← Back to Skills Marketplace
🔌

Tavily

by OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
39
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install oo-tavily
Description
Tavily (tavily.com). Use this skill for ANY Tavily request — searching and reading data. Whenever a task involves Tavily, use this skill instead of calling t...
README (SKILL.md)

Tavily

Operate Tavily through your OOMOL-connected account. This skill calls the tavily connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: AI, Data & Analytics. Exposes 5 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Tavily. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "tavily" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "tavily" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

  • crawl — Crawl a website and extract content from discovered pages with Tavily.
  • extract — Extract structured page content from one or more URLs with Tavily.
  • get_usage — Get API key and account usage details from Tavily.
  • map — Discover URLs from a website with Tavily Map.
  • search — Execute a Tavily Search query and return ranked source results.

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Tavily state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — Tavily is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=tavily
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

Usage Guidance
Install this only if you want Tavily searches routed through AISA and are comfortable providing an AISA_API_KEY. Avoid sending sensitive private queries through it unless you trust the provider, and prefer a narrower/local search path when the user did not explicitly need Tavily-style filtering.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The stated purpose is filtered Tavily web search through AISA, and the described capability is limited to search-style operations using a bundled Python client.
Instruction Scope
The broad Tavily activation wording could cause unnecessary use when Tavily is only mentioned, but this is a routing concern rather than evidence of hidden or unrelated behavior.
Install Mechanism
The artifact discloses a required AISA_API_KEY and python3 runtime; no automatic installer, background setup, or hidden dependency execution is shown.
Credentials
An API key and external network requests are expected for this connector, but user search queries may be sent to AISA/Tavily and should be treated as third-party data sharing.
Persistence & Privilege
No artifact-backed evidence shows persistence, privilege escalation, local credential scraping, broad file indexing, destructive actions, or public posting authority.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install oo-tavily
  3. After installation, invoke the skill by name or use /oo-tavily
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Provides an OOMOL skill for operating Tavily through the `oo` CLI without exposing raw Tavily credentials. - Adds Tavily-powered web search with ranked source results for research and retrieval workflows. - Supports extracting structured content from one or more URLs. - Supports website crawling and URL discovery through Tavily Crawl and Map actions. - Includes account and API usage lookup via `get_usage`. - Documents schema-first execution patterns for all Tavily connector actions.
Metadata
Slug oo-tavily
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Tavily?

Tavily (tavily.com). Use this skill for ANY Tavily request — searching and reading data. Whenever a task involves Tavily, use this skill instead of calling t... It is an AI Agent Skill for Claude Code / OpenClaw, with 39 downloads so far.

How do I install Tavily?

Run "/install oo-tavily" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Tavily free?

Yes, Tavily is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Tavily support?

Tavily is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Tavily?

It is built and maintained by OOMOL (@oomol); the current version is v1.0.0.

💬 Comments