$ loading_
Search the web, extract content, and organize research efficiently.
Overall, this appears to be low risk: the system flags it as an open-source, prompt-only skill with no declared secrets, local execution, or local file permissions. The main caution is that its described web search and extraction functionality may send queries or URLs to an external search/extraction service, while the materials do not clearly enumerate the actual endpoints.
Both the materials and system checks indicate no required secrets or environment variables. There is no request for API tokens, account passwords, or other highly sensitive credentials, so credential exposure appears minimal.
The description explicitly includes web search and URL content extraction, which typically send user queries, URLs, or filters to an external search/extraction service. However, the current materials do not specify concrete remote hosts, so network egress transparency is limited.
The system marks this as prompt-only, and the materials do not indicate spawning local processes, running scripts, invoking a shell, or requesting system-level execution privileges. No local code-execution surface is evident.
There is no declared access to local files, databases, clipboard, or other host resources. Based on the materials, it mainly operates on user-provided queries and URLs rather than local data stores, with no obvious sign of overbroad access.
The source is an open-source GitHub repository with very strong community adoption (about 377k stars), which are significant risk-reducing signals. Although the license is not stated and maintenance status is unknown, there is no evident red flag such as closed-source opaque exfiltration, spoofed provenance, or obvious supply-chain abuse.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "tavily" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/extensions/tavily/skills/tavily/SKILL.md 2. Save it as ~/.claude/skills/tavily/SKILL.md 3. Reload skills and tell me it's ready
Search for major competitors related to "AI search assistants" from the past year, extract their websites, core features, pricing, and recent updates, then organize them into a comparison table.
A structured competitor comparison table with source links and key information summaries.
Visit this article URL, extract the main body content, remove navigation, ads, and footer elements, and summarize 5 key points.
Cleaned main text and a concise list of key takeaways.
Conduct web research on "main risks of enterprise adoption of generative AI," compile common risks, examples, and mitigation advice from authoritative sources, and produce a research summary.
A source-backed research summary categorized by risk type with illustrative examples.
| Need | Tool | When |
|---|---|---|
| Quick web search | web_search | Basic queries, no special options needed |
| Search with advanced options | tavily_search | Need depth, topic, domain filters, time ranges, or AI answers |
| Extract content from URLs | tavily_extract | Have specific URLs, need their content |
Tavily powers this automatically when selected as the search provider. Use for straightforward queries where you don't need Tavily-specific options.
| Parameter | Description |
|---|---|
query | Search query string |
count | Number of results (1-20) |
Use when you need fine-grained control over search behavior.
| Parameter | Description |
|---|---|
query | Search query string (keep under 400 characters) |
search_depth | basic (default, balanced) or advanced (highest relevance, slower) |
topic | general (default), news (real-time updates), or finance |
max_results | Number of results, 1-20 (default: 5) |
include_answer | Include an AI-generated answer summary (default: false) |
time_range | Filter by recency: day, week, month, or year |
include_domains | Array of domains to restrict results to |
exclude_domains | Array of domains to exclude from results |
| Depth | Speed | Relevance | Best for |
|---|---|---|---|
basic | Faster | High | General-purpose queries (default) |
advanced | Slower | Highest | Precision, specific facts, detailed research |
include_domains to focus on trusted sources.time_range for recent information (news, current events).include_answer when you need a quick synthesized answer.Use when you have specific URLs and need their content. Handles JavaScript-rendered pages and returns clean markdown. Supports query-focused chunking for targeted extraction.
| Parameter | Description |
|---|---|
urls | Array of URLs to extract (1-20 per request) |
query | Rerank extracted chunks by relevance to this query |
extract_depth | basic (default, fast) or advanced (for JS-heavy pages, tables) |
chunks_per_source | Chunks per URL, 1-5 (requires query) |
include_images | Include image URLs in results (default: false) |
| Depth | When to use |
|---|---|
basic | Simple pages — try this first |
advanced | JS-rendered SPAs, dynamic content, tables, embedded content |
…
Create, search, and manage Bear notes on macOS via grizzly CLI.
Run or recover OpenClaw macOS signing, notarization, and release promotion.
Automatically add redacted agent transcripts to GitHub PRs or issues.
Search and analyze Slack archives, count threads, and support repo workflows.
Diagnose OpenClaw node pairing, auth, routing, and connection issues.
Summarize or transcribe URLs, videos, PDFs, and local files quickly.
Search, extract, map, and crawl live web data through the Tavily API.
Search the web, extract content, crawl sites, and support AI research.
Use Tavily via MCP for search, extraction, crawling, and web research workflows.
Search and scrape web content with automatic Tavily-to-Firecrawl fallback.
Access real-time web search, extraction, mapping, and crawling with optional PII protection.
Proxy Tavily search and extract APIs with key rotation and bearer auth.