How do I install the Turing Tavily Web Search skill?

Run npx skillmds@latest add dvcrn/turing-tavily-web-search in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Turing Tavily Web Search safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Turing Tavily Web Search?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Turing Tavily Web Search free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Turing Tavily Web Search?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Turing Tavily Web Search by dvcrn — Agent Skill

Name: Turing Tavily Web Search
Rating: 4.5 (4 reviews)
Author: dvcrn

Turing Tavily Web Search

Search the web via the Turing Tavily proxy. Use when the user asks to search the web, look up real-time information, research current events, or needs up-to-date data not in training data. Run the bundled script via bash — do NOT construct HTTP requests manually.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

Tavily Web Search

Search the web via the Turing Tavily proxy API.

Usage

python3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '<JSON>'

Request Parameters

Param	Type	Required	Default	Description
`query`	`str` or `list[str]`	yes	—	Search query, or list of queries for batch search
`max_results`	`int`	no	`10`	Max results per query (1–20)
`max_tokens_per_page`	`int`	no	`1024`	Max tokens extracted per result page
`search_domain_filter`	`list[str]`	no	—	Restrict results to specific domains (max 20)

Response Fields

Field	Type	Description
`answer`	`str`	AI-generated summary (if available)
`results[].title`	`str`	Page title
`results[].url`	`str`	Page URL
`results[].content`	`str`	Content snippet
`results[].publishedDate`	`str`	Publication date (if available)

Examples

# Basic search
python3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '{"query": "latest AI news"}'

# Limit results
python3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '{"query": "latest AI news", "max_results": 5}'

# Domain filter
python3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '{"query": "transformer architecture", "search_domain_filter": ["arxiv.org", "github.com"]}'

Configuration

Set in openclaw.json under skills.entries.turing-skills.env:

Variable	Required	Description
`TURING_API_KEY`	yes	Bearer token (`sk-...`)
`TURING_CLIENT`	yes	Client identifier
`TURING_ENVIRONMENT`	yes	Environment name
`TURING_API_BASE`	no	API base URL (default: `https://live-turing.cn.llm.tcljd.com`)

---name: turing-tavily-web-searchdescription: Search the web via the Turing Tavily proxy. Use when the user asks to search the web, look up real-time information, research current events, or needs up-to-date data not in training data. Run the bundled script via bash — do NOT construct HTTP requests manually.---# Tavily Web SearchSearch the web via the Turing Tavily proxy API.## Usage```bashpython3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '<JSON>'```## Request Parameters| Param | Type | Required | Default | Description ||---|---|---|---|---|| `query` | `str` or `list[str]` | yes | — | Search query, or list of queries for batch search || `max_results` | `int` | no | `10` | Max results per query (1–20) || `max_tokens_per_page` | `int` | no | `1024` | Max tokens extracted per result page || `search_domain_filter` | `list[str]` | no | — | Restrict results to specific domains (max 20) |## Response Fields| Field | Type | Description ||---|---|---|| `answer` | `str` | AI-generated summary (if available) || `results[].title` | `str` | Page title || `results[].url` | `str` | Page URL || `results[].content` | `str` | Content snippet || `results[].publishedDate` | `str` | Publication date (if available) |## Examples```bash# Basic searchpython3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '{"query": "latest AI news"}'# Limit resultspython3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '{"query": "latest AI news", "max_results": 5}'# Domain filterpython3 ~/.openclaw/skills/turing-tavily-web-search/scripts.py '{"query": "transformer architecture", "search_domain_filter": ["arxiv.org", "github.com"]}'```## ConfigurationSet in `openclaw.json` under `skills.entries.turing-skills.env`:| Variable | Required | Description ||---|---|---|| `TURING_API_KEY` | yes | Bearer token (`sk-...`) || `TURING_CLIENT` | yes | Client identifier || `TURING_ENVIRONMENT` | yes | Environment name || `TURING_API_BASE` | no | API base URL (default: `https://live-turing.cn.llm.tcljd.com`) |

Frequently asked questions