hyperframes-registry
Skill30 starsChanged 40 days agoMITView on GitHub
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
54 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- cubxxw/agent-kitedited, first seen Nov 8, 2026
- cblain100-prog/motion-design-claude-codetheir own version, first seen Nov 8, 2026
- notivn/AIEVv2their own version, first seen Nov 8, 2026
- OpenMontageInc/OpenMontagetheir own version, first seen Nov 8, 2026
- calesthio/OpenMontagetheir own version, first seen Nov 8, 2026
- delorenj/skillstheir own version, first seen Nov 7, 2026
Used with
Projects with it also use cut-mistakes, cut-silences and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
nateherkaiSkillcut-mistakes
Agent 2 of the video editing pipeline. Finds and removes spoken mistakes — stutters, repeated words, false starts, and retakes (re-recorded lines) — from a talking-head recording. Use after cut-silences, when asked to cut mistakes, remove stutters / repeats / filler restarts, clean up flubs, or keep the best take. Works review-gated: it proposes every cut with context and a reason for approval, then renders only the approved cuts via ffmpeg. Requires a word-level transcript.
Also in 5 projects that use this
- nateherkaiSkill
cut-silences
Agent 1 of the video editing pipeline. Removes silences and dead air from a talking-head recording. Use when asked to cut silences, trim pauses, remove dead air / gaps, or tighten the pacing of a raw video, given a word-level transcript. Produces an edit list (EDL), a re-timed transcript for downstream agents, and optionally the cut video via ffmpeg. Does NOT cut mistakes, repeats, or false starts — that is the cut-mistakes agent.
Also in 5 projects that use this
anton-abyzovSkillhyperframes-media
Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.
Also in 12 projects that use this
NexumAI-onlineSkillshort-form-edit
Convertí una grabación hablada en un reel, YouTube Short o anuncio corto terminado, con apertura que genere curiosidad, resolución respaldada por el contenido, cortes narrativos, gráficos sincronizados, B-roll en movimiento, subtítulos, música sutil y efectos. Para videos largos usá edit-video; para quitar sólo pausas, cut-silences.
Also in 4 projects that use this
- +2 more from nateherkai
Other versions54 projects use a version of this.
Word for word · 1
- aipphilie/claude-skills★ 0100% same
Edited · 2
- heygen-com/hyperframes★ 81k90% same
- cubxxw/agent-kit★ 297% same
Wrote their own version · 51
- calesthio/OpenMontage★ 78ksame name
- OpenMontageInc/OpenMontage★ 78ksame name
- openai/plugins★ 7.8ksame name
- nateherkai/hyperframes-student-kit★ 2.2ksame name
- edenfunf/reelmimic★ 1.8ksame name
- nateherkai/herk-edit-kit★ 1.5ksame name
- EvovexAI/EvoFlow★ 612same name
- langchain-ai/design-agent★ 596same name
- boraoztunc/skills★ 454same name
- duyet/clickhouse-monitoring★ 303same name
41 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- embedded-captionsSkill
- faceless-explainerSkill
- figmaSkill
- general-videoSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframesSkill
- hyperframes-studioSkill
- media-useSkill
- motion-graphicsSkill
- music-to-videoSkill
- product-launch-videoSkill
- pr-to-videoSkill
- remotion-to-hyperframesSkill
- slideshowSkill
- talking-head-recutSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 51 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Plugin installs: Before setup or freshness commands, follow plugin execution rules when this skill is inside a HyperFrames plugin.
“Common” is measured: kept by at least 6 in 10 of the 51 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plugin installs: Before setup or freshness commands, follow plugin execution rules when this skill is inside a HyperFrames plugin.
HyperFrames registry
Starting from an item is faster and usually better than writing the effect yourself, and an installed item is ordinary source in your project: change it, cut it down, restyle it.
Find and install
npx hyperframes catalog --query "<what the beat should do, in English>" --json
npx hyperframes add <name> --json # prints the written files and the mount snippet- Query in English even when the video is not: the catalog is indexed in English, and another script returns
No searchable words in query, which is not a gap. - Search is local and sends nothing. The default
wordstier only finds items that reuse your words;--on-deviceranks by meaning after a one-time ~33 MB download. Offer that download and let the person decide; never enable it silently. The--jsonenvelope names the tier that answered. - Narrow with
--type block|componentand--tag <tag>.add <tag>installs every block with that tag; dependencies install first.addneeds the network even for an item installed before; search works offline from the cached manifest. - Nothing fits: report it before you hand-build, on either tier.
catalog --queryprints the line pre-filled (report_gapin--json):npx hyperframes feedback --search-miss "<query>" --wanted "<the move you needed>" --tier <tier>. Describe the effect, not an item name you imagined.
Tiers, dropped and unindexed, stale indexes, offline behaviour: references/search.md.
What's in it
| Blocks: a scene with its own timeline | Examples |
| Transitions | beat-freeze-cut, chromatic-radial-split, cinematic-zoom |
| Overlays and lower thirds | camcorder-hud, editorial-flash-overlay, lt-clean-bar |
| Title cards and kinetic type | canopy-part-title, code-slice-hero |
| Social, chat and UI cards | ai-chat-reveal, chatgpt-exchange |
| Code, charts, data and maps | code-diff, bar-chart-race, data-chart |
| 3D, shader and backgrounds | app-showcase, aurora, blob |
| Components: a snippet merged into your scene | Examples |
| Motion primitives and text effects | agent-cursor, blur-in, bottom-up-letters |
| Caption styles | caption-clip-wipe, caption-editorial-emphasis |
| Camera moves | camera-shake, camera-scan-gate |
| Product demo and UI props | before-after-wipe, browser-device-stage |
| Textures, particles and effects | ascii-render-pass, grain-overlay |
Wiring
- Block: installs to
compositions/<name>.html. Mount it withdata-composition-src,data-composition-idmatching the block's own id,data-startand thedata-durationyou need; the snippetaddprints is the starting point.references/wiring-blocks.md. - Component: installs to
compositions/components/<name>.html. Copy its markup,<style>and script into your scene, and follow its comment block if it hooks into your timeline.references/wiring-components.md. - Take the largest unit that fits, then edit it. Keep an installed item's ids prefixed as they are, so two items can't collide.
- An item keeps its own variables; set them for one mount with
data-variable-valueson its host (add --vars '{"title":"…"}'writes that), and point its colour and font variables at your brand's. - Beat-synced blocks take hit times from
npx hyperframes beats --json: the beat times minus the mount'sdata-start. - Install paths come from
hyperframes.json(references/install-locations.md).
Contributing
Authoring a new block or component for an upstream PR: references/contributing.md, starter templates in references/templates.md, quality bar in references/component-quality-bar.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.