web-search

Recherche web et extraction de contenu avec Tavily et Exa via l'interface en ligne de commande inference.sh. Applications : Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capacités : recherche assistée par IA, extraction de contenu, réponses directes, recherche documentaire. Utilisation pour : recherche, pipelines RAG, vérification des faits, agrégation de contenu, agents. Déclencheurs : recherche web, tavily, exa, api de recherche, extraction de contenu, recherche, recherche internet, recherche IA, assistant de recherche, scraping web, rag, alternative à 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

Plus de skills de halt-catch-fire

ai-image-generation
halt-catch-fire
Générez des images IA avec GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve et plus de 50 modèles via l'interface CLI inference.sh. Modèles : GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capacités : texte vers image, image vers image, inpainting, LoRA, édition d'image, upscaling, rendu de texte. Utilisation pour : art IA, maquettes de produits, concept art, graphiques pour réseaux sociaux, visuels marketing, illustrations. Déclencheurs : flux, génération d'image, image IA, texte vers...
creativemediaimage
ai-video-generation
halt-catch-fire
We need to translate the given text from English to French. The text describes an AI video generation skill. We must preserve the name "ai-video-generation" but it's not in the text, so we ignore. Preserve product names, protocol names, URLs, numbers, technical terms. So "Google Veo", "Seedance 2.0", "HappyHorse", "Wan", "Grok", "inference.sh CLI", "Veo 3.1", "Veo 3", "Seedance 2.0", "HappyHorse 1.0", "Wan 2.5", "Grok Imagine Video", "OmniHuman", "Fabric", "HunyuanVideo", "text-to-video", "image-to-video", "reference-to-video", "video editing", "lipsync", "avatar animation", "video upscaling", "foley sound", "social media videos", "marketing content", "explainer videos", "product demos", "AI avatars",
creativevideomedia
twitter-automation
halt-catch-fire
Automatisez Twitter/X avec publication, engagement et gestion des utilisateurs via l'interface CLI inference.sh. Applications : x/post-tweet, x/post-create (avec média), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Capacités : publier des tweets, planifier du contenu, aimer des publications, retweeter, envoyer des messages directs, suivre des utilisateurs, obtenir des profils. Utilisation pour : automatisation des réseaux sociaux, planification de contenu, bots d'engagement, croissance d'audience, API X. Déclencheurs : 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 French, preserving the name "ai-avatar-video" and other technical terms. The text describes creating AI avatar and talking head videos via inference.sh CLI. It recommends P-Video-Avatar, and lists other options: OmniHuman, Fabric, PixVerse. Audio options: Inworld TTS-2, ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars,... We must not include the name "ai-avatar-video" unless it appears in the source text. It does not appear in the source text, so we omit it. We translate the rest naturally. Keep product names, protocol names, URLs, numbers, technical terms as is. So "inference.sh CLI" stays, "P-Video-Avatar", "OmniHuman", "F
videocreativemedia
agent-browser
halt-catch-fire
Automatisation de navigateur pour agents IA via inference.sh. Naviguer sur des pages web, interagir avec des éléments en utilisant les références @e, prendre des captures d'écran, enregistrer des vidéos. Capacités : scraping web, remplissage de formulaires, clics, saisie, glisser-déposer, téléchargement de fichiers, exécution JavaScript. Utilisation pour : automatisation web, extraction de données, tests, navigation agent, recherche. Déclencheurs : navigateur, automatisation web, scraping, navigation, clic, remplissage de formulaire, capture d'écran, navigation web, playwright, navigateur headless, agent web, surf internet, enregistrement vidéo
browser-automationweb-scrapingtesting
infsh-cli
halt-catch-fire
We need to translate the given text from English to French, 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, so we don't include it. The source text has "inference.sh CLI" - that should be preserved as is? The instruction says preserve product names, so "inference.sh CLI" should stay. Also "FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter" are product names, keep them. "Twitter" is a product name. "AI" is a term, keep as is or translate? Usually "IA" in French, but the instruction says preserve technical terms? "AI" is a common acronym, often kept as is. But in French, "IA" is used. However, the instruction says "preserve product names
developmentapicreative
landing-page-design
halt-catch-fire
We need to translate the given text from English to French. The text is a description of an agent skill for landing page design. We must preserve the name "landing-page-design" but it's not in the text, so we don't include it. We translate only the text inside <text>. No extra labels. Keep technical terms like "CTA", "F-pattern", "SaaS", etc. as is or translate if appropriate? The instruction says preserve technical terms, so "CTA" stays, "F-pattern" might be kept or translated? Usually "F-pattern" is a known term, but in French it might be "motif en F" or keep as is. Since it's a technical term, I'll keep "F-pattern" as is. "above-the-fold" is a term, often kept as "above-the-fold" or "au-dessus de la ligne de flottaison". I'll keep as "above-the-fold" for consistency. "social proof" -> "preuve sociale". "mobile design" -> "conception mobile
product-photography
halt-catch-fire
We need to translate the given text from English to French. The text describes an AI product photography skill. We must preserve the name "product-photography" but it's not in the text, so we don't include it. We translate only the text inside <text>. No extra labels. Keep technical terms like "packshot", "hero shot", "lifestyle shots", "e-commerce", "Amazon" as is or with appropriate French translation? The instruction says preserve product names, protocol names, URLs, numbers, technical terms. "Amazon" is a product name, keep as is. "packshot" is a technical term, often kept in English in French contexts, but could be translated? The instruction says preserve technical terms, so keep "packshot". "hero shot" is also technical, keep. "lifestyle shots" - "lifestyle" is often used in French, but "shots" might be translated as "photos" or kept. I'll keep "lifestyle shots" as is. "studio lighting" - "éclairage studio".
creativeecommerceimage