HyperFrames Video Entry Point
heygen-com/hyperframes
Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.
A skill your agent uses when turning product links, app store listings, landing pages, or product briefs into advertising videos with Remotion or Hyperframes projects, storyboards, render-engine…
$ npx skills add leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install leosssvip-dot/remotion-ad-video-skill remotion-ad-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/leosssvip-dot/remotion-ad-video-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/remotion-ad-video .claude/skills/remotion-ad-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 "remotion-ad-video" agent skill from https://github.com/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-video into .claude/skills/remotion-ad-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remotion-ad-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/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-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 leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install leosssvip-dot/remotion-ad-video-skill remotion-ad-video --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leosssvip-dot/remotion-ad-video-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/remotion-ad-video .agents/skills/remotion-ad-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 "remotion-ad-video" agent skill from https://github.com/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-video into .agents/skills/remotion-ad-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remotion-ad-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 leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install leosssvip-dot/remotion-ad-video-skill remotion-ad-video --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leosssvip-dot/remotion-ad-video-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/remotion-ad-video .cursor/skills/remotion-ad-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 "remotion-ad-video" agent skill from https://github.com/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-video into .cursor/skills/remotion-ad-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remotion-ad-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/leosssvip-dot/remotion-ad-video-skill.git --path skills/remotion-ad-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 leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install leosssvip-dot/remotion-ad-video-skill remotion-ad-video --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leosssvip-dot/remotion-ad-video-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/remotion-ad-video .gemini/skills/remotion-ad-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 "remotion-ad-video" agent skill from https://github.com/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-video into .gemini/skills/remotion-ad-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remotion-ad-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 leosssvip-dot/remotion-ad-video-skill remotion-ad-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 leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/leosssvip-dot/remotion-ad-video-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/remotion-ad-video .github/skills/remotion-ad-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 "remotion-ad-video" agent skill from https://github.com/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-video into .github/skills/remotion-ad-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remotion-ad-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 leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-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 leosssvip-dot/remotion-ad-video-skill remotion-ad-video --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leosssvip-dot/remotion-ad-video-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/remotion-ad-video .opencode/skills/remotion-ad-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 "remotion-ad-video" agent skill from https://github.com/leosssvip-dot/remotion-ad-video-skill/tree/main/skills/remotion-ad-video into .opencode/skills/remotion-ad-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "remotion-ad-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.
remotion-ad-videoA skill your agent uses when turning product links, app store listings, landing pages, or product briefs into advertising videos with Remotion or Hyperframes projects, storyboards, render-engine…
Remotion Ad Video is an agent skill from leosssvip-dot/remotion-ad-video-skill. Use when turning product links, app store listings, landing pages, or product briefs into advertising videos with Remotion or Hyperframes projects, storyboards, render-engine props/variables, render QA, and handoff assets.
Its SKILL.md is about 6.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 51 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/hyperframes-template/README.md` and `assets/hyperframes-template/package.json`).
It sits in Media & Creative, covering Video production, Motion graphics and Landing pages. It works with Remotion and HeyGen. The repository describes itself as: Create Remotion ad video projects from a URL with an AI coding agent, no video-generation AI required. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e734c02. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
npxnodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Remotion Ad Video loads about 6.3k tokens when it runs, and up to ~33k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 3,307 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.
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); the scripts in this folder are not scanned.
The full file from leosssvip-dot/remotion-ad-video-skill at commit e734c02, republished under its MIT licence (© leosssvip-dot). 3,307 words, ~6,294 tokens.
.claude/skills/remotion-ad-video/SKILL.md (or your agent's skills folder). This skill also uses 46 other files; get the full folder from GitHub.Use this skill to make performance-oriented ad videos with an AI agent plus a deterministic code renderer. The agent owns the creative and production workflow. Remotion is the default renderer; Hyperframes is supported when the user asks for HTML-based video authoring or an existing Hyperframes project.
Use for:
Do not use for:
Asset and claim policy (default to pragmatic, not restrictive):
Collect only the source material needed for the ad. For URLs, inspect the live page when tools are available; otherwise ask for product name, target customer, core offer, screenshots, logo, and brand constraints.
Load references/ad-intake.md when source quality, claim safety, or asset rights are unclear.
Load references/ad-brief-contract.md for every URL job before storyboard or code. Create or update ad-brief.json after source classification and keep preflight answers/defaults there.
Load references/asset-harvest.md for URL-based jobs before writing the storyboard.
Load references/fast-test-workflow.md for skill tests, first-pass iterations, or when the user cares about speed.
Load references/hyperframes-output.md when the user asks for Hyperframes, the target repo already uses Hyperframes, open-source renderer licensing is a priority, or ad-brief.json has renderEngine: "hyperframes".
Load references/preflight-questionnaire.md for URL-only jobs before storyboard or code. Ask exactly two required preflight choices first: format and creative route. Only skip questions when the user explicitly asks for no questions, fastest possible defaults, or a benchmark run with inferred defaults. Ask optional follow-ups only after those choices, and only when they materially change the ad.
Load references/platform-presets.md when the user needs to choose vertical, square, or landscape output.
Load references/industry-angle-library.md when the product category is not obviously covered by games or social-feed patterns.
Load references/game-ad-patterns.md for casual games, mobile games, app-store game listings, puzzle games, hypercasual games, or simple gameplay loops.
Load references/social-feed-ad-patterns.md for short-video, social, creator, UGC, live shopping, community, or content-feed apps.
Load references/variant-system.md when the user wants options, batch ads, or a commercial-quality ad rather than a single sample.
Load references/motion-language.md before implementing motion in either engine; it is the ease, stagger, and kinetic-typography vocabulary (Remotion src/motion.ts + KineticText, or GSAP for Hyperframes) that keeps motion from defaulting to flat linear interpolation.
Language policy:
format and creativeRoute questions in Chinese even when the source URL is English.interactionLanguage, sourceLanguage, and outputLanguage in ad-brief.json. Only change outputLanguage when the user explicitly asks for a different video language.Required decisions:
Recorded defaults, not required user decisions:
sfx-only for quick URL jobs, fast tests, and first-pass iterations. Commercial-quality, batch, or "make it more creative" requests default to a full soundscape — music-sfx plus a scripted voiceover — without asking. A bold ad with no voice and one repeated click sounds thin. Still ask only if the user requests silent-safe, a specific music plan, or a platform-specific sound plan.Minimum URL jobs must attempt to harvest favicon, touch icon, Open Graph image, visible logo or screenshots, and brand colors. Ecommerce product URLs must also attempt a product main image with scripts/harvest-ecommerce-assets.mjs before creative work starts; the linked item is the ad subject, and platform/store context stays secondary. Store usable public assets locally in the generated project public/<brand>/ folder, create or update an asset manifest when practical, and reference assets with staticFile().
Run scripts/classify-ad-source.mjs for URL jobs before creative work, passing --interaction-language <current-user-language> when known, --project-dir <target-project> when working inside an existing project, and --render-engine remotion|hyperframes only when the user explicitly chose one. Otherwise let --render-engine auto detect the engine. Write its output to ad-brief.json when a project directory exists. The brief is the source of truth for source type, language plan, render engine, render-engine reason, preflight defaults or answers, format, audio mode, blockers, and asset requirements. If ad-brief.json has blockers, includes preflight_answers_required, render_engine_choice_required, render_engine_install_required, or assetPlan.status is blocked/user_required, stop and ask for the missing decision or asset. Use interactionPlan.choiceQuestions for the first creative preflight step: ask only format and creative route first, in interactionLanguage. If the agent supports structured choice UI, present the choices there; otherwise use a text fallback with the same options. Audio defaults to audible synced SFX; ask about audio only when the user requests silent-safe, music, voiceover, or a platform-specific sound plan. Do not front-load the longer open-question list. Use --preflight-mode defaults only when the user explicitly approved skipping questions.
Pick one primary ad angle before writing scenes. Load references/creative-direction.md before implementation to avoid static slide-deck output. Start from an insight (the one true customer tension or surprising approved fact), not from the template.
Tag claims as observed (on-page facts plus public store metrics like rating, downloads, and review count), user_supplied, inferred, or blocked. Render observed and user_supplied freely — including real public store numbers attributed to the store. Do not render inferred or blocked numbers, and never fabricate or inflate a figure.
Every real commercial sample needs a thumb-stopping visual idea, not just copy. Examples: chat bubbles becoming completed tasks, before/after workflow collapse, a product screenshot exploding into features, or a terminal command triggering visible automation.
Every concept also needs a bold layout idea before storyboard or code: poster-scale type, one dominant visual, asymmetric composition, aggressive crop, oversized product/app frame, kinetic split screen, or a staged reveal. Avoid neat centered slide layouts unless the contrast or motion makes them feel like an ad.
Default to bold. A tasteful, restrained, presentation-safe ad loses the scroll. Push each concept past comfortable: dramatize the feeling with at least one spectacle move (surreal-scale, impossible-physics, world-bend, hyperbolic-before-after, maximal-kinetic-burst, dramatized-stakes, ui-comes-alive, or time-break — the spectacleMove enum) so there is a "wait, what?" beat. Exaggeration lives in the visual and emotional register only — every numeric and factual claim stays honest and source-backed. Load references/creative-direction.md (Bold By Default) and references/ad-exemplars.md (Spectacle / Exaggeration Mechanics) for the mechanics.
When source-backed numeric proof exists, plan it as motion instead of static copy: ratings count up, discounts snap from 0 to the final percent, prices or savings roll into place, download/review counts tick upward, and scores burst like a game HUD. Use the exact approved number as the final value and never animate unsupported or inflated claims.
For simple games, especially app-store listings, the visual idea should usually be a gameplay-style simulation: falling pieces, swaps, merges, collisions, score pops, explosions, level-up moments, near-fail rescues, or reward cascades. Static screenshots alone are proof assets, not the ad.
For short-video, creator, or social-feed apps, the visual idea should usually be a feed-native simulation: a phone frame that scrolls or swaps content, creator imagery, UI rails, sound/effect stickers, LIVE or Shop chips when source-supported, and quick cuts that feel like the platform itself rather than a product explainer.
Write concepts.json before implementation for every job, unless the user dictated one exact direction. Fast tests and quick URL jobs use a lean version (3 concepts, one-line fields) — lower resolution is allowed, lower creativity is not; the old "only for commercial-quality" carve-out is exactly how default jobs shipped template-filler. Generate at least three distinct concepts (distinct hook mechanic and structure, not just color/copy), each with a signatureMoment (the frame only this product could own) and a spectacleMove, score them with references/variant-system.md, and follow references/concept-contract.md. Pull mechanics from references/ad-exemplars.md so the bar is great ads, not the stock template. Then gate it:
node scripts/validate-creative.mjs <project-dir>/concepts.jsonDo not start the storyboard until the gate passes. The chosen concept must score attention, distinctiveness, and boldness at least 4, with claimSafety at least 3, and its structure must not silently default to the stock hook/pain/demo/proof/cta arc unless it records a forceDefaultReason. A merely-acceptable 3 on attention, distinctiveness, or boldness does not ship — pick or revise a bolder concept. Score boldness for how exaggerated and dramatized the idea is, never for how truthful a claim is. Implement the strongest or user-selected concept, and make the storyboard reflect its structure, firstFrame, and motionIdea.
Create a timed storyboard before code. Load references/storyboard-contract.md for the scene contract.
Use outputLanguage from ad-brief.json for all video-facing copy unless the user explicitly asks for another language.
There is no default structure — derive the scene list from the chosen concept's structure (see references/storyboard-contract.md, Mapping rules). Hard beat budgets that always apply for 15s:
transitionOut on the final scene).references/ad-exemplars.md (Structure-Diverse Shapes).Keep each beat to one visual idea. Avoid paragraphs in video text; prefer short lines that fit mobile. In most scenes, use one headline plus one support line at most; make the dominant word or number much larger instead of spreading many equal-size text blocks. If a scene uses a source-backed numeric claim, include a metric plan with from, to, prefix/suffix, decimals, and a short label so the renderer can animate the value. For games, use fast kinetic shots; cuts are fine, but each shot should contain gameplay, product motion, character/world action, or a visual payoff rather than a static information card.
For social or short-video apps, cuts are expected. Each shot should feel like a feed moment, creator clip, notification, sound cue, live/shop moment, or action prompt instead of a static feature card.
Load references/audio-caption-system.md when adding music, sound effects, voiceover, captions, or silent-autoplay readability.
If no project exists and renderEngine is remotion, copy assets/remotion-template/ into the target workspace. If a Remotion project exists, adapt its existing package manager, entrypoint, and component style — and install @remotion/google-fonts if missing; the template imports it even when fontPreset stays on the no-network default.
If renderEngine is hyperframes, copy assets/hyperframes-template/ or adapt the existing Hyperframes project. Hyperframes output is native HTML: index.html is the composition source, variables.json carries approved ad copy and asset paths, and QA uses npx hyperframes lint, inspect, preview, and render. Load references/hyperframes-output.md before implementation. For a new ad, author native Hyperframes HTML; do not use a Remotion-to-Hyperframes porting workflow unless the user explicitly asks to migrate existing Remotion source.
Remotion template rules:
block to a scene-block kind (cold-open-payoff, split-before-after, device-frame, stat-slam, hero-morph, ui-takeover, charge-reveal, cta-card, or standard) so the chosen concept's structure renders as distinct layouts and motion, not one repeated card. Map the concept's structure scene blocks onto these template blocks; add a new block component instead of forcing every scene through standard. ui-takeover (fake notification expands into the hero) and charge-reveal (progress-bar squeeze→slam) are purpose-built hook blocks — reach for them before inventing a weaker opener.Composition, Sequence, and AbsoluteFill.format / platform into the actual composition dimensions and scene layout. Square and landscape outputs must not reuse the vertical layout unchanged.public/<brand>/ and reference with staticFile().startFrame, category, scene/anchor sync metadata, and visible-event cue descriptions, not one repeated click. Treat audio as a default implementation detail, not a required preflight or QA gate. Only plan or verify special audio when the user asks for silent-safe, music, voiceover, or platform-specific sound.music-sfx with a generated, licensed, or user-supplied music bed plus picture-locked SFX when the user requests music. Keep quick URL jobs and fast tests on default sfx-only.voiceover. Write the voiceover as 3-5 spoken beats with varied delivery (energy, pace, tone) per references/audio-caption-system.md (Voiceover Scriptcraft), in outputLanguage. A generated TTS voice uses rightsStatus: generated.spectacleMove as a real on-screen beat (see references/ad-exemplars.md for the mechanics) so the spot has its "wait, what?" moment.references/motion-language.md, not bare linear interpolate. Use src/motion.ts eases (power3Out entrances, expoOut count-ups, backOut/springPop pops) and staggerDelay for multi-element reveals, and reveal headlines/CTAs with KineticText (split words/chars) instead of fading whole text blocks. For shared-element reveals (screenshot→hero, before→after) use FlipMove (the hero-morph block is a ready example); for reward/spectacle/game beats (confetti, coins, score pops, explosions) use Burst.scene.transitionOut (whip-left/whip-right/whip-up, zoom-punch, luma-wipe, or a deliberate cut). Never ship an all-fade spot, never repeat the same kind on consecutive boundaries, and align an SFX (sfx-whoosh, sfx-impact, sfx-swipe) to each boundary frame. Leave the final scene without a transition so the CTA holds.scene.impact: { atFrame, strength } beat (flash + camera shake) or a block's built-in slam (metric lock, CTA spring), synced to sfx-impact/sfx-sub-boom on the same frame. Use scene.celebrate: { preset } to fire a Burst payoff from props when a reward beat needs it.fontPreset that matches the brand register (bold-geometric, condensed-impact, editorial-serif, rounded-friendly, mono-tech) instead of shipping the default clean-sans Inter look; non-default presets load via @remotion/google-fonts (network needed once per render). Give exactly one scene (usually stat-slam or cta-card) colorMode: "inverted" so the spot has a color beat.props.captions with word-synced karaoke captions (same timestamps as the voiceover track, emphasis: true on numbers and power words) — most feeds play muted, and an uncaptioned voiceover effectively does not exist. See references/audio-caption-system.md (Karaoke captions).finish.grain / finish.vignette, default on) enabled unless the concept's art direction calls for a flat look.For Remotion implementation details, use the Remotion best-practices skill when available, especially composition, parameter, assets, timing, transitions, audio, and subtitle rules.
Hyperframes template rules:
data-composition-id, data-start, data-duration, data-width, and data-height on the root composition.data-start, data-duration, and data-track-index on every clip.data-composition-variables and pass values with variables.json / --variables-file.width, height, and layoutMode in variables.json and write them back to the composition data-width / data-height before render.window.__hyperframes.getVariables() for copy, CTA, colors, and local asset paths.window.__timelines. Build it with the ease/stagger vocabulary in references/motion-language.md (this path uses GSAP directly): power3.out entrances, expo.out/power3.out count-ups, back.out(1.7) pops, and stagger for multi-element reveals.Load references/render-qa-checklist.md before handoff.
Minimum checks:
npx hyperframes lint and inspect pass before preview/render.references/ad-aesthetic-qa.md for every job (a lean pass — scan the scorecard, fix anything obviously failing — is fine for fast tests; a full scored pass for commercial-quality).For skill tests, default to half-size draft video output and do not rerender full-size MP4 for non-blocking polish. Use the blocking/non-blocking split in references/fast-test-workflow.md.
Return:
ad-brief.json path or inline summary, including source type, interactionLanguage, sourceLanguage, outputLanguage, renderEngine, preflight answers/defaults, blockers, format, and audio mode.variables.json.interpolate (no easing, no stagger, whole-block text fades) so motion feels cheap — use the ease/stagger/kinetic-typography vocabulary in references/motion-language.md.public/<brand>/.© leosssvip-dot, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 46 other files (scripts, references, assets) in skills/remotion-ad-video of leosssvip-dot/remotion-ad-video-skill.
Open the folder on GitHubat commit e734c02
Remotion Ad 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 |
|---|---|---|---|---|---|---|
| Remotion Ad Video this skillleosssvip-dot/remotion-ad-video-skill | 111 | — | ~6.3k | Automated safety check: Pass | MIT | |
| HyperFrames Video Entry Pointheygen-com/hyperframes | 60k | 3 repos | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Remotion to HyperFrames Porterheygen-com/hyperframes | 60k | 3 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Reference Video Replica QcPluviobyte/video-production-skills | 671 | — | ~1.8k | Automated safety check: Pass | None | |
| Black White Text OpenerPluviobyte/video-production-skills | 671 | — | ~1k | Automated safety check: Pass | None | |
| Remotion To Hyperframeschmonitor/chmonitor | 301 | 1 repos | ~2.5k | Automated safety check: Pass | GPL-3.0 |
heygen-com/hyperframes
Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.
heygen-com/hyperframes
Ports an existing Remotion (React) composition to HyperFrames HTML with GSAP, one way, and grades the result against a tiered set of reference fixtures.
Pluviobyte/video-production-skills
Analyze, recreate, align, and verify reference-video motion.
Pluviobyte/video-production-skills
Create reusable black-background white-text opening animations for new videos.
chmonitor/chmonitor
Port an existing Remotion (React) composition to HyperFrames HTML.
Bomx/super-video-maker-skill
End-to-end AI video production skill for agentic frameworks.
Categories
A skill your agent uses when turning product links, app store listings, landing pages, or product briefs into advertising videos with Remotion or Hyperframes projects, storyboards, render-engine…. Remotion Ad Video is an agent skill from leosssvip-dot/remotion-ad-video-skill. Use when turning product links, app store listings, landing pages, or product briefs into advertising videos with Remotion or Hyperframes projects, storyboards, render-engine props/variables, render QA, and handoff assets.
Remotion Ad Video fits situations like: turning product links; app store listings; product briefs into advertising videos with Remotion; hyperframes projects.
Run `npx skills add leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a claude-code`. Or copy the skill folder (skills/remotion-ad-video in leosssvip-dot/remotion-ad-video-skill) into .claude/skills/remotion-ad-video in your project. Claude Code loads it when a task matches its description.
Run `npx skills add leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-video -a codex`. Or copy the skill folder (skills/remotion-ad-video in leosssvip-dot/remotion-ad-video-skill) into .agents/skills/remotion-ad-video in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add leosssvip-dot/remotion-ad-video-skill --skill remotion-ad-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/remotion-ad-video, .gemini/skills/remotion-ad-video, .github/skills/remotion-ad-video and .opencode/skills/remotion-ad-video in your project.
Going by SKILL.md and its folder, Remotion Ad Video needs the command-line tools its instructions call (npx and node).
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Remotion Ad Video is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 6.3k tokens (SKILL.md is roughly 25k 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 27k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Remotion Ad Video: HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars), Remotion to HyperFrames Porter (heygen-com/hyperframes, 60k stars), Reference Video Replica Qc (Pluviobyte/video-production-skills, 671 stars) and Black White Text Opener (Pluviobyte/video-production-skills, 671 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
leosssvip-dot (a GitHub user) maintains it in leosssvip-dot/remotion-ad-video-skill, which has 111 GitHub stars. The repository was last updated on June 10, 2026.
Source: leosssvip-dot/remotion-ad-video-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.