product-hunt-launch

We need to translate the given text from English to Vietnamese. The text is about Product Hunt launch optimization. We must preserve the name "product-hunt-launch" but it's not in the text, so we ignore. Also preserve URLs, numbers, technical terms. The text includes terms like "Product Hunt", "taglines", "gallery images", "maker comments", "launch day tactics", etc. Translate naturally. The triggers list: product hunt, ph launch, etc. Keep them as is? The instruction says preserve product names, protocol names, URLs, numbers, technical terms. "Product Hunt" is a product name, so keep as "Product Hunt". "PH" might be abbreviation, but likely keep as "PH" or translate? Probably keep as "PH" since it's a known abbreviation. But careful: "ph launch" might be "PH launch" - keep as "PH launch". Similarly "ph optimization" -> "PH optimization". The rest: "taglines" -> "khẩu hiệu" or "tagline"? Since it's

npx skills add https://github.com/halt-catch-fire/skills --skill product-hunt-launch

Install the belt CLI skill: npx skills add belt-sh/cli

Product Hunt Launch

Optimize your Product Hunt launch with research and visuals via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Generate gallery hero image
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean product showcase, modern SaaS dashboard interface on laptop screen, floating UI elements around it, soft gradient background from blue to purple, professional marketing hero shot, minimal clean design",
  "width": 1248,
  "height": 832
}'

# Research competitor launches
belt app run tavily/search-assistant --input '{
  "query": "Product Hunt top launches this week SaaS tools"
}'

Listing Specifications

ElementSpecNotes
Product nameKeep it short, memorable
Tagline60 character limitNo period at end
DescriptionFirst 260 chars show in previewFull description can be longer
Gallery imagesUp to 8 images1270 x 760 px recommended
TopicsMax 3Pick the most specific ones
MakersTag all team membersThey can engage in comments
LinkProduct URLWhere upvoters go

Gallery Images

The First Image Is Everything

The first gallery image shows in the feed, email digest, and social shares. It IS your first impression.

PositionContentGoal
1 (Hero)Product in action, core value visibleStop the scroll, communicate what it does
2Key feature demonstrationShow the "aha moment"
3Before/after or problem/solutionShow the transformation
4Social proof or metricsBuild credibility
5Technical differentiator or integrationsFor evaluators

Dimensions

  • Recommended: 1270 x 760 px (16:9 ish)
  • Minimum: 600px wide
  • Supports GIF for animated demos

Generating Gallery Images

# Image 1: Hero product shot
belt app run falai/flux-dev-lora --input '{
  "prompt": "modern SaaS product showcase, clean dashboard interface floating above gradient background, UI showing analytics charts and metrics, professional product marketing style, soft shadows, blue and white color scheme, wide format",
  "width": 1248,
  "height": 832
}'

# Image 2: Feature demo
belt app run falai/flux-dev-lora --input '{
  "prompt": "product feature showcase, split screen showing drag-and-drop interface on left and generated output on right, clean UI design, modern SaaS aesthetic, subtle grid background, professional marketing",
  "width": 1248,
  "height": 832
}'

# Image 3: Before/after
belt app run infsh/stitch-images --input '{
  "images": ["before-state.png", "after-state.png"],
  "direction": "horizontal"
}'

# Image 4: Social proof / metrics
belt app run falai/flux-dev-lora --input '{
  "prompt": "clean infographic style image showing upward growth metrics, large numbers and charts on dark background, professional data visualization, startup metrics dashboard style, modern minimal design",
  "width": 1248,
  "height": 832
}'

Tagline

60 characters. No period. Must communicate what the product does AND why someone should care.

Formulas That Work

FormulaExample
[Action] for [audience]"AI writing assistant for developers"
[Result] without [pain]"Beautiful docs without the design skills"
[Tool] that [benefit]"Analytics that explain themselves"
[Adjective] [category]"Instant customer feedback surveys"
The [category] for [niche]"The Figma for data visualization"

Examples

❌ "The best project management tool ever created" (superlative, 52 chars)
❌ "We help you manage projects better." (vague, has period, 37 chars)
❌ "AI-powered machine learning project management SaaS" (buzzword soup)

✅ "Ship docs in minutes, not days" (31 chars)
✅ "AI turns your data into stories" (32 chars)
✅ "The open-source Calendly alternative" (37 chars)

Timing

When to Launch

FactorRecommendation
DayTuesday, Wednesday, or Thursday (highest traffic)
Time12:01 AM PT (Pacific Time) — start of the PH day
AvoidWeekends, holidays, major Apple/Google events
DurationPH day = midnight PT to midnight PT

Why 12:01 AM PT

  • Maximum time in the running for daily top spot
  • Accumulate upvotes throughout the full day
  • Morning email digest (US time) includes your product
  • Allows engagement across all US time zones

Maker Comment

Post within 5 minutes of going live. This is your pitch.

Structure

Hey Product Hunt! 👋

[1 sentence: what it is]

[2-3 sentences: why you built it / the problem you noticed]

[1-2 sentences: how it works / key differentiator]

[1 sentence: what's next / what you're looking for]

Would love to hear your thoughts — happy to answer any questions!

Example

Hey Product Hunt!

DataFlow turns raw SQL queries into visual dashboards in seconds.

As a data engineer, I was frustrated spending more time formatting
reports than actually analyzing data. Every BI tool I tried required
a PhD in their configuration. So I built DataFlow — paste your SQL,
get a dashboard.

It auto-detects chart types, handles large datasets, and exports
to PDF/PNG with one click.

We're offering 50% off the first year for PH users. Would love
your feedback — what reporting pain points do you have?

Launch Day Playbook

Before Launch (1-2 weeks)

  • Gallery images finalized (5 recommended)
  • Tagline tested with 5+ people (do they understand what it does?)
  • Maker comment drafted and proofread
  • Landing page with PH badge ready
  • Early supporter list ready (people who want to check it out)
  • Social media announcement posts drafted

Launch Day Timeline

Time (PT)Action
12:01 AMProduct goes live, post maker comment immediately
12:15 AMShare on personal social media
6:00 AMFirst engagement check — reply to all comments
9:00 AMShare in relevant communities (naturally, not spammy)
12:00 PMMid-day check — reply to all new comments
3:00 PMShare any early traction or interesting feedback
6:00 PMEvening engagement — reply to remaining comments
11:59 PMDay ends — results are final

Engagement Rules

  • Reply to every comment — makers who engage get more visibility
  • Ask questions back — creates conversation threads
  • Be genuine — don't use canned responses
  • Never ask for upvotes — against PH terms of service
  • Share the link naturally — "Check it out at [url]" not "Please upvote"

Research for Preparation

# Study similar product launches
belt app run tavily/search-assistant --input '{
  "query": "Product Hunt top launches analytics tools best practices"
}'

# Competitive landscape
belt app run exa/search --input '{
  "query": "Product Hunt analytics dashboard tools launched 2024 2025"
}'

# Community sentiment
belt app run tavily/search-assistant --input '{
  "query": "Product Hunt launch tips what works 2024 maker advice"
}'

Post-Launch

WhenAction
Day 1-3Reply to all remaining comments, thank supporters
Week 1Publish a "lessons learned" blog post / Twitter thread
Week 2Follow up with interested users from comments
Month 1Check if you're eligible for "Product of the Week/Month"

Common Mistakes

MistakeProblemFix
Launching on Friday/weekendLow traffic, wasted launchTue-Thu only
Launching at noonHalf the day already gone12:01 AM PT
No maker commentLooks abandonedPost within 5 minutes
Asking for upvotesAgainst TOS, can get flaggedShare naturally, let product speak
Generic gallery imagesDoesn't show the productShow real UI, real features
Not replying to commentsLow engagement signalReply to every single comment
Too many topicsDilutes discoverabilityMax 3, pick the most specific
Tagline with buzzwordsNobody knows what you doClear, specific, benefit-focused

Related Skills

npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@web-search
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: belt app list

Thêm skills từ halt-catch-fire

ai-image-generation
halt-catch-fire
Tạo hình ảnh AI với GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve và hơn 50 mô hình qua CLI inference.sh. Mô hình: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Khả năng: văn bản thành hình ảnh, hình ảnh thành hình ảnh, inpainting, LoRA, chỉnh sửa hình ảnh, nâng cấp độ phân giải, hiển thị văn bản. Sử dụng cho: nghệ thuật AI, mô phỏng sản phẩm, nghệ thuật ý tưởng, đồ họa mạng xã hội, hình ảnh tiếp thị, minh họa. Kích hoạt: flux, tạo hình ảnh, hình
creativemediaimage
ai-video-generation
halt-catch-fire
Tạo video AI với Google Veo, Seedance 2.0, HappyHorse, Wan, Grok và hơn 40 mô hình qua CLI inference.sh. Các mô hình: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Khả năng: văn bản thành video, hình ảnh thành video, tham chiếu thành video, chỉnh sửa video, đồng bộ môi, hoạt ảnh đại diện, nâng cấp video, âm thanh foley. Sử dụng cho: video mạng xã hội, nội dung tiếp thị, video giải thích, demo sản phẩm, đại diện AI. Kích hoạt: tạo video, video AI,...
creativevideomedia
twitter-automation
halt-catch-fire
Tự động hóa Twitter/X với tính năng đăng bài, tương tác và quản lý người dùng qua CLI inference.sh. Ứng dụng: x/post-tweet, x/post-create (có media), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Khả năng: đăng tweet, lên lịch nội dung, thích bài, retweet, gửi DM, theo dõi người dùng, lấy hồ sơ. Sử dụng cho: tự động hóa mạng xã hội, lên lịch nội dung, bot tương tác, tăng trưởng khán giả, X API. Kích hoạt: twitter api, x api, tự động hóa tweet, đăng lên twitter, twitter bot, tự động hóa mạng xã hội, x...
marketingapicommunication
ai-avatar-video
halt-catch-fire
Tạo video AI avatar và video người nói qua CLI inference.sh. Đề xuất: P-Video-Avatar (nhanh nhất, rẻ nhất, TTS tích hợp). Ngoài ra: OmniHuman, Fabric, PixVerse. Âm thanh: Inworld TTS-2 (hơn 100 ngôn ngữ, điều chỉnh cảm xúc cho nhân vật), ElevenLabs, Kokoro. Khả năng: avatar điều khiển bằng âm thanh, văn bản thành avatar, video đồng bộ môi, tạo người nói, người dẫn ảo, nội dung UGC. Sử dụng cho: người dẫn AI, video giải thích, người có ảnh hưởng ảo, lồng tiếng, video tiếp thị, quảng cáo UGC, avatar trò chơi,...
videocreativemedia
agent-browser
halt-catch-fire
Tự động hóa trình duyệt cho các tác nhân AI qua inference.sh. Điều hướng trang web, tương tác với các phần tử bằng @e refs, chụp ảnh màn hình, ghi video. Khả năng: thu thập dữ liệu web, điền biểu mẫu, nhấp chuột, gõ chữ, kéo-thả, tải tệp lên, thực thi JavaScript. Sử dụng cho: tự động hóa web, trích xuất dữ liệu, kiểm thử, duyệt web tác nhân, nghiên cứu. Kích hoạt: trình duyệt, tự động hóa web, thu thập, điều hướng, nhấp chuột, điền biểu mẫu, chụp ảnh màn hình, duyệt web, playwright, trình duyệt không đầu, tác nhân web, lướ
browser-automationweb-scrapingtesting
web-search
halt-catch-fire
Tìm kiếm web và trích xuất nội dung với Tavily và Exa thông qua CLI inference.sh. Ứng dụng: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Khả năng: tìm kiếm hỗ trợ AI, trích xuất nội dung, trả lời trực tiếp, nghiên cứu. Sử dụng cho: nghiên cứu, pipeline RAG, kiểm tra thông tin, tổng hợp nội dung, tác nhân. Kích hoạt: tìm kiếm web, tavily, exa, search api, trích xuất nội dung, nghiên cứu, tìm kiếm internet, tìm kiếm AI, trợ lý tìm kiếm, thu thập dữ liệu web, rag, thay thế perplexity
researchweb-scrapingapi
infsh-cli
halt-catch-fire
We need to translate the given text from English to Vietnamese, preserving the name "infsh-cli" and other technical terms, product names, protocol names, URLs, numbers, etc. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "infsh-cli" appears in the source? Actually the source text does not contain "infsh-cli" explicitly; the name to preserve is given as "infsh-cli" but it's not in the text. The instruction says "Do not include the name unless it appears in the source text." So we should not add it. The text inside <text> is: "Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos
developmentapicreative
landing-page-design
halt-catch-fire
Tối ưu hóa chuyển đổi trang đích với quy tắc bố cục, thiết kế phần hero và tâm lý học CTA. Bao gồm công thức above-the-fold, vị trí đặt bằng chứng xã hội, thiết kế di động và cách đọc theo mô hình F. Sử dụng cho: trang đích khởi nghiệp, trang sản phẩm, tiếp thị SaaS, tối ưu hóa chuyển đổi. Kích hoạt: trang đích, phần hero, above the fold, tối ưu hóa chuyển đổi, thiết kế trang đích, nút CTA, hình ảnh hero, bố cục trang đích, trang đích SaaS, thiết kế trang sản phẩm, tỷ lệ chuyển đổi, trang đích...