large imagery / cards / ambient content under the captions is fine; the caption skin is designed to read over content.
  • There is no machine keep-out gate (the old captions.mjs keepout check is retired). Finalize snapshot QA judges caption-over-content legibility visually.

When captions are disabled: identical positioning freedom — the overlay simply doesn't exist.

Why these two rules are one doctrine

The model says the rail rides in front and an embed is a rare word composited behind the subject — both are layers added to footage that ships untouched. The overlay law says the caption line is a layer composited on top of the whole film, not a band carved out of the layout. So in both the captioning pipeline and the launch-video pipeline, captions are an overlay you add, not a zone you reserve:

  • Keep the full frame; center on true center; let content run to the edges.
  • Make the rail (or the small overlay caption line) carry the verbatim words.
  • Promote a word to an embed only at a genuine peak — scarce, spaced, never two at once.
  • Reserve nothing; judge legibility of captions-over-content visually, not by a keep-out gate.

© heygen-com, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/captions-overlay of heygen-com/hyperframes.

Open the folder on GitHubat commit 0c76e52

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in heygen-com/hyperframes, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Captions Overlay Rules 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.

Captions Overlay Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Captions Overlay Rules this skillheygen-com/hyperframes59k1 repos~1.5kAutomated safety check: PassApache-2.0
Short Form Editnateherkai/hyperframes-student-kit1.2k—~5.3kAutomated safety check: PassCustom licence
3D Camera Captions for HyperFramesheygen-com/hyperframes-community-skills1781 repos~2.3kAutomated safety check: PassApache-2.0
Plotbeat Data VideosUnclecheng-li/AI_Animation1.5k—~2.6kAutomated safety check: PassMIT
Yuv Viral Videohoodini/ai-agents-skills281—~7.5kAutomated safety check: NotesNone
HyperFrames Studio Timeline Conventionsedenfunf/reelmimic1.7k1 repos~916Automated safety check: PassMIT

Similar skills

  • Short Form Edit

    nateherkai/hyperframes-student-kit

    Turn talking-head footage into a finished reel, YouTube Short, or short advertisement with curiosity-led openings, earned payoffs, story-driven cuts, transcript-synced motion graphics, moving…

    1.2k GitHub stars~5.3k tokensUpdated 10 days ago
    Media & CreativeAuto-check passed

  • 3D Camera Captions for HyperFrames

    heygen-com/hyperframes-community-skills

    Builds captions that move in 3D space around a talking head: a virtual camera flies past words at different depths, hero words hide behind the speaker, and text steps at 15 fps with motion blur.

    178 GitHub starsUsed in 1 repo~2.3k tokens
    Media & CreativeAuto-check passed

  • Plotbeat Data Videos

    Unclecheng-li/AI_Animation

    Turns a local CSV or JSON file, or data fetched from an approved source, into an editable data-visualization video by adapting HyperFrames templates.

    1.5k GitHub stars~2.6k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

  • Yuv Viral Video

    hoodini/ai-agents-skills

    Edit any selfie or screen-share footage into a viral short-form video in YUV.AI's signature style — Apple-style liquid-glass cards (real CSS backdrop-filter), dark-mode polish, MrBeast-paced cuts…

    281 GitHub stars~7.5k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes

  • HyperFrames Studio Timeline Conventions

    edenfunf/reelmimic

    Conventions for laying out a HyperFrames project so it opens as a readable Studio timeline: one caption track, one element kind per track, scenes as sub-compositions, and safe zones.

    1.7k GitHub starsUsed in 1 repo~916 tokens
    Media & CreativeAuto-check passed

  • Short Form Video

    nateherkai/hyperframes-student-kit

    Maintain the existing May Shorts teaching compositions using their legacy face-mode, scene-overlay, and karaoke-caption patterns.

    1.2k GitHub stars~5k tokensUpdated 10 days ago
    Media & CreativeAuto-check passed

More from heygen-com/hyperframes

All 32 skills in this repo

  • HyperFrames Animation

    heygen-com/hyperframes

    Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.

    59k GitHub starsUsed in 3 repos~2.1k tokens
    Auto-check passed

  • Embedded Video Captions

    heygen-com/hyperframes

    Adds captions to a single-subject talking-head video without editing the footage, from plain subtitles to cinematic text placed behind the speaker.

    59k GitHub starsUsed in 3 repos~8.6k tokens
    Auto-check passed

  • Weekly Changelog Video

    heygen-com/hyperframes

    Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.

    59k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Faceless Explainer Video

    heygen-com/hyperframes

    Turns an article, notes or a topic brief into an explainer video whose visuals are invented per scene, built frame by frame in HyperFrames with no footage.

    59k GitHub starsUsed in 3 repos~7.7k tokens
    Auto-check: notes

  • Figma to HyperFrames

    heygen-com/hyperframes

    Imports Figma assets, brand tokens, components and motion into a HyperFrames video composition, using the Figma REST API with a connector or native export for shaders.

    59k GitHub starsUsed in 3 repos~4.5k tokens
    Auto-check: notes

  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    59k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Captions Overlay Rules

What does Captions Overlay Rules do?

Rules for captioning talking-head and launch videos: classify each phrase as drop, rail or embed, and composite captions over the film instead of reserving space. Every spoken phrase gets one of three fates. Filler such as um and stutters is dropped.

When should I use Captions Overlay Rules?

Captions Overlay Rules fits situations like: adding captions or subtitles to a talking-head or launch video; deciding whether a phrase is dropped, shown on the rail or embedded; laying out a composition that will carry captions without a keep-out band; centering a composition on the true frame center under captions.

How do I install Captions Overlay Rules in Claude Code?

Run `npx skills add heygen-com/hyperframes --skill captions-overlay -a claude-code`. Or copy the skill folder (.agents/skills/captions-overlay in heygen-com/hyperframes) into .claude/skills/captions-overlay in your project. Claude Code loads it when a task matches its description.

How do I install Captions Overlay Rules in Codex?

Run `npx skills add heygen-com/hyperframes --skill captions-overlay -a codex`. Or copy the skill folder (.agents/skills/captions-overlay in heygen-com/hyperframes) into .agents/skills/captions-overlay in your project. Codex loads it when a task matches its description.

Can I use Captions Overlay Rules 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 heygen-com/hyperframes --skill captions-overlay -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/captions-overlay, .gemini/skills/captions-overlay, .github/skills/captions-overlay and .opencode/skills/captions-overlay in your project.

What does Captions Overlay Rules need to run?

SKILL.md names no scripts, command-line tools or credentials: Captions Overlay Rules is instructions for the agent only. Our summary lists: The upstream embedded-captions skill.

Does Captions Overlay Rules access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Captions Overlay Rules 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 Captions Overlay Rules use?

Captions Overlay Rules is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Captions Overlay Rules use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Captions Overlay Rules?

Skills that share tags, products or a category with Captions Overlay Rules: Short Form Edit (nateherkai/hyperframes-student-kit, 1.2k stars), 3D Camera Captions for HyperFrames (heygen-com/hyperframes-community-skills, 178 stars), Plotbeat Data Videos (Unclecheng-li/AI_Animation, 1.5k stars) and Yuv Viral Video (hoodini/ai-agents-skills, 281 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Captions Overlay Rules?

heygen-com (a GitHub organization) maintains it in heygen-com/hyperframes, which has 58,669 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on October 8, 2026.

Source: heygen-com/hyperframes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.