Communitygithub.com

getedgehq/product-launch-video

Turn a product URL, launch brief, or approved script into a production-ready launch video. Use for product reveals, feature announcements, SaaS launches, and narrated product films; not for generic explainers or editing existing footage.

Was ist product-launch-video?

product-launch-video is a Claude Code agent skill that turn a product URL, launch brief, or approved script into a production-ready launch video. Use for product reveals, feature announcements, SaaS launches, and narrated product films; not for generic explainers or editing existing footage.

Funktioniert mit~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/getedgehq/skills/tree/main/product-launch-video

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Product Launch Video

Create a launch film whose story, visual system, motion, and evidence all come from the product being launched. The deliverable is a rendered video plus the editable project that produced it.

Use HyperFrames when it is installed. A Remotion project is also supported; prefer maintained remocn components over recreating common animation primitives. Do not switch stacks after the storyboard is approved.

Inputs to lock

Before building, establish:

  • product URL or source brief;
  • audience and the one change in belief the film should create;
  • aspect ratio, target duration, language, and narration choice;
  • claims that may appear and the evidence behind each;
  • whether an existing script must remain verbatim or may be restructured.

If any of these would materially change the film, ask once before starting.

Required output

Keep the project editable. At minimum, produce:

capture/                 product copy, screenshots, logos, and design tokens
STORYBOARD.md            approved shot-by-shot plan
SCRIPT.md                narration, when the film is narrated
design.md                type, color, spacing, motion, and framing rules
compositions/            source for every shot
renders/launch.mp4       final delivery

Do not treat a preview, storyboard, contact sheet, or silent draft as the final video.

Workflow

1. Capture the product

Inspect the supplied URL or assets. Preserve exact product copy, real UI, logos, typography, colors, and interface states. Record every usable asset and its source. Do not invent features, customers, metrics, or integrations.

If no website exists, create a small source record from the brief and supplied assets so later shots still have a traceable basis.

2. Choose the story

Write one sentence for each of these before storyboarding:

  • the audience's present frustration;
  • the product's distinctive mechanism;
  • the proof the viewer should believe;
  • the action the viewer should take.

Select only the beats the source material supports. A short film usually needs a hook, mechanism, proof, and close; it does not need a feature inventory.

Read references/story-and-shot-system.md when planning the sequence.

3. Establish the visual system

Derive design.md from the captured product rather than from a generic video template. Define the canvas, typography, color roles, grid, safe areas, visual density, motion character, caption treatment, and transition family.

Limit the film to one visual grammar. Repetition creates identity; a new style for every shot makes the film feel assembled from templates.

4. Storyboard before animation

For every shot, record:

  • start and end time;
  • narrative job;
  • exact on-screen copy;
  • source asset or UI state;
  • composition and camera intent;
  • entrance, development, and exit;
  • transition to the next shot;
  • any claim and its evidence source.

The frame must continue developing for its useful duration. Avoid an entrance animation followed by several seconds of static content.

Show the storyboard for approval before building the full film.

5. Build with maintained primitives

HyperFrames is preferred for HTML shot sequences. For Remotion, read references/remotion-and-remocn.md and use remocn for common typography, terminal, chart, background, and transition behaviors. Custom animation is appropriate only when the product requires a motion idea that the library cannot express.

Every shot must be deterministic at an arbitrary frame. Do not rely on runtime timers, non-seeded randomness, or interaction state that a renderer cannot reproduce.

6. Review the assembled film

Before rendering, inspect:

  • first, middle, and final frames of every shot;
  • every transition seam;
  • text wrapping, clipping, contrast, and safe areas;
  • timing against narration and music;
  • product fidelity and claim accuracy;
  • the full film at normal speed with audio;
  • a silent pass, so the visual story still makes sense.

Run node scripts/check-project.mjs <project-dir> for the package-level project gate. Also run the native lint, validation, and render checks of the selected video stack.

Pause for approval on the assembled preview. Render the final MP4 only after approval.

Evidence boundary

A polished example demonstrates intended craft; it does not prove the skill improves model performance. Report separately:

  • package and project checks;
  • successful final render;
  • human visual review;
  • any comparative evaluation, only when recorded runs and scoring exist.

Never call the skill evaluated because one attractive video was produced.

Failure conditions

Stop rather than ship when:

  • the primary product claim cannot be sourced;
  • captured UI is replaced by invented interface chrome;
  • a shot is illegible at delivery resolution;
  • narration and picture disagree;
  • the project cannot render deterministically;
  • the editable source or final MP4 is missing.

Individual skills in this repo

This repo contains 15 individual skills — each has its own dedicated page.

getedgehq/agent-evals

Build evals for an AI agent that already does real work. Use when someone asks "how do I know my agent is right", wants to test an agent before trusting it, compare models on cost versus quality, or turn production failures into tests. Walks from first tasks and yes/no verifiers, to isolated environments, to a trace-driven improvement loop.

getedgehq/cli-ux-review

Audit a command-line tool for user-friendliness — clear situation / next-step / options in every output, colour-highlighted runnable commands, no raw jargon, no silent hangs. Invoke for "CLI UX audit", "review my CLI", "is this CLI intuitive", or before any CLI release.

getedgehq/generate-image

Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

getedgehq/harness-first

Diagnose and fix an unreliable, expensive, or unsafe LLM agent by auditing its harness (golden set, judge, cost caps, data layer, action approvals, tracing) before blaming or swapping the model. Use when someone says an agent is "burning tokens", "hallucinating", "brittle", gives inconsistent answers, asks whether to switch to a cheaper/better model, or wants to ship an agent or prompt change to customers.

getedgehq/http-error-triage

Run before concluding anything from an HTTP error on a third-party API. Separates a real credential/entitlement problem from a CDN or WAF block, a wrong endpoint, or a client-signature ban. Use whenever an API returns 401/403/402/429 and you are about to say "the key is dead", "credits are exhausted", "the plan lacks access", or "we are rate limited".

getedgehq/linkedin-media-prep

Convert, crop, resize, and compress images and videos for optimal LinkedIn upload quality and file size. Use when the user wants to prepare a photo, image, or video for LinkedIn (profile picture, cover photo, post image, article featured image, post video, or video ad), optimize file size for LinkedIn, crop and resize for LinkedIn dimensions, convert HEIC/RAW/PNG/MOV to LinkedIn-ready JPEG or MP4, or mentions LinkedIn media requirements, specs, or limits.

getedgehq/monid

>-

getedgehq/opendraft

An 18-agent pipeline that turns one topic line into a drafted

getedgehq/people-search

Find and rank professional people for recruiting, partnerships, sales, or research from user-provided data, public web sources, an authenticated search session, or a connected provider. Use for people discovery, LinkedIn or Sales Navigator search design, profile-list ranking, or provider filter translation.

getedgehq/rocketlist

Turn a CV into a shortlist of live startup roles from Rocketlist's public job board, including adjacent job titles the person would never have searched for, each with its published salary, the evidence for the fit, and a direct apply link. Use for "find roles I would be a strong fit for", career pivots, remote or VC-backed job hunts, and salary-visible role discovery.

getedgehq/security-audit-checklist

Run a comprehensive security audit across application code, cloud infrastructure, containers, CI/CD pipelines, and infrastructure-as-code. Covers privacy compliance, OWASP basics, secret leakage, API security, IAM misconfigurations, storage exposure, Kubernetes hardening, and network security. Use when the user asks to audit, review, or harden app or cloud security, check for secrets, scan for XSS/SQLi, verify security headers, review Terraform/CloudFormation, audit AWS/GCP/Azure configs, or perform any security-focused review.

getedgehq/shadcn-first

>-

getedgehq/strip-image-ai-metadata

Strip C2PA and AI-generation metadata from images (PNG, JPEG, WebP) to remove "Generated by AI" / "ChatGPT" / "DALL-E" labels that platforms like LinkedIn, Instagram, and X display. Use when the user wants to clean AI-generated images before posting, remove AI attribution from photos, strip C2PA manifests, sanitize image metadata for professional use, or verify whether an image contains C2PA data.

getedgehq/top-down-comms

>-

getedgehq/workplan

Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: "workplan", "work plan", "create a plan", "what's the plan", "where was I", or when Claude detects

Verwandte Skills