Search the Web with Tavily and Exa
Research tasks need current sources and clean page content. This skill uses inference.sh with Tavily and Exa to search, extract, and summarize web material.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "web-search" from https://skillstore.io/skills/inference-sh-web-search.md and its manifest at https://skillstore.io/api/skills/inference-sh-web-search/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "web-search". Search for recent AI safety regulation sources.
Expected outcome:
A concise answer with relevant links, source titles, and short context for each result.
Using "web-search". Extract two public articles for a project brief.
Expected outcome:
Clean article text, image references, and source details ready for summarization.
Using "web-search". Compare search results for a technical topic.
Expected outcome:
A ranked source list with evidence notes, disagreements, and recommended follow-up reading.
Most static hits are Markdown backticks around examples and app identifiers, so they are false positives. The audit confirms the line 20 pipe-to-shell installer and its installer URL as real risks that must be removed or replaced.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/inference-sh-web-search/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/inference-sh-web-search?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/inference-sh-web-search?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-web-search/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/inference-sh-web-search.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>inference-sh. (2026). web-search security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-web-search/audits/4@techreport{inference-sh-inference-sh-web-search-2026,
author = {inference-sh},
title = {web-search security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-web-search/audits/4},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "web-search security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-sh"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-web-search/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-web-search:audit:4"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
qu-skills-web-search
2026-08-21
inference-skills-web-search
2026-08-21
infsh-skills-web-search
2026-08-21
skillssh-web-search
2026-08-21
inferen-sh-web-search
2026-08-21
halt-catch-fire-web-search
2026-08-21
101-skills-web-search
2026-08-21
inference-sh-9-web-search
2026-08-21
cain96-web-search
2026-08-21
inference-sh-skills-web-search
2026-08-21
inference-sh-web-search
2026-08-21
Find current sources, links, and context for a topic before drafting a report.
Collect and extract public web pages for retrieval-augmented generation workflows.
Search for supporting or conflicting evidence before publishing a factual claim.
Search the web for recent sources about renewable energy storage. Return a short answer and source list.
Extract the main content from this public URL: [URL]. Summarize key points and include source metadata.
Use Tavily and Exa to research [topic]. Compare top sources, note disagreements, and cite the strongest evidence.
Search for [topic], extract the best pages, then prepare a RAG-ready brief with source quality notes.
Author
inference-shLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
5 downloads · 164 views
File structure
📄 SKILL.md
Build React Agent Interfaces
Agent interfaces require streaming chat, tool states, approvals, and runtime wiring. This skill helps add a React or Next.js agent component with proxy setup, scoped tools, and UI patterns.
Generate AI Images with inference.sh Models
Teams need quick access to many image models without memorizing each CLI command. This skill provides ready prompts for generation, editing, upscaling, and image stitching.
Remove Image Backgrounds with BiRefNet
Removing image backgrounds often requires manual editing or switching tools. This skill routes Claude, Codex, or Claude Code through belt to create transparent PNGs.
Generate AI Videos with CLI Models
AI video workflows require many model choices and exact CLI inputs. This skill maps common video goals to inference.sh commands, model families, and media preparation steps.
Create Social Media Assets with AI
Social teams need platform-ready visuals and copy quickly. This skill provides prompts and CLI workflows for videos, images, captions, hashtags, and repurposed posts.
Run Python Code in a Remote Sandbox
Teams need quick Python execution without preparing local environments. This skill runs code through inference.sh with libraries for analysis, scraping, media, and automation.
Search and Research the Web with Tavily
by sickn33
AI assistants often need current web context and clean source material. This skill guides Tavily search, extraction, crawling, and research tasks from Claude, Codex, and Claude Code.
Search the Web with Tavily
by CK991357
AI assistants often lack current information for news, prices, releases, and fast-moving topics. This skill guides Claude, Codex, and Claude Code to call Tavily Search with clear query parameters.
Search the Web with Firecrawl
by firecrawl
Current web research often needs more than short search snippets. This skill runs Firecrawl searches, saves structured results, and can extract full page content for review.
Search the Web Semantically with Exa
by sickn33
Keyword searches can miss conceptually relevant sources and related content. This skill guides Exa API searches for semantic discovery, category filtering, and structured research.
Simulate Nature-Style Reviewer Reports
by Yuan1z0825
Researchers often need an objective pre-submission critique before sending a manuscript. This skill turns supplied manuscript material into grounded Nature-style reviewer reports.
Research Complex Topics With Citations
by shubhamsaboo
Deep research is hard when sources disagree or lack context. This skill guides Claude, Codex, and Claude Code to synthesize sources, compare viewpoints, and produce cited research summaries.