Communitygithub.com

amplitude/builder-skills

Plan and produce video and visual assets for product launches — demo videos, GIFs, screenshots, and programmatic video with Remotion. Use this skill whenever someone asks to create a demo video, record a product walkthrough, make a launch GIF, plan visual assets for a launch, or decide what media to create for an announcement. Also trigger for "what should our demo video show," "how do we record the product," "I need visuals for the launch," "make a video for this launch," or any request about creating non-text media tied to a product release. Covers video scripting, recording, programmatic video (Remotion), GIF creation, screenshot best practices, and per-platform format guidance.

What is builder-skills?

builder-skills is a Cursor agent skill that plan and produce video and visual assets for product launches — demo videos, GIFs, screenshots, and programmatic video with Remotion. Use this skill whenever someone asks to create a demo video, record a product walkthrough, make a launch GIF, plan visual assets for a launch, or decide what media to create for an announcement. Also trigger for "what should our demo video show," "how do we record the product," "I need visuals for the launch," "make a video for this launch," or any request about creating non-text media tied to a product release. Covers video scripting, recording, programmatic video (Remotion), GIF creation, screenshot best practices, and per-platform format guidance.

Works with~Claude Code~Codex CLI✓Cursor
npx skills add https://github.com/amplitude/builder-skills/tree/HEAD/launch-skills/skills/launch-video

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Launch Video & Visuals

This skill covers the creation of visual and video assets for product launches. These are the highest-impact assets you'll create — a great demo video or GIF stops the scroll, communicates value faster than words, and gets shared. A bad one can actively undermine the launch by making the product look confusing or unpolished.

The media hierarchy

For most launches, the decision of what to create follows this order:

  1. Demo video — Shows the product in action with context. Best for explaining how something works.
  2. Animated GIF or screen recording loop — Shorter, auto-plays inline on social. Best for showing a specific interaction.
  3. Annotated screenshot — Static, fast to produce, good for showing a specific state or feature.
  4. Diagram or illustration — For architecture, concepts, or things that can't be screenshotted.

In general: use video when the flow matters, GIF when a single interaction communicates the value, and screenshots when one specific state is the point.

Demo video

Length by platform

PlatformTarget lengthHard limit
Product Hunt60-90 seconds3 minutes
Landing page hero60-90 seconds2 minutes
X/Twitter embedded30-45 seconds2 minutes 20 seconds
LinkedIn45-90 seconds10 minutes
YouTube (full demo)3-5 minutes—

The platform hard limits aren't just technical — engagement drops sharply beyond them. A 4-minute PH video is effectively no video.

Script structure (for short-form demo)

Keep this to 5-7 beats:

  1. Problem (5-10 seconds) — State the problem being solved. One sentence. Not a long setup.
  2. Introduce the solution (5-10 seconds) — Name the product and the core value prop.
  3. Demo: happy path (30-60 seconds) — Show the primary use case working end-to-end. This is the heart of the video.
  4. Key capabilities (10-20 seconds) — 2-3 quick cuts showing secondary features. Keep it fast.
  5. Proof point (5-10 seconds) — A metric, customer quote, or benchmark. One slide or voiceover line.
  6. CTA (5 seconds) — One action. "Try it free at [URL]" or "Sign up at [URL]."

Avoid: long intros, animated logos (audiences click away), slow product startup screens, and anything that doesn't show the product doing something.

Recording tips

  • Use a demo environment, not production. Clean data, no embarrassing customer info, reliable state.
  • Slow down deliberate interactions. People follow cursor movements better when you move intentionally, not at normal working speed.
  • Record at 2x your target resolution. Record at 2880×1800 or 1440×900 (Retina), then downscale for delivery. This gives you zoom room and looks sharper.
  • Hide everything extraneous. Close Slack notifications, hide browser bookmarks bar, use a clean browser profile. Distractions in the recording erode trust.
  • Capture more than you'll use. Record full workflows and cut in post. It's faster than re-recording because you missed a beat.

Voiceover vs. silent

Both work. The choice depends on context:

  • Voiceover: Warmer, more explanatory, works better on YouTube and landing pages. Requires a clean recording environment and good audio quality. Bad audio is worse than no audio.
  • Silent with text overlays: Works better on autoplay-with-mute contexts (social feeds). Faster to produce. Requires clear on-screen labels.

If you're unsure: record the demo silently, add text overlays for key moments, then decide whether to add voiceover based on the platform.

Tooling

  • Screen recording: Loom (quick), Screen Studio (polished output, good for marketing), QuickTime (raw), OBS (full control)
  • Video editing: CapCut (fast, easy), DaVinci Resolve (professional, free), Final Cut Pro, Adobe Premiere
  • Motion design / logo animations: After Effects, Motion (Mac), Jitter (web-based)
  • Captions/subtitles: Descript (also good for editing by transcript), Captions app, Rev
  • Programmatic video: Remotion (React-based — see section below)

Programmatic video with Remotion

For teams that ship fast and don't want to wait on a motion designer for every launch, programmatic video lets you write React components and render them as MP4 files. The video is code: version-controlled, parametrized, and iteratable without a timeline editor.

When to use programmatic video

Works well for:

  • Launch announcement clips (15-45 seconds) for social media
  • Product walkthrough videos showing UI in action
  • Feature highlight reels with text overlays and screenshots
  • Data-driven videos (benchmark comparisons, growth metrics)
  • Templated videos you'll reuse across launches (just swap content)

Less suited for:

  • Cinematic brand videos requiring complex motion design
  • Founder narrative videos with live footage
  • Videos that need extensive custom illustration or 3D

For major Tier 1 launches, you might combine approaches: programmatic video for social clips and a professional motion designer for the hero video.

Remotion setup

npx create-video@latest my-launch-video
cd my-launch-video
npm start  # Opens Remotion Studio for preview

Key concepts:

  • Composition: A video is a React component with a defined duration (in frames) and framerate
  • useCurrentFrame(): Hook that returns the current frame number — use it to drive animations
  • Sequence: Component that offsets its children in time — use it to sequence scenes
  • spring(): Animation utility for natural-feeling motion (ease-in/out)
  • Assets: Images, screenshots, and audio go in the public/ folder

Scene planning template

Before writing code, plan the video scene by scene:

FieldDescription
Scene #Sequential number
DurationSeconds (e.g., "3s")
PurposeWhat this scene communicates (one sentence)
Text contentExact text that appears on screen
Visual elementsScreenshots, icons, code snippets, diagrams
Animation styleFade in, slide from left, typewriter, scale up, etc.
Transition outHow this scene exits (fade, cut, slide)

Code patterns

Sequenced scenes:

<Sequence from={0} durationInFrames={90}>
  <HookScene />
</Sequence>
<Sequence from={90} durationInFrames={120}>
  <DemoScene />
</Sequence>
<Sequence from={210} durationInFrames={90}>
  <CTAScene />
</Sequence>

Text reveal:

const frame = useCurrentFrame();
const opacity = interpolate(frame, [0, 20], [0, 1], {
  extrapolateRight: 'clamp',
});

return <h1 style={{ opacity }}>Your primary value prop here</h1>;

Iteration workflow

  1. Plan scenes using the template above
  2. Collect assets — screenshots, logos, product images → public/ folder
  3. Write or prompt the first draft — get the structure and content right
  4. Preview in Studio — watch it through, note timing and visual issues
  5. Iterate — adjust timing, animation, and content. Usually takes 2-4 rounds
  6. Render — npx remotion render src/index.ts MyComposition out/video.mp4
  7. Check platform specs — verify resolution and file size work for your target platform

GIFs and short loops

GIFs auto-play on most platforms and are ideal for showing a single interaction — a UI state change, a CLI command output, an API response. They're faster to produce than video and often more effective for social posts.

When to use GIF vs. video

Use GIF when:

  • The entire value can be communicated in 3-8 seconds
  • You're showing a single UI interaction, not a workflow
  • The asset will be embedded in a tweet or README where video playback is less reliable

Use video when:

  • The value requires context (problem → solution)
  • The interaction takes more than 8 seconds to demonstrate
  • You need audio

Recording GIFs

  • Capture at 2x, downscale to target resolution
  • Keep under 5MB for web performance (use palette reduction or fewer frames)
  • Loop seamlessly — the start and end state should match so the loop doesn't jar
  • Tool options: CleanShot X (recommended for Mac), Kap, Giphy Capture, Gifski (for converting video clips)

Optimizing GIF file size

  • Reduce color palette (256 → 128 or 64 colors for many UI recordings)
  • Drop frames (30fps → 15fps is rarely noticeable in UI recordings)
  • Crop aggressively — show only what's changing, not the whole screen
  • Convert to MP4 with autoplay/loop instead of GIF when the platform supports it (MP4 is ~10x smaller than equivalent GIF)

Screenshots

Screenshots are underused in launches. A well-composed screenshot with clear annotation communicates a feature faster than a paragraph.

Composition

  • Show the product in a meaningful state — not an empty screen, not a loading state, not a screen full of dummy data that makes features hard to see
  • Use a clean environment — browser without tabs, dark or light mode consistently applied, no personal data visible
  • Highlight the relevant area — callout boxes, arrows, or highlights direct attention to what matters

Annotation tools

  • CleanShot X (Mac) — captures, annotates, and exports in one flow
  • Skitch — simple annotations
  • Figma / Sketch — for more polished product shots with custom styling

Browser framing

For web products, use a browser frame to make screenshots look intentional rather than raw. Tools like Screely, Browserframe, or custom Figma templates add a browser chrome overlay.

Multiple screenshots for feature grids

Landing pages and Product Hunt galleries often need 3-5 screenshots showing different aspects of the product. Plan these as a set:

  • Each screenshot shows a distinct capability
  • Consistent visual treatment (same zoom level, same browser theme, same annotation style)
  • Tell a progression: entry → key action → result

Asset checklist by tier

Tier 1

  • Demo video (60-90 seconds, suitable for PH and landing page)
  • Short social cut (30-45 seconds from the same recording)
  • 3-5 annotated screenshots for landing page and PH gallery
  • 1-2 GIFs for social posts (showing key interactions)
  • Open Graph image for blog post and social link previews

Tier 2

  • 1-2 GIFs or short screen recording
  • 2-3 screenshots for landing page section
  • Open Graph image

Tier 3

  • 1 screenshot
  • Optional: short GIF if the change is visual

Open Graph images

Every piece of content that gets shared as a link (blog post, landing page, changelog entry) should have a custom Open Graph (OG) image. The OG image is what appears when the link is pasted into Twitter, Slack, iMessage, or LinkedIn.

  • Size: 1200×630px
  • Content: Product name + primary value prop. Treat it like a billboard — readable at small size
  • Consistency: Use a template so all your launch content has a cohesive look
  • Tools: Figma template, Vercel OG (code-generated), Bannerbear (automated)

Video specs by platform

PlatformResolutionMax lengthFormatNotes
X/Twitter1280×720 or 1920×10802:20MP4 (H.264)Autoplay muted — add captions
LinkedIn1920×108010 minMP4 (H.264)Square (1080×1080) works well in feed
Product Hunt1920×108090 secMP4Keep under 50MB
Website hero1920×1080No limitMP4/WebMConsider autoplay loop (no audio)

Companion skills

  • launch-strategy — determines which assets are needed for the launch tier
  • launch-tweet — the GIFs and videos go in the tweet (attached, not linked)
  • launch-landing-page — the demo video and screenshots go on the page
  • launch-distribution — per-platform format requirements

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

amplitude/builder-skills

Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers.

amplitude/builder-skills

Deeply analyze Amplitude dashboards by analyzing key charts, surfacing top areas for concern and takeaways, identify anomalies, then explain changes using customer feedback trends.

amplitude/builder-skills

Designs A/B tests with proper metrics and variants, analyzes running or completed experiments, and interprets results with statistical rigor. Use when setting up experiments, checking experiment status, analyzing results, or making ship decisions.

amplitude/builder-skills

Synthesizes customer feedback into actionable themes including feature requests, bugs, pain points, and praise. Use when planning product roadmap, understanding user sentiment, investigating specific issues, or preparing voice-of-customer reports.

amplitude/builder-skills

Analyze MCP server usage instrumented with Amplitude's MCP Analytics SDK: break usage and errors down by tool, read the rationales within each tool to see what callers are trying to do, and produce a prioritized write-up of actionable fixes. Use this skill whenever the user asks to understand how their MCP server is being used, what agents/users are trying to do with it, why tool calls are failing, what to fix or improve in their MCP server, or asks for an "MCP usage report", "tool error analysis", "intent analysis", "rationale clustering", or "MCP insights". Also trigger when the user mentions [MCP]-prefixed events, tool rationale, tool call errors, or just finished instrumenting their MCP server and wants to see what the data says. Requires the Amplitude MCP connector.

amplitude/builder-skills

Read lost deals and churned accounts from your CRM, extract reasons clustered by theme (missing features, pricing, competitors, UX), and write a prioritized weekly analysis with product improvement recommendations. Use before roadmap planning or to build the case for prioritizing retention work.

amplitude/builder-skills

Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices. Use when you know what you want to measure but prefer not to build the chart manually.

amplitude/builder-skills

Guide an Amplitude user through building a custom agent by suggesting use cases grounded in their role and data, shaping the idea into a well-formed spec, and generating a ready-to-run Global Agent deeplink that creates it. Use to create, build, or set up a custom agent, automate a recurring analysis, or put a repeated report on a schedule.

amplitude/builder-skills

Builds comprehensive Amplitude dashboards from requirements or goals, organizing charts into logical sections with appropriate layouts. Use when creating a complete dashboard from scratch or assembling existing charts into a cohesive view.

amplitude/builder-skills

Monitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.

amplitude/builder-skills

Pull Intercom tickets and Slack support messages from the past 7 days, classify each signal, enrich with CRM data (ARR, plan, renewal), score by customer value and churn risk, and output a tiered priority report saved to Drive. Use when you need a fast, data-driven view of what support signals matter most.

amplitude/builder-skills

Use this skill whenever a user wants to improve existing pages on their website to get cited more by AI models — whether they say "our pages aren't getting cited", "improve this page for AI visibility", "which of our pages should we update", "make this article more cite-worthy", "our competitors are getting cited instead of us", "update our content for AI search", or any variation where the goal is improving an existing asset rather than creating something new. This skill pulls owned pages from AI Visibility, identifies which ones have citation potential but are underperforming, compares them against the external pages that are winning citations on the same topics, and produces section-level rewrites or a full-page update — then pushes the revision to the CMS as a draft. Trigger even if the user just says "help me get cited more" or "why is [competitor] getting cited instead of us".

amplitude/builder-skills

Use this skill whenever a user wants to win AI citations on prompts that competitors currently dominate — whether they say "competitors are getting cited instead of us", "we're losing on these prompts", "how do I outrank [competitor] in AI answers", "find prompts where we should be winning", "create content to beat [competitor]", or any variation where the goal is capturing AI share on prompts a competitor currently owns. This skill pulls competitor visibility data from AI Visibility, identifies the specific prompts where competitors win and Amplitude is absent, clusters them by intent, and produces targeted comparison pages, alternatives content, or rebuttal assets — then pushes drafts to CMS. Trigger on any mention of competitor, prompt hijack, outrank, or "why is [competitor] getting cited instead of us".

amplitude/builder-skills

Use this skill whenever a user wants to turn AI Visibility data into published content — whether they say "find content gaps", "what should we write about", "which topics have low visibility", "help me get cited by AI models", "create a blog post from our AI Visibility gaps", "we're losing to competitors on these prompts", or any variation where they want to go from AI visibility weakness to a draft article, landing page, or FAQ. This skill connects directly to Amplitude AI Visibility data (topics, prompts, visibility scores, citations, competitor data, full LLM responses and sources) and produces a publish-ready content brief plus full article draft. If the user mentions CMS (WordPress, Webflow, Contentful, Sanity, HubSpot, Ghost, Shopify), also trigger this skill to push the draft directly. Trigger even if they just say something vague like "what content should we create?" in an AI Visibility context.

amplitude/builder-skills

Use this skill whenever a user wants to test content variants before publishing to find which one will get cited most by AI models — whether they say "which version of this content will perform better", "test this article before we publish", "simulate how AI will respond to this content", "which angle should we use", "generate content variants and pick the winner", "run a simulation before publishing", or any variation where the goal is data-driven content selection rather than gut-feel publishing. This skill takes an identified content opportunity, generates 2–3 distinct variants with different angles or structures, scores them against actual AI model responses from AI Visibility, references the Simulate Changes feature for pre-publish validation, and produces a clear recommendation on which variant to publish — then pushes the winner to CMS. Trigger on any mention of "simulate", "test variants", "which performs better", "A/B content", or "before we publish".

amplitude/builder-skills

Use this skill whenever a user wants to understand which external sources are being cited by AI models on topics relevant to their brand, and wants to create content that will outrank those sources — whether they say "what sources are AI models citing", "why is [third-party site] being cited instead of us", "we want to be the definitive source on X", "build something that gets cited more than G2 or TechRadar", "create an authoritative asset", or any variation where the goal is producing a new reference asset (definition page, benchmark, methodology, glossary, comparison hub) designed to beat existing top-cited sources. This skill analyzes AI Visibility source data, reverse-engineers what makes top-cited pages authoritative, and produces a superior source asset — then pushes it to CMS as a draft. Trigger on any mention of "sources", "third-party citations", "authoritative content", "definitional pages", or "outrank".

amplitude/builder-skills

Instrument a Node/TypeScript MCP server with Amplitude's @amplitude/mcp-analytics SDK so tool calls, sessions, and rationale are tracked as Amplitude events. Use this skill whenever the user wants to add Amplitude analytics to their MCP server, mentions "MCP Analytics", "@amplitude/mcp-analytics", "instrument my MCP server", "track MCP tool calls", "add rationale to my MCP tools", or wants agent traffic (Claude, Cursor, ChatGPT) attributed back to Amplitude. Also use for adding UTM tagging to MCP-returned links, or for troubleshooting identity/user_id mismatches between MCP events and web/mobile Amplitude data.

amplitude/builder-skills

Instruments a pull request with Amplitude analytics that conform to the project's existing taxonomy. Reads the tracking plan via the Amplitude MCP server (events, properties, naming conventions), analyzes the PR diff to find the few user actions genuinely worth tracking, detects the codebase's SDK and tracking patterns, and adds instrumentation that matches both. Optionally (opt-in) stages new events and properties on an Amplitude tracking-plan branch for data-governance review. Use when asked to "instrument this PR", "add analytics to this change", "add tracking", "add Amplitude events", "instrument this feature", or "what should I track here".

amplitude/builder-skills

Diagnoses product health by cross-referencing Amplitude analytics (dashboards, charts, funnels, feedback, AI agent analytics), optionally Datadog (errors, latency, stack traces), and optionally Slack (qualitative feedback, bug reports, feature requests). Identifies what's broken, what's working, and what to do about it — with root causes, not just symptoms. Use when asked to "diagnose my product", "what's going on", "product health check", "what's broken", "where are users struggling", "give me a product diagnosis", or "what should I focus on".

amplitude/builder-skills

Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.

Related Skills