Screen demos and B-roll for creators, from a script or plain instructions: screen (real headed Chrome, one or two windows, beats timed to a voice or to seconds, the pointer moving like a hand), assemble (large Screen Studio-style pointer, spring zooms, plain browser frame, fades, 4K 60 fps, normalized loudness), audio (loudness, peaks, pauses and speech rate; normalize to -16 or -14 LUFS; pause cap), voice (optional: generate with ElevenLabs, or bring your own audio or video and get line and word timings; shorter pauses), broll (optional, paid: people B-roll with Higgsfield). macOS, Linux and Windows.
Plugin demo-studio from marketplace psoares-claude-plugins in ps-dev-team/psoares-claude-plugins. Commands read from the repo's manifest — 11 days ago.
assembleTurn screen recordings (and an optional voice) into the finished video: a large Screen Studio-style pointer, 2x spring zooms, two windows side by side in a plain browser frame, fades between scenes, the voice with its gaps, 4K at 60 fps. Use after the screen skill: "assemble the video", "render less
audioCheck and fix how a voice-over or a finished video sounds. Reports loudness (LUFS), true peak, loudness range, pauses and speech rate; brings a file to a standard loudness (-16 LUFS for speech on the web, -14 for YouTube) with the picture untouched; shortens long pauses with crossfades. Use for "is
brollOptional, and paid (Higgsfield credits). Make B-roll with Higgsfield from photos of people: an enlarged photo, the person placed in a real-life setting, short clips of them talking or listening, and from those clips seamless loops, overlay clips, or fake-camera feeds for a recorded video call (talki
screenRecord a web app or website in real headed Chrome from written instructions or a script, timed to a voice or free-running for B-roll: one or two real windows (for example an admin and a user side by side), the pointer and zooms recorded as data. Use for product demos, course lessons, walkthroughs an
voiceThe voice of a screen video, and the timing of every line and word that the screen skill follows. Optional. Three ways in: generate it from a script with ElevenLabs (eleven_v4, your own cloned voice or any voice), bring your own recording or any other TTS, or take the audio from a video of your own.
Capture raw content (metadata, transcript, frames) from YouTube videos and Instagram reels, analyze it in the current Claude session, download YouTube videos (full or trimmed), and extract multiple clips from long-form content (podcasts, courses) via a conversational brainstorm. Skills: view-youtube-video, view-instagram-reel, extract-content, clip-youtube-video, clip-video-parts.
5 skills
Writing for videos and content. Skills: hooks for the opening (six formats, the spoken, text and visual hook lined up, the lock-in zone, four mistakes), storytelling for the structure that keeps people watching (stakes, a big question, head fakes, re-hooks), and video-script for scripts recorded one take per line.
3 skills
Development workflow tooling. Skills: create-github-issue for filing grounded, well-scoped GitHub issues from the codebase, and journal-session for recording what happened in a Claude session as a narrative project journal.
2 skills
Voices with ElevenLabs that sound like the speaker: eleven_v4 clones through text-to-dialogue, script tags and punctuation for pacing, pronunciation fixes that never touch the script, per-language pause caps, picking website takes from history, word timings and misread checks with Scribe. Script in, voice and line timings out.
1 skill
Gruvbox Material Dark statusline with directory, git branch, model, context bar, cost estimate, agent, and vim mode.
1 skill
The Markdown Teleprompter app's script format. Skill: teleprompter-script, which lays out a script the way the app reads it: directives, chapters, presenter tabs, presenter notes, voice cues, and bullet points to talk from instead of reading word for word.
1 skill
Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.
Recommended: all published HyperFrames skills in one versioned bundle. Create and render videos from HTML: the contract, film, captions, overlays, motion and look references, the CLI, the registry, media, Figma, slideshows and Remotion ports.
22 skills
53 marketing skills for technical marketers and founders: CRO, copywriting, cold email, prospecting, SEO, AI SEO, paid ads, SMS, ad creative, video production, image generation, co-marketing, churn prevention, pricing, referrals, revenue operations, sales enablement, customer research, site architecture, comprehensive AARRR-structured marketing plans, public relations and earned media, offer design, event marketing and webinars, and more
53 skills
HyperFrames by HeyGen. Write HTML, render video. Compositions, GSAP and runtime adapter animations, captions, voiceovers, audio-reactive visuals, and website-to-video capture for HyperFrames.
34 skills
XSS prevention, CSRF protection, content security policies, mobile app security, and secure storage patterns
1 command · 3 agents
Plan, build, and debug Zoom integrations across REST APIs, Meeting SDK, Video SDK, webhooks, bots, and MCP workflows. Search meetings, retrieve recordings, access transcripts, and design AI-powered Zoom experiences.
44 skills · 3 MCP servers
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.