本文へ移動
cccskills
無料GitHub で公開

ozor-video-best-practices

Expert guide for crafting high-quality video prompts for Ozor.ai, the AI video generation platform. Use this skill whenever the user mentions Ozor, wants to create a launch video, product demo, feature announcement, explainer video, social ad, release notes video, investor update, tutorial, or any marketing video. Also trigger when the user asks for help writing video prompts, improving video output, structuring video scenes, choosing video formats, or wants best practices for AI video creation. Trigger on phrases like 'make a video', 'create a launch video', 'video for my product', 'Ozor prompt', 'video best practices', 'explainer video', 'product demo video', 'social clip', 'announcement video', or any request involving short-form video content for products and marketing.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md12.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Ozor Video Best Practices

A comprehensive guide to creating outstanding AI-generated videos with Ozor.ai. This skill encodes the principles, patterns, and prompt formulas that consistently produce professional results — so you spend fewer credits and get better output on the first try.

What Ozor Is

Ozor is an AI video agent that turns text prompts (or uploaded documents) into fully produced, animated videos. It renders each scene as an animated React component at 30 FPS, supports real-time preview, and exports to MP4 at 720p, 1080p, or 4K. It's designed for product launches, marketing, and explainers — not talking-head or long-form content.

Key capabilities:

  • Text-to-video from a single prompt
  • Document-to-video from PDFs, PowerPoints, images, Google Docs, and URLs
  • Brand Kit extraction from your website (logo, colors, fonts)
  • Scene-by-scene editing and regeneration
  • Templates for common use cases
  • Landscape (16:9) and portrait (9:16) formats

The Prompt Quality Principle

The single biggest factor in Ozor output quality is the prompt. A vague prompt forces the AI to guess — and its guesses will be generic. A specific prompt gives it constraints to work within, which is where creativity happens.

Every effective Ozor prompt answers five questions:

  1. What — the topic, product, or message
  2. Who — the target audience
  3. How long — duration or scene count
  4. What it looks like — visual style, colors, mood
  5. What it should do — the goal (launch, explain, sell, update)

Prompt Formulas

These are copy-and-customize templates. Replace [brackets] with specifics.

Product Launch

Create a 45-second product launch video for [product name].
12 scenes:
(1) Hook — bold one-line problem statement
(2) Problem setup — show the pain point visually
(3) Solution reveal — introduce [product name] as the answer
(4) Product in action — show the main UI or experience
(5) Feature 1 — [key feature with one-line benefit]
(6) Feature 2 — [key feature with one-line benefit]
(7) Feature 3 — [key feature with one-line benefit]
(8) How it works — quick 3-step flow
(9) Social proof — "[customer quote]" or key metric
(10) Pricing/offer — "[pricing or launch offer]"
(11) CTA — "[your call to action]"
(12) Logo close — logo + tagline + URL

Style: [minimal / bold / dark / light]. Brand colors: [colors]. Target audience: [who].

Social Short (Vertical)

Create a 15-second vertical video (9:16) for [platform].
5 scenes:
(1) Hook — bold text: "[attention-grabbing statement]"
(2) Problem — quick visual of the pain point
(3) Solution — show the product or key idea in action
(4) Proof — [metric, testimonial, or before/after]
(5) CTA — "[short call to action]" with logo

Style: [energetic / calm / funny]. Use large text and minimal background.

Feature Announcement

Make a 30-second video announcing [feature name] for [product].
10 scenes:
(1) Hook — "[feature name] is here" with bold text
(2) Problem — the pain point this feature solves
(3) Old way — how users handled it before (brief)
(4) New way — introduce the feature visually
(5) How it works — step 1 of the workflow
(6) How it works — step 2 of the workflow
(7) How it works — step 3 of the workflow
(8) Key benefit — the single biggest improvement
(9) Availability — who gets it and when
(10) CTA — "[try it now / learn more]" with link

Keep the tone [professional / casual / excited]. Use [brand color] as the primary accent.

Explainer / How It Works

Create a 60-second step-by-step explainer for [topic or process].
15 scenes:
(1) Hook — "[topic] explained in 60 seconds"
(2) Why it matters — one-line context for the audience
(3) Overview — high-level diagram or flow
(4) Step 1 — [first step with visual]
(5) Step 1 detail — key tip or callout
(6) Step 2 — [second step with visual]
(7) Step 2 detail — key tip or callout
(8) Step 3 — [third step with visual]
(9) Step 3 detail — key tip or callout
(10) Step 4 — [fourth step with visual]
(11) Step 4 detail — key tip or callout
(12) Common mistake — what to avoid
(13) Pro tip — one expert recommendation
(14) Recap — summary of all steps in one view
(15) CTA — "[next action]" with link or resource

Audience: [who this is for]. Tone: [simple and clear / technical / conversational].
Use a [light / dark] background with [color] accents.

Release Notes

Create a release notes video for [product name] version [X.X].
2–3 scenes per feature:
(1) Intro — "What's new in [version]" with logo
(2) Feature 1 title — [feature name] with one-line benefit
(3) Feature 1 demo — show it in action
(4) Feature 2 title — [feature name] with one-line benefit
(5) Feature 2 demo — show it in action
(6) Feature 3 title — [feature name] with one-line benefit
(7) Feature 3 demo — show it in action
(8) Recap — all features in a single summary view
(9) CTA — "Try it now" with link

Style: [clean / playful / technical]. Duration: ~30 seconds.

Investor Update

Create a 45-second investor update video for [company name].
15 scenes:
(1) Title card — "[Company] Q[X] Update"
(2) Headline metric — [e.g., MRR] with large number
(3) Growth chart — visual trend over time
(4) Key milestone 1 — [what happened]
(5) Key milestone 2 — [what happened]
(6) Revenue breakdown — key financial data
(7) Customer highlight — notable win or logo
(8) Product update 1 — [what shipped]
(9) Product update 2 — [what shipped]
(10) Team update — key hires or team growth
(11) Roadmap — Q[X+1] priorities
(12) Roadmap detail — top 2–3 initiatives
(13) Key risk or challenge — [brief note]
(14) The ask — [what you need from investors]
(15) Close — logo + contact info

Tone: confident and data-driven. Style: professional, dark background, clean typography.

Tutorial / Walkthrough

Create a step-by-step tutorial for [task or feature].
2–3 scenes per step:
(1) Intro — "How to [task]" with context
(2) Prerequisites — what you need before starting
(3) Step 1 instruction — what to do
(4) Step 1 visual — annotated screenshot or demo
(5) Step 2 instruction — what to do
(6) Step 2 visual — annotated screenshot or demo
(7) Step 3 instruction — what to do
(8) Step 3 visual — annotated screenshot or demo
(9) Step 4 instruction — what to do
(10) Step 4 visual — annotated screenshot or demo
(11) Result — show the finished outcome
(12) CTA — "Learn more at [link]"

Use "Next:" transitions between scenes. Include annotated screenshots where possible.
Audience: [who]. Tone: [friendly / technical / conversational].

Scene Structure Principles

Think in scenes, not paragraphs. Every scene should have one job:

  • Hook — grab attention in the first 2 seconds (especially for social)
  • Problem — state the pain point the audience recognizes
  • Solution — show your product or concept in action
  • Proof — metrics, testimonials, before/after, social proof
  • CTA — tell them exactly what to do next

The classic flow that works for almost any video: Intro → Problem → Solution → CTA

For longer videos, extend the middle: Intro → Problem → Solution → Benefits → Proof → CTA

Scene count guidelines by use case (aim for ~1 scene per 3 seconds):

  • Social ads: 5–8 scenes (15–30s)
  • Product launches: 10–15 scenes (45–60s)
  • Explainers: 12–20 scenes (60–90s)
  • Investor updates: 12–15 scenes (45–60s)
  • Release notes: 2–3 scenes per feature
  • Tutorials: 2–3 scenes per step

Format Selection

Choose before you start — changing aspect ratio later regenerates all scenes.

Landscape (16:9) — 1920×1080px Best for: YouTube, LinkedIn, website embeds, presentations, investor decks, webinars, conference screens.

Portrait (9:16) — 1080×1920px Best for: Instagram Reels & Stories, TikTok, YouTube Shorts, Pinterest video pins, Snapchat.

Rule of thumb: if it's going on a phone feed, go portrait. If it's going on a screen or webpage, go landscape.

Brand Consistency

Set up a Brand Kit before creating videos. Ozor can auto-extract brand assets from your URL (logo, colors, fonts). Once set, every video inherits them automatically.

Upload assets before writing your prompt — the AI can only use what's already available. Reference uploaded assets by name in your prompt: "use the product screenshot I uploaded."

Editing Workflow

Ozor is conversational — you refine by chatting, not by dragging timelines.

The most effective editing pattern:

  1. Start broad — get the structure and flow right first
  2. Target one scene at a time — click the scene thumbnail, then ask for changes
  3. One change per message — stacked requests lead to mixed results
  4. Ask for alternatives — "give me 3 headline options for this scene"
  5. Save what works — save good scenes as templates for reuse

Useful editor commands:

  • "Edit scene 2 to..." — target a specific scene
  • "Add a new scene after scene 3" — insert at a position
  • "Make the text larger in scene 1" — adjust visual details
  • "Change the color palette to..." — restyle the whole video
  • "Regenerate scene 2" — redo one scene, keep the rest
  • "Make this scene shorter" — trim duration
  • "Save this as a template" — reuse later
  • "Export at 1080p" — trigger export

Common Mistakes to Avoid

  1. Being too vague — "make a cool video" gives generic results. Always specify duration, audience, style, and scene structure.
  2. Not targeting a scene — click the scene thumbnail before asking for changes, otherwise the AI may regenerate the whole video.
  3. Uploading assets after the prompt — upload images and brand assets first, then reference them.
  4. Requesting too many changes at once — one change per message. Get the text right, then refine animation.
  5. Skipping the Brand Kit — set it once, benefit forever.
  6. Wrong aspect ratio — pick 16:9 or 9:16 at the start. Changing later means regenerating everything.

Export Reference

QualityAvailable onBest for
720pFreeDrafts, previews, internal sharing
1080pPro ($29/mo)Social media, landing pages, presentations
4KBusiness ($69/mo)Conference screens, broadcast, premium campaigns

Exports render server-side in 2–5 minutes depending on length and complexity.

When Helping Users Write Ozor Prompts

When a user asks for help creating a video with Ozor, follow this process:

  1. Clarify the use case — what type of video? (launch, explainer, social ad, etc.)
  2. Identify the audience — who will watch this?
  3. Determine the format — landscape or portrait? What platform?
  4. Draft a structured prompt using the appropriate formula above
  5. Include specific visual direction — colors, style, mood, background
  6. Suggest a scene count based on the use case guidelines
  7. Remind about Brand Kit and assets — upload before prompting

Always produce a complete, copy-pasteable prompt the user can drop directly into Ozor. Don't give abstract advice — give them the actual prompt text.

Example: From Vague to Great

User says: "I need a video for my app"

You produce:

Create a 45-second launch video for [App Name], a [one-line description].
12 scenes:
(1) Hook — "[pain point the audience feels]"
(2) Problem — show the frustration visually
(3) Solution reveal — introduce [App Name] with logo
(4) Product in action — show the app's main screen with [key feature]
(5) Feature 1 — [benefit 1] with quick demo
(6) Feature 2 — [benefit 2] with quick demo
(7) Feature 3 — [benefit 3] with quick demo
(8) How it works — 3-step setup flow
(9) Social proof — "[customer quote or key metric]"
(10) Pricing — "Free to start" or [pricing info]
(11) CTA — "Try it free at [url]"
(12) Logo close — [App Name] logo + tagline

Style: dark background, clean typography, [brand color] accents.
Audience: [target audience].
Tone: confident and modern.

Then ask the user to fill in the brackets — or help them fill them in based on what you know about their product.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Convert changelogs, release notes, and version updates into Ozor.ai video prompts. Use this skill whenever the user has a CHANGELOG.md, release notes, GitHub release, version bump summary, or any list of product changes and wants to turn them into a video. Trigger on phrases like 'video from my changelog', 'release notes video', 'make a video from this update', 'announce this release', 'version update video', 'what's new video', 'product update video', 'feature release video', or any request to transform a list of product changes into video format using Ozor.

日本語の概要は準備中です。原文の説明を表示しています。

Mintii-Labs/ozor-skills62026年5月28日 更新

Convert any document into a production-ready Ozor.ai video prompt. Use this skill whenever the user uploads a document (PDF, PowerPoint, Google Doc, Markdown, text file, or URL) and wants to turn it into a video. Also trigger when the user mentions 'turn this doc into a video', 'make a video from this PDF', 'video from my pitch deck', 'convert this presentation to video', 'video from this blog post', 'video from these release notes', 'create a video from this document', 'turn this into an explainer', or any request to transform written content into video format using Ozor. This skill reads the document, extracts the core message, structures it into scenes, and outputs a complete prompt the user can paste directly into Ozor.ai.

日本語の概要は準備中です。原文の説明を表示しています。

Mintii-Labs/ozor-skills62026年5月28日 更新

Turn a real document (PDF, PPTX, DOCX, Keynote export, slide deck, proposal, whitepaper, report) into a finished AI-generated video using the Ozor MCP. Use this skill whenever the user attaches, uploads, references, or points to a document file and wants a video from it — e.g. 'make a video from this pitch deck', 'turn this PDF into a video', 'video from my proposal.docx', 'generate a video from this PowerPoint', 'create a video from this report', 'this whitepaper → video'. This skill runs the document-to-video pipeline: analyze_document → present the plan to the user → update_plan if needed → generate_from_plan → export_video → wait_for_export → get_embed_code. It always uses the plan-based flow so slide visuals are preserved. Do NOT use this skill for plain-text creative briefs (use ozor-generate) or for URLs/landing pages (use ozor-url-to-video).

日本語の概要は準備中です。原文の説明を表示しています。

Mintii-Labs/ozor-skills62026年5月28日 更新

Generate an AI video end-to-end on Ozor.ai from a short text brief. Use this skill whenever the user wants to actually create a video (not just write a prompt) from a creative description, idea, or short brief — e.g. 'make me a video about X', 'generate a launch video for Y', 'create an explainer for Z', 'render a video', 'produce a 30s ad about ...', 'spin up a quick video for our new feature'. This skill runs the full Ozor MCP pipeline: generate_video → wait_for_job → export_video → wait_for_export → get_embed_code, and returns the shareUrl, editorUrl, downloadUrl, and a ready-to-paste <iframe> embed. Do NOT use this skill when the input is a document/PDF/PPTX/deck/URL — use ozor-document-video or ozor-url-to-video instead.

日本語の概要は準備中です。原文の説明を表示しています。

Mintii-Labs/ozor-skills62026年5月28日 更新

Convert any landing page or website into an Ozor.ai video prompt. Use this skill whenever the user provides a URL, landing page content, or website copy and wants to turn it into a video. Trigger on phrases like 'make a video from my website', 'video from this landing page', 'turn my homepage into a video', 'video from this URL', 'product page to video', 'website to video', 'marketing video from my site', 'convert this page to video', or any request to transform web content into video format using Ozor.

日本語の概要は準備中です。原文の説明を表示しています。

Mintii-Labs/ozor-skills62026年5月28日 更新

Analyze and improve existing Ozor.ai video prompts for better output quality. Use this skill whenever the user has an Ozor prompt that produced mediocre results, wants to improve a video prompt, needs help debugging why a video didn't turn out well, or wants expert feedback on their prompt before running it. Trigger on phrases like 'improve this prompt', 'optimize my Ozor prompt', 'why did my video look bad', 'fix this prompt', 'make this prompt better', 'review my Ozor prompt', 'the video didn't turn out right', 'prompt feedback', 'better results from Ozor', or any request to refine, debug, or enhance an existing Ozor video prompt.

日本語の概要は準備中です。原文の説明を表示しています。

Mintii-Labs/ozor-skills62026年5月28日 更新

Mintii-Labs のスキルをすべて見る

このスキルの問題を報告する