# SuperDuperAI
> SuperDuperAI builds privacy-first AI tools: Life2Film (AI video montage on your phone), open-source Claude Code skills, and a free library of copy-ready prompts and how-tos for short-form video.

Everything here is public, free, and may be quoted with a link back. Every library entry, product
and tool page has a markdown twin at its URL with `.md` appended, and any of them (and this home
page) answers `Accept: text/markdown` with it. The whole library is in /llms-full.txt and as JSON
in /library.json; products in /products.json. One search, one answer: /api/search?q=<words>
returns the top entries with their full prompts as markdown (&format=json for JSON).
Content signal: search=yes, ai-input=yes, ai-train=no.

## For agents
- MCP server: https://superduperai.co/mcp (Streamable HTTP, no key). Tools: search_library, get_prompt,
  build_veo3_prompt, list_tools, list_products, contact. How to connect: [/agents/](/agents/).
- MCP server card: /.well-known/mcp/server-card.json · agent card: /.well-known/agent-card.json ·
  API catalog: /.well-known/api-catalog · policy: /agents.txt

## Products
- [SuperDuperAI Video](/products/video/): AI video generation from a brief: script, shots, generated clips, a cut. The product the previous superduperai.co sold as the Video Editor, being rebuilt. Early access by email.
- [Life2Film](/products/life2film/): AI video montage on your phone and Mac: scores every frame, finds the scene changes, cuts a film from your camera roll. Nothing uploaded.
- [SuperStoryboard](/products/superstoryboard/): AI storyboard generation with real-time Figma sync, built on Supabase. Second place at the Supabase Hackathon.
- [FaceAlarm](/products/face-alarm/): Face yoga tracker with a daily selfie alarm: the alarm will not turn off until you take a selfie, so you track the transformation every day. iOS and Android.
- [Jaw Harp Synth](/products/jaw-harp-synth/): A physics-based jaw harp (kubyz, vargan) synthesizer for iOS, with tunings from Bashkir, Yakut and Vietnamese traditions.
- [Air Signal and Crew Air](/products/air-signal/): Air quality and 14 outdoor comfort signals for any place, and a shift planner for outdoor crews on wildfire-smoke and heat days. One Rust core, web live, iOS in review.
- [You2Idea](/products/you2idea/): Startup idea search over 700+ YouTube videos from 46 startup channels: semantic search, PRD generator, topic graph, a free daily digest.
- [Visayes](/products/visayes/): Passport and visa photos in the browser: crop to 13 country specs, AI background removal, face guides, print-ready PDF. Photos never leave the device.
- [Starlapse](/products/starlapse/): Long-exposure night sky camera for iPhone: stacks hundreds of 1-second frames into one sharp photo and shows where to aim for meteors.
- [Live2play](/products/live2play/): Vertical reel camera for musicians: one tap records, with a clean audio feed from your computer, on-device motion tracking and a built-in synth.
- [Tugan Tel](/products/tugan-tel/): Bashkir, Tatar and Kazakh for children 1 to 7, in the voice of their own family: animals in a tap-and-listen game say the phrases a grandparent recorded.
- [PhotoSweep](/products/photosweep/): Find the biggest videos and old screenshots in your photo library and delete them to free iPhone storage. Free, nothing uploaded.
- [Voxlog](/products/voxlog/): Record a meeting or a whole day and read it back as text, transcribed on the iPhone. Nothing uploaded. Public beta on TestFlight.
- [CurrencyPals](/products/currencypals/): Converts 36 currencies at once: type in any row and every row updates. Works offline with the last rates. Free, no account.
- [SuperDuper Terminal](/products/superduper-terminal/): SSH client for iPhone and iPad with tmux sessions that survive a dropped connection. Free, open source, no account.
- [PocketMap](/products/pocketmap/): Offline OpenStreetMap maps for iPhone: download an area, route on the phone, find the way back with no signal. No account, no analytics.
- [Flykeeper](/products/flykeeper/): Keep a fruit fly whose behaviour comes from a live simulation of a real fly brain, 138,584 neurons, running on your iPhone.

## Open source
- [solo-factory](/products/solo-factory/): Claude Code plugin for solopreneurs: 57 skills and 2 agents that run a startup pipeline from research and validation to build, deploy and launch. MIT.
- [solograph](/products/solograph/): MCP server for a portfolio of projects: symbol search across every repository, full-text search over Claude Code sessions, a knowledge base and external sources. 5 tools, all SQLite FTS5.
- [SuperDuper DSP](/products/superduper-dsp/): 36 free, open-source audio plugins in Rust (CLAP/VST3/AU) for macOS and Windows: EQ, compressors, reverbs, vocal tools, a spatial panner and 7 instruments. Every parameter reachable by an AI agent over MCP.
- [superduper-analytics](/products/superduper-analytics/): One cookieless, self-hosted counter for every site and app: a Cloudflare Worker, Analytics Engine, a daily D1 rollup. No cookie, no per-person id, installs attributed per store campaign token.
- [openai-oxide](/products/openai-oxide/): An idiomatic OpenAI client in Rust with 1:1 parity with openai-python: typed responses, streaming, function calling; bindings for Node and Python, WASM.
- [rust-code](/products/rust-code/): A TUI coding agent in Rust: structured agent loop, 22 tools, fuzzy search, tmux background tasks, skills, MCP support.
- [supervox](/products/supervox/): Voice pipeline TUI in Rust: live call assistant with real-time subtitles, post-call analysis, agent chat with history. STT, VAD and TTS on the device.
- [airq](/products/airq/): Air quality CLI and the Rust/WASM core behind Air Signal and Crew Air: 14 outdoor signals, pollution fronts, EPA NowCast, Open-Meteo and Sensor.Community data merged.
- [agent-board](/products/agent-board/): An API-only task board where an agent claims work on an open-source repository under a lease and returns a URL plus the sha256 of what it delivered. No money, no hiring.

## Free tools (free, run entirely in the browser: no sign-up, nothing uploaded)
- [Veo 3 prompt generator](/tool/veo3-prompt-generator/): Structured Veo 3 prompts with camera, light, style, ambient sound and dialogue; viral-format presets; text and JSON output. In English, Spanish, Russian and Turkish.
- [Video prompt builder](/tools/video-prompt-builder/): Fill seven fields, get a text-to-video prompt in the structure Veo, Sora, Kling and Runway read best.
- [Script, shot list and prompt list](/tools/script-formatter/): Paste a rough script; get timed beats, word count, a shot-list table, a storyboard JSON and one generation prompt per shot.
- [Image to prompt](/tools/image-to-prompt/): Drop a reference image: palette, brightness, contrast, orientation and composition are read in the browser and written into a prompt skeleton for image-to-video.
- [Frame grabber](/tools/frame-grabber/): Pick frames from a video for a first-frame or a thumbnail: scrub, grab, compare on a contact sheet, download PNGs. The file never leaves your browser.
- [Safe-zone and aspect-ratio overlay](/tools/safe-zone/): Drop a frame or a video and see the TikTok, Reels and Shorts UI zones over it; crop and pad numbers between 16:9, 9:16, 4:5 and 1:1 with the ffmpeg line.
- [Caption reading-speed checker](/tools/caption-checker/): Paste an SRT: words per second per cue, lines over the limit, and how long a voice-over takes to say.
- [Hook generator](/tools/hook-generator/): Twenty opener variants for your topic from eight hook archetypes, with the on-screen text version.

Tools whose home is another of our sites (listed here, hosted there):
- [Trim Video](https://life2film.com/tools/video-trimmer/): Cut a clip to in and out points; the picture is copied, not re-encoded, so nothing is lost. Or trim to fit a file size. (Life2Film)
- [Video Splitter](https://life2film.com/tools/video-splitter/): Cut a long video into Reels or Shorts that start on a shot change, ranked by picture quality. (Life2Film)
- [Compress Video](https://life2film.com/tools/video-compressor/): Make a file smaller and see exactly what it cost. No size limit, because there is no server. (Life2Film)
- [Convert Video](https://life2film.com/tools/video-converter/): MP4, WebM and MOV in any direction, or pull the audio out as WAV. (Life2Film)
- [Video to MP3](https://life2film.com/tools/video-to-mp3/): Pull the audio out of a video and keep it as MP3, WAV or OGG. (Life2Film)
- [Video to Frames](https://life2film.com/tools/video-to-frames/): Pull frames out of a video as JPG or PNG, one a second or ten, and download them all as one ZIP. (Life2Film)
- [Scene Detector](https://life2film.com/tools/scene-detector/): Find every cut in a video and get the shot list with thumbnails, timecodes and quality scores, from the Life2Film engine. (Life2Film)
- [BPM Detector](https://life2film.com/tools/bpm-detector/): Tempo and the time of every beat of a track; send the grid to Resolve, Premiere, Final Cut or Audacity as markers. (Life2Film)

## Library (121 entries)
Index: /library/ · by tool: /library/for/{claude-code|chatgpt|veo|kling|runway|life2film|...}/ · by platform: /library/on/{tiktok|reels|shorts|youtube|linkedin}/

### Video generation (23)
Prompts for text-to-video and image-to-video models: shots, camera moves, styles, consistency.
- [Before you post a generated video: disclosure and rights checklist](/library/ai-video-disclosure-and-rights-checklist/): Six checks for AI-generated clips before they go on TikTok, Reels, Shorts or a client's site: labels, likeness, music, logos, model terms and provenance.
- [Anime style: 2D cel look, limited animation, clean line weight](/library/anime-cel-style-video-prompt/): A filled 7-part prompt for a hand-drawn anime shot: flat cel shading, animation on twos, a held painted background, and the three things the style breaks in current video models.
- [Architectural walkthrough: an interior on a steadicam in natural light](/library/architectural-walkthrough-interior-prompt/): A filled 7-part prompt for a real-estate or design walkthrough: one slow steadicam path through a room, windows as the only light, straight verticals, and the turns that make geometry drift.
- [Generate a 10-clip b-roll pack for a talking-head video](/library/b-roll-pack-generation-prompt/): One agent prompt that reads your transcript and writes ten generation prompts for cutaways that show what is being said, each tagged with the sentence it covers.
- [Camera movement vocabulary that video models understand](/library/camera-movement-vocabulary/): The 14 camera moves that generation models respond to reliably, with the phrasing that works and the phrasing that produces a wobbling mess.
- [Keep the same character across clips: the reference sheet prompt](/library/character-consistency-reference-sheet/): A character description block you reuse verbatim in every prompt, plus a generated reference sheet, so a face, outfit and build stay the same from shot to shot.
- [Establishing shot: open a video with a place](/library/cinematic-establishing-shot-prompt/): A prompt for the wide opening shot that tells the viewer where they are, with the three things that make a generated landscape look filmed rather than rendered.
- [Claymation and stop motion: 12 fps feel, fingerprints, slight jitter](/library/claymation-stop-motion-video-prompt/): A filled 7-part prompt for a clay stop-motion shot where the imperfections are the point: visible fingerprints, a frame-by-frame stutter, a set that looks built by hand, and what not to ask for.
- [Fashion lookbook: a model walks in a studio at 24 fps](/library/fashion-lookbook-studio-walk-prompt/): A filled 7-part prompt for a lookbook clip: seamless backdrop, one walk toward the camera, cinema frame rate so the fabric moves like fabric, and the faces, feet and prints that need extra care.
- [Fewer warped hands and faces: what to change in the prompt](/library/fix-warped-hands-and-faces/): The prompt-side fixes for the classic generation failures (melting hands, drifting faces, extra limbs), ordered by how often each one works.
- [Food close-up: macro, steam, a slow pour](/library/food-macro-close-up-video-prompt/): A filled 7-part prompt for a food shot that looks edible: one macro framing, one slow physical event (a pour, steam, a crack), side light that shows texture, and the hands and labels to keep out.
- [Ask an agent to turn a script into a numbered generation shot list](/library/generation-storyboard-from-script-agent/): A prompt for Claude or ChatGPT that converts a 30-second script into 6-8 shot prompts in the 7-part structure, ready to paste into a video model one by one.
- [Image-to-video: generate the first frame, then animate it](/library/image-to-video-first-frame-method/): Make a still with an image model first, fix the composition there, and only then ask the video model to animate it. Cheaper iterations and the look you chose, not the one the video model guessed.
- [Music visualizer: abstract particles that pulse to a stated tempo, loopable](/library/music-visualizer-abstract-loop-prompt/): A filled 7-part prompt for an abstract background clip: particles that pulse at a stated BPM, a near-seamless loop, no text; the model cannot hear your track, so the beat is matched in the editor.
- [Nature documentary: long lens, slow motion, no narration](/library/nature-documentary-long-lens-prompt/): A filled 7-part prompt for a wildlife shot that looks filmed from a hide: 600mm compression, heat haze, one animal doing one slow thing, slow motion at a stated rate, and the anatomy traps.
- [Pixel art: an 8-bit game cutscene on a locked pixel grid](/library/pixel-art-8bit-game-cutscene-prompt/): A filled 7-part prompt for a retro game cutscene: a stated sprite size, a palette of 16 colours, parallax layers, no sub-pixel smoothing, and why a still from an image model is the safer first frame.
- [Product hero shot: a 5-second generated clip for an ad or a listing](/library/product-hero-shot-generation/): Prompt for a clean product shot with one motion and one light change, the kind that sits at the top of a listing or opens a 15-second ad.
- [Retro VHS: a 1990s home video shot on a camcorder](/library/retro-vhs-1990s-home-video-prompt/): A filled 7-part prompt for the camcorder look: 4:3 inside the frame, tracking noise, colour bleed, auto-focus hunting and a zoom nobody meant, with the date stamp added in the editor.
- [Style lock: one paragraph that makes every clip look like the same film](/library/style-lock-block/): A reusable style paragraph (stock, palette, grain, light rules) appended to every generation prompt so a series cuts together instead of looking like ten different ads.
- [Talking-head clip: the script format AI avatar and lip-sync tools read best](/library/talking-head-avatar-script-prompt/): How to write a 20-second spoken script so that a lip-sync or avatar model delivers it with natural pauses and no mispronounced numbers.
- [UGC-style generated ad: make it look like a phone, not a studio](/library/ugc-style-generated-ad-prompt/): Prompt rules that push a video model toward the handheld, imperfect look of user-generated content, which still outperforms polished ads in most feeds.
- [The 7-part prompt structure for text-to-video](/library/video-prompt-structure-seven-parts/): A fill-in template that gives any video model the seven things it needs: subject, action, setting, camera, light, style and sound. Fewer vague words, fewer wasted generations.
- [Watercolor and painterly: a moving painting with paper grain and bleeding edges](/library/watercolor-painterly-animation-prompt/): A filled 7-part prompt for a hand-painted look: wet-on-wet edges, visible paper grain, boiling pencil lines, slow motion so the paint stays paint, and the drift to 3D when the action is too fast.

### Viral formats (20)
Recipes for the short-form formats that keep working, written so an agent can rebuild one for your topic.
- [Before/after: the 20-second reveal with the 'after' shown first](/library/before-after-reveal-format/): The before/after format with the twist that keeps it from being skipped: open on the finished result, then show how bad it was, then the change. The prompt returns a timed script and text plan.
- [Build in public: a 45-second behind-the-scenes cut around one decision](/library/build-in-public-behind-the-scenes-format/): The founder diary format that earns trust because it shows the decision, not the launch: the prompt structures a week of real screen and desk footage around one choice and one measured result.
- [Day in the life: a 45-second cut from real footage with one through-line](/library/day-in-the-life-format-script/): A recipe for the vlog-style day that keeps working because the viewer waits for one promised payoff; the prompt turns your clip list into a timed script with text overlays.
- [Founder explainer: 'I built this because' in 40 seconds, to camera, one problem](/library/founder-explainer-format/): The founder-to-camera format that converts because it names the specific moment the problem became unbearable, then shows the product once. The prompt bans origin-story clichés and budgets the words.
- ['I tried it for 7 days': a diary cut with one metric logged every day](/library/i-tried-it-for-seven-days-format/): The experiment-diary format that stays honest because one number is measured daily and shown on screen; the prompt plans the daily clip, the tally and a verdict that includes what did not work.
- [Countdown listicle: 5 items in 45 seconds, best one last, numbers on screen](/library/listicle-countdown-format/): The ranked list format, with the rule that makes it hold: each item gets shorter as the count drops and number one gets the longest shot. The prompt returns script, text plan and the caption list.
- [Myth vs fact: three beliefs checked in 35 seconds, each with a demonstration](/library/myth-vs-fact-format/): The format where a common belief is stated, then tested on camera, then labelled. Works because the viewer picks a side in the first second; the prompt insists on a visible test per myth.
- [POV: a 15-second first-person scene with the text doing the storytelling](/library/pov-format-script/): The POV format in which the camera is the viewer's eyes and one line of on-screen text sets the situation; the prompt writes the text, the single action and the beat where it turns.
- [Reaction / duet style: respond to a clip in 30 seconds without stealing it](/library/reaction-duet-style-format/): The split-screen or picture-in-picture response format, written so the reaction adds a fact or a demonstration instead of a face. The prompt plans the pause points and what you say at each.
- [Satisfying process / ASMR: 30 seconds of one process, real sound, no talking](/library/satisfying-process-asmr-format/): The sound-led format that holds without a hook sentence because the first frame is mid-action and the audio is the process itself. The prompt plans the cuts to the sounds and the single text line.
- [Screen-recording walkthrough: 45 seconds, one outcome, zoom on every click](/library/screen-recording-walkthrough-format/): The faceless screen walkthrough that stays watchable because every click is zoomed and labelled and the outcome is shown first. The prompt returns the click list, the zoom plan and the voice-over.
- [Comparison: two ways to do one thing, side by side, same task, same clock](/library/side-by-side-comparison-format/): The split-screen comparison that is fair enough to be believed: identical task, identical start, a visible timer, a verdict earned on screen. Prompt returns the script and the fairness checks.
- [Silent text-on-screen story: 25 seconds, one line per shot, paced for reading](/library/silent-text-on-screen-story-format/): The no-voice format that works with sound off because the text is the narration; the prompt paces each line to its shot at 2 words a second and puts the turn on the second-last card.
- ['Stitch this' opinion: 5 seconds of their claim, 25 seconds of your answer](/library/stitch-this-opinion-format/): The stitch format in which a short borrowed clip sets up a claim and you answer with one argument and one demonstration. The prompt picks the 5 seconds to keep and bans the straw man.
- [Storytime with a twist: a 60-second told story with the turn at 40 seconds](/library/storytime-with-a-twist-format/): The talking-to-camera story that holds because the opener promises a turn and the turn arrives late. The prompt plans the beats, the b-roll inserts and the one line of text per beat.
- [Street interview style: one question, 5 answers, 40 seconds, real or generated](/library/street-interview-format/): The vox-pop format: one short question, five contrasting answers, the last one lands the point. The prompt writes the question, the answer spread and, if generated, the per-person shot prompts.
- ['Things I wish I knew': 5 lessons in 50 seconds, each with what it cost me](/library/things-i-wish-i-knew-format/): The advice format that gets saved because every lesson is attached to the mistake that taught it. The prompt orders the lessons by cost and plans one number on screen per lesson.
- ['3 mistakes' in 40 seconds: the educational format that converts](/library/three-mistakes-format/): Three mistakes the viewer is making right now, each with the fix shown in a shot, ranked so the last one is the one they did not know about. Prompt returns the script, text plan and shot list.
- [Tutorial in 30 seconds: result first, then the steps at reading speed](/library/tutorial-in-30-seconds-format/): The compressed how-to that gets saved: the finished thing in frame 1, then 3-5 numbered steps each shown and captioned. The prompt budgets the words so the steps fit at 165 wpm.
- ['Watch me use it': a 30-second product demo with no pitch and one real task](/library/watch-me-use-it-product-demo-format/): The demo that converts because it is a task, not a feature tour: one thing the viewer wants done, done on camera, in real time where possible. The prompt forbids adjectives and plans the text.

### Hooks (15)
First-three-seconds openers: templates, prompts to generate them, and how to test them.
- [Generate 20 hooks for a topic and rank them by a stated rubric](/library/generate-20-hooks-ranked-by-rubric/): One prompt that produces 20 openers across the 8 archetypes, scores each on four named criteria, and returns the top 5 with the score shown, so the ranking can be argued with instead of trusted.
- [Hook for a generated video: what must be in frame 1 when a model draws it](/library/generated-video-first-frame-hook/): The first-frame rules for Veo, Kling and Runway: start mid-action, name the motion already happening, keep text out of the generation, and generate the hook shot as its own 4-second prompt first.
- [A/B test hooks with campaign links: judge after a week on installs, not views](/library/hook-ab-test-campaign-links/): The creator-growth method: same video, different hook, one store campaign link per variant, installs per campaign read after a week. Includes the iOS ct= link shape and the noise rule.
- [Bold claim hook: say the thing you can prove in the next 20 seconds](/library/hook-archetype-bold-claim/): Template and rules for the claim hook: one declarative sentence that the viewer expects you to fail to back up, plus the rule that the proof must be in the video, not in the caption.
- [Contrarian hook: disagree with the standard advice, then earn it in 20 seconds](/library/hook-archetype-contrarian/): Template for the hook that reverses what the audience has been told, with the two rules that separate it from rage bait: quote the standard advice fairly, and name the case where it still holds.
- [Curiosity-gap hook: withhold one fact, promise it by a stated second](/library/hook-archetype-curiosity-gap/): Template for the hook that opens a gap and names when it closes, with the rule that keeps it from being clickbait: the withheld fact is real, single, and delivered where you said it would be.
- [Number hook: a count the viewer can track, and the one item that justifies it](/library/hook-archetype-number-countdown/): Template for the hook built on a number (3 mistakes, 5 tools, 7 days), with the rule that the number must be small enough to finish and the last item must be named as the reason to stay.
- [Pain-point hook: name the exact moment, not the general problem](/library/hook-archetype-pain-point/): Template for the hook that opens on the viewer's own bad moment, with the specificity test (a place, a time, an object) that turns 'struggling with X' into a line the right viewer cannot scroll past.
- [Question hook: the opener the viewer answers in their head before you do](/library/hook-archetype-question/): Template and rules for the question hook, with the test that separates a question that holds (the viewer has an answer and wants it checked) from one that is skipped (nobody cares either way).
- [Result-first hook: show the finished thing in frame 1, say how long it took](/library/hook-archetype-result-first/): Template for the hook that opens on the outcome, the one that works with sound off and for products whose output is the content; the first frame is the result, not you holding it.
- ['Stop doing X' hook: the correction that must come with the replacement](/library/hook-archetype-stop-doing-x/): Template for the interrupt hook that names a habit the viewer has and tells them to stop; the rule that makes it work is that the replacement is in the same sentence or the next one.
- [Hook rewrite: a boring opener in, 5 stronger versions out, each with the reason](/library/hook-rewrite-five-stronger-versions/): A prompt that diagnoses why an opener is weak (generic, unprovable, needs sound, buried number) and rewrites it five ways, each labelled with the archetype and the fault it fixed.
- [Hooks for a product with nothing to show: text and voice carry the first 3 s](/library/hooks-for-product-with-no-visuals/): For an API, a CLI, a service, a habit, anything without a screen worth filming: five hook shapes built on a typed line, a number and a voice, and what goes on screen instead of the product.
- [Re-hook at 3 s and at the midpoint: two lines that carry a viewer past the drop](/library/rehook-at-three-seconds-and-midpoint/): Retention is lost twice, after the hook pays off and halfway through; this prompt writes the second promise for 3 s and the third for the midpoint, each as a line the viewer can check before the end.
- [Visual hook rules: first frame, text on screen, sound off, and how long you have](/library/visual-hook-first-frame-rules/): The checklist for what the viewer sees before any word is heard: first frame, text, the sound-off case, and the attention windows the creator-growth skill states (about 0.1 s, 0.5 s, 1-2 s by age).

### Scripts & shot lists (10)
From an idea to a timed script and a shot list an agent or a camera can follow.
- [Turn a blog post into three short scripts: one claim per video](/library/blog-post-to-three-short-scripts/): A prompt that reads a post and returns three 30-45 second scripts, each built on a different claim from the text, with the hook, the proof, the ask and the source sentence for each.
- [Forced reasoning before scripting: goal, hook type, demo moments, emotion arc](/library/forced-reasoning-before-scripting/): Four questions an agent must answer in writing before it writes a line of script. Skips the generic promo every model produces when asked for one directly.
- [The 30-45 second promo script: hook, problem, demo, CTA with timings](/library/promo-script-30-45-seconds-template/): A fill-in script template for a vertical product promo: four blocks with second counts and a 75-100 word narration budget, so the video ends before the viewer scrolls.
- [Cut any script to 55 words: the 20-second rewrite prompt](/library/rewrite-script-to-55-words-20-seconds/): A rewrite prompt that compresses a script to 55 words (about 20 seconds at 165 wpm) without losing the number, the name or the ask, and reports what it removed so you can argue.
- [Screen-recording demo script for an app: what to click, what to say, when](/library/screen-recording-demo-script-app/): A prompt that writes a demo script where every spoken line is paired with one on-screen action, so the recording is done in one pass and the narration recorded over it afterwards.
- [Write the cut as a script, not a timeline: the JSON storyboard prompt](/library/script-to-storyboard-json-cut/): An agent prompt that writes the edit of real footage as a small JSON file: which sentences, which cover shots, what the cold open is. A complaint becomes a one-line edit, and the render repeats.
- [Shot list generator: a table with shot, duration, visual, audio and overlay](/library/shot-list-table-generator-prompt/): An agent prompt that turns any script into a numbered shot table a camera operator or a video model can follow: one visual, one audio line and one text overlay per row, durations that add up.
- [60-second founder update: the script prompt for a weekly build-in-public clip](/library/sixty-second-founder-update-script/): A prompt that writes a 60-second talking-head update from your week's notes: the number first, one thing that broke, one thing shipped, one ask. About 150 words, no greeting.
- [One script, two languages: EN and RU versions that match shot for shot](/library/two-language-script-en-ru-prompt/): A prompt that writes a script in English and Russian side by side, same shots and same timings, with the Russian rewritten rather than translated so it fits the same seconds.
- [YouTube explainer, 8 minutes: the outline prompt with timestamps](/library/youtube-eight-minute-explainer-outline/): A prompt that produces a timed outline for an 8-minute explainer: a cold open, a promise, five sections with a visual each, the mistake, a recap and one ask, before any script is written.

### Editing & montage (12)
Cuts, cutaways, pacing, cold opens, and letting an agent edit real footage.
- [Analyse once: sidecar files beside the sources, shooting time from the container](/library/analyse-once-sidecar-files-metadata-time/): The storage rule that makes a long film possible a month later: each clip's shots, frame scores, beats and speech live in a file beside it, and shooting time comes from the container metadata.
- [Cold open, then hook: 8-10 s of best frames, hand-picked from a contact sheet](/library/cold-open-then-hook-contact-sheet/): The opening that holds a viewer on real footage: 8-10 s of the strongest frames with no speech, then one line with a twist. What to look for on the sheet, and why the automatic pick is wrong.
- [The critic pass: repeats and sagging scenes first, mid-word joins second](/library/critic-pass-two-passes/): A two-pass review prompt for a subagent or a second session: pass one on structure (repeats, sagging scenes), pass two on joins (mid-word cuts, audio seams). One read finds one kind of problem.
- [A contact sheet of every cutaway with its line under it](/library/cutaway-contact-sheet-with-lines/): The one-page check that catches off-topic cutaways before anyone watches: every cutaway frame in a grid, its sentence under it. Measured once: 12 of 54 automatic cutaways were off topic.
- [The cutaway rule: what is said, same place and time, never over moving lips](/library/cutaway-rule-same-place-same-time/): Three constraints for every cutaway in a talking film, and the agent prompt that applies them to a transcript. Kills what viewers read as broken: a picture from elsewhere, a face out of sync.
- [The day as one text file: an agent reads the speech and proposes the story](/library/day-as-one-text-file-story-and-cut-prompt/): The step before any timeline: the day's speech in shooting order, numbered by clip and sentence, read by an agent like a scriptwriter. It proposes story, scenes, hook and cutaways; you argue in text.
- [Length follows the material: cut stammers and repeats, not thoughts](/library/length-follows-the-material/): The decision rule for how long a film should be. A target length makes you stretch a thin day or chop a full one; the material decides, and the checklist says what may be removed.
- [Promise and payoff: find the pairs that thread a multi-day film](/library/promise-payoff-pairs-multi-day-film/): An agent prompt that reads several days of transcripts and pairs every promise ('tomorrow we'll buy the boat') with the moment it is kept or broken, so the film has a thread, not a sequence of days.
- [Read the film as text before rendering: the last check that costs nothing](/library/read-the-film-as-text-before-rendering/): The cut, printed as its lines in order, read by someone who never saw the raw footage. Catches the question whose answer was cut, the name said before the person, the 'this' that points at nothing.
- [Scenes, not best phrases: keep the lead-in, the talk and the reaction](/library/scenes-not-best-phrases/): Why a reel of good lines confuses everyone who was not there, and the checklist for keeping a scene whole: the lead-in, the talk, the reaction, with filler trimmed only at the ends.
- [Take something from every clip, and list the ones you cut with a reason](/library/take-something-from-every-clip/): A rule for cutting someone else's footage, or your own from a year ago: each clip was filmed because it mattered, so each gets a chance, and the rejects get a written reason the person can argue with.
- [Voice as one continuous track, pictures on top, and the one-frame length check](/library/voice-as-one-continuous-track-length-check/): The assembly rule for talking films: cut the audio from the same pieces as the picture, snapped to frames, then verify film length equals voice length. Drift over one frame is a bug, not a quirk.

### Captions & text (8)
On-screen text, subtitles, reading speed, safe zones, and caption prompts.
- [Burned subtitles for 9:16: position, lines, characters, colour, as parameters](/library/burned-subtitles-9-16-parameters/): Settings for subtitles burned into vertical video for muted feeds: above the platform UI, two lines, about 32 characters each, white with a dark outline. Starting values, checked on a phone.
- [Accessible on-screen text: contrast, the bottom 20 percent, no flashing](/library/caption-accessibility-checklist/): A checklist for text that everyone can read, including people watching muted, on a small screen, in sunlight, or with photosensitivity. Eight checks, each with the parameter to test against.
- [Three caption variants plus hashtags, with per-platform length limits](/library/caption-variants-hashtags-per-platform-prompt/): An agent prompt that writes three captions (short, story, question) and a hashtag set per platform, counting characters and hashtags against limits you paste in from today's upload form.
- [Burn subtitles with ffmpeg: the command with size, outline and margin](/library/ffmpeg-burn-in-subtitles-command/): One ffmpeg command that burns an SRT into a 9:16 video with white text, a dark outline and the block held above the platform UI, plus the check that your ffmpeg build can run it at all.
- [Hook text on screen: a plan for the first three seconds, word by word](/library/hook-text-on-screen-plan-prompt/): A prompt that plans what text appears in the first 3 seconds of a vertical video: the words, the moment each appears, the hold, what the picture does under it. Written so the hook works muted.
- [Reading speed for on-screen text and speech: the parameters to check against](/library/reading-speed-on-screen-text-parameters/): How long a text overlay must stay up and how many words a voice can carry per second, given as parameters you measure on yourself, with the formula and the two failure modes: unreadable, and slow.
- [SRT cleanup: fix names from a glossary, merge short cues, cap line length](/library/srt-cleanup-glossary-merge-cues-prompt/): An agent prompt that takes a raw speech-to-text SRT and returns one you can publish: names fixed from your glossary, sub-second cues merged, lines wrapped at a character cap, timings untouched.
- [Transcript to YouTube chapters: timestamps in the format the description needs](/library/transcript-to-youtube-chapters-prompt/): A prompt that turns a timestamped transcript into a chapter list for the YouTube description: first chapter at 0:00, at least three, each 10 seconds or more, titles that say what the viewer gets.

### B-roll (6)
Finding, generating and placing cutaways that show what is being said.
- [From a sentence to five search queries and one generation prompt](/library/broll-search-query-generator-prompt/): A prompt that turns each line needing a cutaway into five queries for your own footage or a stock site, ordered from literal to loose, plus one generation prompt as the fallback when nothing is found.
- [B-roll shot list from a transcript: the table to film or generate from](/library/broll-shot-list-from-transcript-table/): An agent prompt that reads a transcript and returns a shot table (timestamp, line, shot, source: have / film / generate) for a camera or a video model, grouped so each location is filmed once.
- [Cutaway matching: sentence to a literal visual, same place and time](/library/cutaway-matching-sentence-to-visual-prompt/): A prompt that reads each sentence of a transcript and names the one picture that shows it, with the place and time it must come from, so the shot list is a list of things, not moods.
- [Generated b-roll or real: the decision rule](/library/generated-vs-real-broll-decision-rule/): When a generated cutaway is fine (faceless, no logos, no claim about a real place or time) and when only footage from the same day will do. Five questions, in order, before you open a video model.
- [A mentioned object must be seen, ideally just before the line about it](/library/mentioned-object-must-be-seen-checklist/): The rule that turns 'X is mentioned, never shown' from a viewer complaint into a check you run on the transcript: every named thing gets a shot, placed just before or on the line.
- [Screen-recording b-roll for app demos: what to record, size, cursor](/library/screen-recording-broll-rules-app-demos/): Rules for screen captures used as cutaways in a product video: real-looking data, output-size or 2x resolution, a slow cursor, one action per clip, and what makes a recording unusable.

### Music & sound (8)
Beat sync, scoring, loudness, stripping copyrighted music, voice cleanup.
- [Beat-sync cutting: cut on the beat, not on every beat](/library/beat-sync-cut-not-every-beat/): A rule and an agent prompt for cutting to music from a list of beat timestamps: cuts land on beats, phrases get room to breathe, and the best shot is held through the hook.
- [Prompt for a music generator: a 30-second instrumental for a short](/library/generated-music-30s-track-brief-prompt/): A brief in the shape music generation tools read: structure by seconds, BPM, three instruments, no vocals, a drop that lands on your hook cut, and an ending that stops instead of fading.
- [Live music in frame: one continuous audio span, picture cuts on top](/library/live-music-one-continuous-audio-span/): When a band or a busker is in the shot, keep one unbroken stretch of that clip's audio under the whole scene and cut only the picture; cut the audio per shot and the beat restarts.
- [Level every chapter to -16 LUFS with ffmpeg loudnorm](/library/loudness-normalize-minus-16-lufs-ffmpeg/): One ffmpeg line that brings a file to -16 LUFS integrated and -1.5 dBTP true peak without touching the video, the two-pass version for exact results, and the timestamp trap on upload.
- [Music brief: describe the track you need before you search for it](/library/music-brief-prompt-for-picking-a-track/): A fill-in brief that names mood as harmony, a BPM range, genre, length and where the drop must land relative to your hook, so a library search or a composer returns something that fits the cut.
- [Score with a hole, not ducking, where something plays live](/library/score-hole-where-live-sound-plays/): Cut the score to silence under live music, a laugh or a knock instead of ducking it; ducking is audible, a hole is not. The rule, the measured levels and the ffmpeg line.
- [Strip other people's music before upload with Demucs and ffmpeg](/library/strip-other-peoples-music-demucs/): Car radio, shop speakers and festival stages trigger Content ID. Split the soundtrack into stems, find the music on drums plus bass, keep the voice, replace the music, rebuild audio only.
- [Voice cleanup checklist: room tone, de-ess, noise gate, in that order](/library/voice-cleanup-checklist-room-tone-deess-gate/): Six passes that turn a phone or lav recording into a usable voice track, each with the ffmpeg filter and a starting parameter to adjust by ear, in the order that keeps the gate off word endings.

### Growth (10)
Posting cadence, hooks that convert, campaign links, when to pay creators.
- [Measurement: one store campaign link per platform and account](/library/campaign-links-per-platform-and-account/): The iOS campaign link format with the provider token and a 40-character ct tag, the Android Play referrer, where installs show up, and the rule to judge a format after a week on installs, not views.
- [The creator budget gate: can you afford a paid creator yet?](/library/creator-budget-gate-payback-arithmetic/): A fill-in prompt that divides a creator's monthly retainer by your net revenue per sale to get payback sales per month, then says whether you are in Phase 1 (founder-led, $0) or allowed to pay.
- [The download ask lives in the comments, not in every video](/library/cta-in-comments-not-in-every-video/): A call to action in every video is what gets a video scrolled. Put the app name in the replies to 'what app is this?', keep the link in the bio, and write the replies before you need them.
- [Phase 1, founder-led: the four formats and what each one buys](/library/founder-led-phase-one-four-formats/): Educational converts, POV and humor get reach, story builds trust, comparison works when the app replaces something expensive. A prompt that plans a week of founder videos across all four.
- [In-app growth levers: brand credit, 9:16 output, one-tap preset](/library/in-app-growth-levers-credit-vertical-preset/): Four product changes that turn every export into UGC and make a creator's demo work in one tap. An audit prompt for the codebase that marks each lever done or next, plus the disclosure rule.
- [2-3 niche accounts, one audience archetype each, one app per account](/library/niche-accounts-one-archetype-each/): Why several small accounts beat one big one for an app: each speaks to one kind of viewer. A prompt that defines the archetypes and the account plan, and the clone trap that gets accounts suppressed.
- [Phase 2 trigger: when to pay micro-creators, and how much](/library/phase-two-trigger-paid-micro-creators/): Pay nobody until one video passes a view threshold AND its campaign link shows installs. Then 3-5 micro-creators in the same niche, paid per video or per million views, no retainer yet.
- [Cadence: 1-2 posts a day, one vertical cut to TikTok, Reels and Shorts](/library/posting-cadence-one-vertical-cut-three-feeds/): The minimum posting rhythm for Phase 1 and the production habit that makes it possible: one 9:16 master per idea, three uploads, no per-platform re-edit. With the ffmpeg line for burned captions.
- [Weekly growth review: an agent reads the posts and the installs per campaign](/library/weekly-growth-review-agent-prompt/): Paste the week's posts and the installs per campaign link; the agent reports numbers first, then what worked by name, then 3-4 actions, judging by installs and by multiples, never by a 20 % swing.
- [YouTube upload checklist: gate the file, publish private, watch on a phone](/library/youtube-upload-checklist-private-then-phone-then-public/): Cheap checks first, upload last: title under 100 characters, the real shooting date and chapters in the description, captions as tracks, Shorts linked both ways, a private publish watched on a phone.

### Claude Code skills (9)
Executable skills from solo-factory: install one line, run it in Claude Code.
- [Turn an article or PRD into a social media pack (/content-gen)](/library/skill-content-gen/): Use when "create content", "write LinkedIn post", "social media pack", "marketing copy", "promotion content", "posts from this article", "repurpose this post", "посты из статьи", or need soc
- [Plan short-form growth for an app: founder-led first, creators after a signal (/creator-growth)](/library/skill-creator-growth/): Plan growth for a consumer app through short vertical video — founder-led content first, paid UGC creators only after a measured signal.
- [Strip AI patterns from a script or caption so it reads like a person (/humanize)](/library/skill-humanize/): Use when "humanize this", "make it sound human", "strip AI patterns", "clean up the copy", or text reads like AI-generated output with em dashes and stock phrases.
- [Write a landing page with copy, SEO, JSON-LD and a cookieless counter (/landing-gen)](/library/skill-landing-gen/): Turn a PRD into a landing page that converts and ships honest. One batch of intake questions, section-by-section copy with A/B headlines, a type, spacing, radius and motion system on Tailwind…
- [Separate vocals, music and drums from a recording (/stem-split)](/library/skill-stem-split/): Separate a song or a film's soundtrack into stems (vocals, drums, bass, other) with Demucs, locally, on the Apple GPU when there is one.
- [Transcribe audio and video locally with word timings (/transcribe)](/library/skill-transcribe/): Transcribe audio or video to text locally — on the Apple GPU with mlx-whisper large-v3, or faster-whisper on CPU/CUDA — with the language decided per stretch of speech, .srt subtitles, word…
- [Edit real footage into a film with the agent as the editor (/video-edit)](/library/skill-video-edit/): Edit real footage into a film with the agent as the editor — read the day's speech as text, write the cut as a script, lay cutaways that match the words, score it, strip other people's music, and…
- [Write a 30-45 s promo video script and storyboard from a product (/video-promo)](/library/skill-video-promo/): Use when "create video", "promo video", "video script", "storyboard", "demo video", "product video plan", or need video marketing material. Do NOT use for social media text posts (/content-g
- [Upload, title, chapter and track videos on a YouTube channel (/youtube-channel)](/library/skill-youtube-channel/): Run a solo founder's YouTube channel from the terminal — upload through the YouTube Data API, subtitles as tracks, thumbnails, publish, bulk hide, link Shorts to the long video, and read the…

## About and contact
- [About](/about/): the company, how we build.
- [Studio](/studio/): the video-generation studio with sign-in, coming; early access by email.
- [agents.txt](/agents.txt): policy for automated agents, in words.
- Contact: info@superduperai.co · book a call: https://calendar.app.google/n4GorZYpiAucGjAE6