talking-head-recut

talking-head-recut is a skill for Claude Code from heygen-com/hyperframes. It costs 112 tokens per session (15,986 once invoked), scanned A, original, Apache-2.0.

A video-editing workflow that adds timed graphic cards over an existing talking-head, interview, or podcast video while leaving the original clip playing underneath.

In plain words
What is it for?
Use it to create synced titles, lower-thirds, quotes, data callouts, side panels, and picture-in-picture layouts for 16:9, 9:16, or 4:5 videos.
Why use it?
It turns spoken content into designed visual sections without replacing the speaker's video with plain subtitles.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Codex.

Part of the hyperframes plugin — 26 skills, 1 hook shipped together

Good fit Use it to create synced titles, lower-thirds, quotes, data callouts, side panels, and picture-in-picture layouts for 16:9, 9:16, or 4:5 videos.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/heygen-com/hyperframes/talking-head-recut
About the project

HyperFrames is an open-source framework that turns HTML, CSS, media, and timed animations into deterministic MP4 videos. It is used locally, by coding agents, and in hosted authoring workflows to create rendered videos from web-based designs. Its catalogue add-ons provide skills, agents, instructions, hooks, settings, and a plugin for agent-driven video production.

heygen-com/hyperframes · 44,503 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add heygen-com/hyperframes --skill talking-head-recut
Clone the repo
git clone --depth 1 https://github.com/heygen-com/hyperframes

Made for: Claude Code.

Or install hyperframes, the plugin that ships this one along with the rest of its 26 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for talking-head-recut

README.md
[![agentmods](https://agentmods.dev/badge/skills/heygen-com/hyperframes/talking-head-recut.svg)](https://agentmods.dev/skills/heygen-com/hyperframes/talking-head-recut)
Your own site
<a href="https://agentmods.dev/skills/heygen-com/hyperframes/talking-head-recut"><img src="https://agentmods.dev/badge/skills/heygen-com/hyperframes/talking-head-recut.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,986 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 21 Aug 2026
  • Snyk warn 21 Aug 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 23 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 1076
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 1077
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 218
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 1079
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 169
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 523
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 769
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 770
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium MCP Rug Pull · line 6
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 41
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 53
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 100
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 1169
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 1189
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 1208
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 446
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Prompt Injection · line 758
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 1074
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 1078
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 1082
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.15986
Opus 5 $0.00056 $0.07993
Sonnet 5 $0.00022 $0.03197
Haiku 4.5 $0.00011 $0.01599

Measured 8d ago against content hash a52cbcd22c65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

talking-head-recut scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/vendor/gsap.min.js, media-contract.test.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

skills/talking-head-recut/SKILL.md · 1,212 lines

How it starts

The opening of the file, as written. The whole thing — 1,212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First, keep this skill fresh — confirm with the user before running: npx hyperframes skills update talking-head-recut. A fast no-op when everything is current; otherwise it refreshes this skill plus the core domain skills it depends on before you rely on them.

Talking Head Recut

Talking Head Recut takes a local video that plays in full and layers a sequence of timed, designed graphic cards onto it — titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to what's being said. The agent designs the cards (timing + content) and writes each card's HTML directly in the conversation, then assembles a single composition HTML and renders it to MP4 via hyperframes. There is no fixed archetype list and no prescribed card structure — the overlays emerge from what the transcript actually says.

The front door is /hyperframes. This skill packages an existing talking-head clip with designed graphic cards (titles, lower-thirds, data callouts, quotes, side panels, PiP) — not plain captions (the spoken words as text). The clip plays untouched. Any other intent — plain subtitles, a standalone graphic, a from-scratch video — or any uncertainty → read /hyperframes first: the intent layer owns every route decision.

Graphic-packaging sibling of embedded-captions. Captions add the spoken words as a readable subtitle; this adds designed graphics on top of the playing video. Plain subtitles → embedded-captions. Build a video from scratch → the creation workflows (product-launch-video / faceless-explainer / …).

Routed through /hyperframes, the intent layer confirms only the input (which clip) and announces the render-strategy questions as deferred asks — aspect, layout, style group, and card count stay at Step 7, where the probed footage and transcript ground the recommendations; the layer's run-shape questions don't apply. A BRIEF.md, when present, carries the confirmed input and any user notes — read it first.

Inspectable intermediate files in the work directory:

  • metadata.json — duration / width / height / fps
  • audio.mp3 — extracted audio
  • transcript.json — a flat word array [{ text, start, end }, …] (Whisper; no segments, no words wrapper)
  • storyboard.json — lightweight card outline (the agent's plan)
  • public/cards/card-XX.html — one HTML fragment per card
  • public/index.html — final assembled composition
  • output.mp4 — rendered video

Read the full file on GitHub · 1,212 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 1,212 lines · 112 tokens per session scan A a52cbcd22c65

Subscribe to this mod's changes

talking-head-recut is a skill published in the GitHub repository heygen-com/hyperframes (44,503 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 15,986 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gsap

A JavaScript animation framework with shared systems for timelines, easing, and timed value changes. It can animate CSS, SVG, Canvas, WebGL, framework state, and other JavaScript objects, with extensions for tasks such as scroll triggers, drag interactions, motion paths, and text animation.

AvalonLee/AstraCraft-Program · 0 tokens

product-launch-motion

Use when making, directing or rescuing a product launch video, promo, teaser, demo reel, sizzle, feature-announcement film or animated product explainer built from code — and when an existing one looks basic, reads as a slideshow, has reveals that miss the voiceover, an invisible cursor, an inaudible sound effect, a…

AbubakrChan/product-launch-motion · 137 tokens

remotion

Use when creating, rendering, and managing programmatic videos using Remotion (React-based video framework). Covers compositions, frame-driven animation, transitions, effects, captions, audio, voiceover, FFmpeg post-production, and professional SaaS-grade motion design.

oyi77/1ai-skills · 54 tokens

motiscope-recreate

Recreate an analyzed animation as working web code — GSAP (JavaScript), CSS/Web Animations, Framer Motion (React), or Lottie/SVG. Use after motiscope-analyze, or when the user asks to "build/recreate this animation in ". Reads the motiscope animation spec and emits a runnable component.

KumarSashank/motiscope · 77 tokens

motion-graphics

Build frame-exact motion graphics — animated logos, kinetic typography, brand videos, animated titles and social clips — as a single HTML file driven by a paused Web Animations timeline, then export them to MP4 in 1:1, 4:5 and 9:16. Use this whenever someone wants to animate a wordmark or logo, make a video from text…

acelera-agency/html-animation · 188 tokens

motiscope-doctor

Check and configure motiscope — verify ffmpeg/ffprobe are installed and scaffold the API-key config used for optional (stubbed) asset generation. Use for first-time setup, "motiscope isn't working", dependency errors, or motiscope-doctor.

KumarSashank/motiscope · 61 tokens