<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs
Devsly

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 3d ago

by per-simmons

launch-video-clone

A Claude Code skill for making product launch videos in HyperFrames that don't look AI-made: original or cloned from a reference.

  • Active — Updated in the last 14 days
Works with
  • Claude
View on GitHub (opens in a new tab)

20 GitHub stars (20)

Steady at 20 stars — no new stars in the 2 days since Oct 29.

  • 5 skills (5 skills found in its SKILL.md files)
  • 6 forks (6 forks)
  • 3d ago last update (Last updated 3d ago)

Install

Skills CLI

npx skills add per-simmons/launch-video-clone

Asks which skills and agents to install. Just one: npx skills add per-simmons/launch-video-clone --skill launch-video-clone — add -g for every project.

Claude Code

git clone https://github.com/per-simmons/launch-video-clonecp -r "launch-video-clone" ~/.claude/skills/launch-video-clone

Copies the launch-video-clone skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add per-simmons/launch-video-clone

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • launch-video-clone

    Make product-launch / motion-graphics videos in HyperFrames, in three modes. ORIGINAL (no reference): pick a category from the type files and build a launch video from scratch with the skill's motion rules. CLONE: rebuild a reference video as closely as possible — same shots, timing, easing, transitions and type — in HyperFrames, optionally re-skinned for a different brand. Opus can't watch video…

    SKILL.md on GitHub (opens in a new tab)

  • footage-transitions

    Transitions between live-action footage and motion graphics (or between two footage shots through graphics) that never go to black and never pop - iris and dot holds on the right person, in-scene transitions (clouds, paper, light), motion-blurred push-ins on a word, match cuts onto real screens, whip pans and material wipes, each landed on a steady destination frame with the audio J-cut under it.…

    subskills/footage-transitions/SKILL.md on GitHub (opens in a new tab)

  • paper-world

    Turn a frame of real footage into a dimensional paper-collage world and back - freeze on a word, cut the subject out as real paper, let the background fall away like a stage flat, climb through a parallax paper city and paper clouds (Blender headless), stage a literal stat or a brand reveal, then return to footage through a cloud. Use for collage / paper-craft / cut-out beats inside a live-action…

    subskills/paper-world/SKILL.md on GitHub (opens in a new tab)

  • vo-beat-timing

    Lock narration and on-camera speech to picture - a frame-numbered timing sheet before anything is built, temp TTS voice-over with word timestamps, picture events pinned to stressed words, J/L-cuts and room tone for real takes, soft sound design placed on frames, and verification on the FINAL mix with Whisper (±3 frames). Includes a safe audio mix pipeline (no hung ffmpeg) and loudness landing. Us…

    subskills/vo-beat-timing/SKILL.md on GitHub (opens in a new tab)

  • word-synced-ui

    Product UI overlays that type, send and respond in sync with a speaker's real words - a prompt box, chat, search or command bar composited beside the person on camera, each word appearing on the frame it is spoken, then the product's real working states (thinking, building, result) over continuing B-roll. Built in HTML/CSS as a pure function of the frame, rendered to RGBA in headless Chrome, and…

    subskills/word-synced-ui/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.