一键导入
tavily
Install and use Tavily CLI (tvly) for web search/extract/crawl. Uses secret/env TAVILY_API_KEY.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Install and use Tavily CLI (tvly) for web search/extract/crawl. Uses secret/env TAVILY_API_KEY.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create, list, and configure OrgOps agents from native agents. Use when the user asks an agent to create agents, list agents, set up WRAPPED agents, OpenClaw wrappers, sidecars, or Cursor coding harnesses.
Manage package secrets (write, list keys, delete). Secrets are stored encrypted; agents can set values and list or delete keys but cannot read secret values. Use for API keys and tokens (e.g. OPENAI_API_KEY). Values are injected as env when running skills and LLM.
Thin CLI bridge to Cursor via official @cursor/sdk (prompt -> streamed stdout)
Use Google Cloud CLI (gcloud) for project/account checks and Google API operations. Use when users ask for gcloud commands, Google Cloud auth, project configuration, IAM, or cloud resource inspection and updates.
Use Trello CLI in orgops agents for Trello board/list/card operations with non-interactive command patterns.
Slack skill: per-agent Slack skill + Socket Mode listener server. Run the server on lifecycle start.
| name | tavily |
| description | Install and use Tavily CLI (tvly) for web search/extract/crawl. Uses secret/env TAVILY_API_KEY. |
This skill provides a portable way to ensure the Tavily CLI (tvly) is installed on the current runner host and to run common Tavily commands.
tavily with key TAVILY_API_KEY.Recommended:
node --import tsx skills/secrets/assets/set.ts -- tavily TAVILY_API_KEY <value>
The scripts in this skill will:
TAVILY_API_KEY from environment.--api-key to pass explicitly (useful for local testing).Use the installer recommended by Tavily docs:
curl -fsSL https://cli.tavily.com/install.sh | bash
Notes:
tvly is typically installed under:
~/Library/Python/<pyver>/bin/tvlyPATH for the subprocess.node --import tsx skills/tavily/assets/ensure.ts
node --import tsx skills/tavily/assets/search.ts -- --query "Cursor agent headless CLI" --max-results 5 --depth advanced --json
node --import tsx skills/tavily/assets/extract.ts -- --url "https://example.com" --json
node --import tsx skills/tavily/assets/crawl.ts -- --url "https://example.com" --max-depth 2 --json
--json, scripts print JSON to stdout (best for piping into other tools/agents).