web-search

Pencarian web dan ekstraksi konten dengan Tavily dan Exa melalui CLI inference.sh. Aplikasi: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Kemampuan: pencarian berbasis AI, ekstraksi konten, jawaban langsung, riset. Gunakan untuk: riset, pipeline RAG, pemeriksaan fakta, agregasi konten, agen. Pemicu: pencarian web, tavily, exa, search api, ekstraksi konten, riset, pencarian internet, pencarian AI, asisten pencarian, web scraping, rag, alternatif perplexity

npx skills add https://github.com/halt-catch-fire/skills --skill web-search

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

Web Search & Extraction

Search the web and extract content via inference.sh CLI.

Web Search & Extraction

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Search the web
belt app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}'

Available Apps

Tavily

AppApp IDDescription
Search Assistanttavily/search-assistantAI-powered search with answers
Extracttavily/extractExtract content from URLs

Exa

AppApp IDDescription
Searchexa/searchSmart web search with AI
Answerexa/answerDirect factual answers
Extractexa/extractExtract and analyze web content

Examples

Tavily Search

belt app run tavily/search-assistant --input '{
  "query": "What are the best practices for building AI agents?"
}'

Returns AI-generated answers with sources and images.

Tavily Extract

belt app run tavily/extract --input '{
  "urls": ["https://example.com/article1", "https://example.com/article2"]
}'

Extracts clean text and images from multiple URLs.

Exa Search

belt app run exa/search --input '{
  "query": "machine learning frameworks comparison"
}'

Returns highly relevant links with context.

Exa Answer

belt app run exa/answer --input '{
  "question": "What is the population of Tokyo?"
}'

Returns direct factual answers.

Exa Extract

belt app run exa/extract --input '{
  "url": "https://example.com/research-paper"
}'

Extracts and analyzes web page content.

Workflow: Research + LLM

# 1. Search for information
belt app run tavily/search-assistant --input '{
  "query": "latest developments in quantum computing"
}' > search_results.json

# 2. Analyze with Claude
belt app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Based on this research, summarize the key trends: <search-results>"
}'

Workflow: Extract + Summarize

# 1. Extract content from URL
belt app run tavily/extract --input '{
  "urls": ["https://example.com/long-article"]
}' > content.json

# 2. Summarize with LLM
belt app run openrouter/claude-haiku-45 --input '{
  "prompt": "Summarize this article in 3 bullet points: <content>"
}'

Use Cases

  • Research: Gather information on any topic
  • RAG: Retrieval-augmented generation
  • Fact-checking: Verify claims with sources
  • Content aggregation: Collect data from multiple sources
  • Agents: Build research-capable AI agents

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# LLM models (combine with search for RAG)
npx skills add inference-sh/skills@llm-models

# Image generation
npx skills add inference-sh/skills@ai-image-generation

Browse all apps: belt app list

Documentation

Lebih banyak skill dari halt-catch-fire

ai-image-generation
halt-catch-fire
We need to translate the given text from English to Bahasa Indonesia. The text describes an agent skill for AI image generation. We must preserve the name "ai-image-generation" but it's not in the text, so we don't include it. Also preserve product names, protocol names, URLs, numbers, technical terms. No extra commentary. Just translate the text inside <text>. The text: "Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to...
creativemediaimage
ai-video-generation
halt-catch-fire
Hasilkan video AI dengan Google Veo, Seedance 2.0, HappyHorse, Wan, Grok dan 40+ model melalui CLI inference.sh. Model: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Kemampuan: teks-ke-video, gambar-ke-video, referensi-ke-video, pengeditan video, lipsync, animasi avatar, peningkatan resolusi video, suara foley. Gunakan untuk: video media sosial, konten pemasaran, video penjelasan, demo produk, avatar AI. Pemicu: pembuatan video, video AI,...
creativevideomedia
twitter-automation
halt-catch-fire
Otomatiskan Twitter/X dengan posting, interaksi, dan manajemen pengguna melalui CLI inference.sh. Aplikasi: x/post-tweet, x/post-create (dengan media), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Kemampuan: memposting tweet, menjadwalkan konten, menyukai postingan, me-retweet, mengirim DM, mengikuti pengguna, mendapatkan profil. Gunakan untuk: otomatisasi media sosial, penjadwalan konten, bot interaksi, pertumbuhan audiens, API X. Pemicu: twitter api, x api, tweet automation, post to twitter, twitter bot, social media automation, x...
marketingapicommunication
ai-avatar-video
halt-catch-fire
We need to translate the given text from English to Bahasa Indonesia. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. So names like "P-Video-Avatar", "OmniHuman", "Fabric", "PixVerse", "Inworld TTS-2", "ElevenLabs", "Kokoro", "CLI", "TTS", "UGC" should remain unchanged. Also "inference.sh" is a URL-like name, preserve. The text inside <text> is a description. We translate the rest naturally. The text: "Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC
videocreativemedia
agent-browser
halt-catch-fire
Otomatisasi peramban untuk agen AI melalui inference.sh. Navigasi halaman web, berinteraksi dengan elemen menggunakan referensi @e, ambil tangkapan layar, rekam video. Kemampuan: pengikisan web, pengisian formulir, klik, mengetik, seret-lepas, unggah berkas, eksekusi JavaScript. Gunakan untuk: otomatisasi web, ekstraksi data, pengujian, penjelajahan agen, riset. Pemicu: peramban, otomatisasi web, kikis, navigasi, klik, isi formulir, tangkapan layar, jelajahi web, playwright, peramban tanpa kepala, agen web, jelajahi internet, rekam video
browser-automationweb-scrapingtesting
infsh-cli
halt-catch-fire
We need to translate the given text from English to Bahasa Indonesia, preserving the name "infsh-cli" and other technical terms, product names, protocol names, URLs, numbers, etc. The instruction says: "Do not include the name unless it appears in the source text." The name "infsh-cli" is not in the source text? Actually, the source text does not contain "infsh-cli" explicitly. The directory item type is "agent skill" and the name to preserve is "infsh-cli", but the text inside <text> does not include that name. So we should not add it. We just translate the text inside <text>. Also, we must not add labels like "description" or "skill name". Just the translation. The text: "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, Open
developmentapicreative
landing-page-design
halt-catch-fire
We need to translate the given text from English to Bahasa Indonesia. The instruction says to preserve product names, protocol names, URLs, numbers, technical terms. The name "landing-page-design" is to be preserved but not included unless it appears in source text. It does not appear in the <text> block. So we just translate the text. The text: "Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page..." Translate carefully. Technical terms like "CTA", "above-the-fold", "F-pattern", "SaaS" should be preserved as is or translated? The instruction says preserve technical terms. Usually "CTA" is kept as
product-photography
halt-catch-fire
Fotografi produk AI dengan pencahayaan studio, foto gaya hidup, dan konvensi packshot. Mencakup sudut, latar belakang, jenis bayangan, hero shot, dan persyaratan gambar e-commerce. Gunakan untuk: foto produk, gambar e-commerce, daftar Amazon, packshot, fotografi gaya hidup. Pemicu: fotografi produk, foto produk, packshot, fotografi e-commerce, bidikan produk, gambar produk, fotografi studio, produk gaya hidup, foto produk Amazon, gambar daftar produk, hero shot, mockup produk,...
creativeecommerceimage