By plabzzxxUpdated 2026-05-114 versions · latest released 2026-03-08tavily-one-step-search@clawhub_plabzzxx/tavily-one-step-search
Workflow OrchestrationTool Use#网页搜索
According to AlphaMoat, as of 2026-09, 联网搜索一键配置 · Tavily One-Step has 3,773 downloads and 3 stars — ranked #2,815 of 5,078 AI skills overall, and #559 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 39 | 1.3K | 1 | - |
| SkillHub ↗ | 501 | 3.8K | 3 | — |
Platforms count differently and update at different times.
Its search, extract, crawl and map subcommands cover filtered searches, content extraction, site crawling and URL discovery. Set TAVILY_API_KEY in the environment or ~/.openclaw/.env before use. Requests inherit system proxy settings by default, with options to force a proxy or disable it. Search results depend on the provider, query and access; verify important claims against the linked source and its date.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 3.8K | — | 3 |
| 2026-08 | 3.0K | +19.9% | 3 |
| 2026-07 | 2.5K | +23.8% | 3 |
| 2026-06 | 2.0K | +13.4% | 3 |
| 2026-05 | 1.8K | — | 1 |
| 2026-03 | 1.1K | — | 1 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: tavily-search description: "联网搜索, 网页搜索, 实时联网, 一键配置。让 OpenClaw 用 Tavily 实现实时搜索（含免费额度）。One-step install + guided key setup. Guide: github.com/plabzzxx/openclaw-tavily-search" --- # Tavily Search Toolkit (V2) This skill provides a single Node CLI with subcommands: - `search` — web search with filters and multiple output formats
- `extract` — fetch clean content from one or more URLs
- `crawl` — crawl a site with extraction controls
- `map` — discover and map site URLs
## Requirements
Set `TAVILY_API_KEY` via one of:
- env var: `TAVILY_API_KEY=...`
- `~/.openclaw/.env` line: `TAVILY_API_KEY=...`
## Quick examples
```bash
# 1) Search (Brave-like structure)
node {baseDir}/scripts/tavily_search.mjs search \
--query "OpenClaw multi-agent" --max-results 5 --format brave
# 2) Search with domain filters
node {baseDir}/scripts/tavily_search.mjs search \
--query "周大福" \
--include-domains ctf.com.cn,ctfmall.com,chowtaifook.com \
--format brave
# 3) Extract specific URLs
node {baseDir}/scripts/tavily_search.mjs extract \
--urls https://docs.openclaw.ai,https://docs.tavily.com \
--content-format markdown --format md
# 4) Crawl docs site
node {baseDir}/scripts/tavily_search.mjs crawl \
--url docs.tavily.com --max-depth 2 --limit 30 --format md
# 5) Map a site structure
node {baseDir}/scripts/tavily_search.mjs map \
--url docs.openclaw.ai --max-depth 2 --limit 40 --format md
```
## Proxy controls
- Inherit system proxy env by default (`HTTP_PROXY` / `HTTPS_PROXY`)
- Force proxy: `--proxy http://127.0.0.1:7890`
- Disable proxy: `--no-proxy`
## Notes
- Keep `max-results` small (3–5) for chat tasks.
- Use `search --format brave` for stable downstream parsing.
- Use `extract/crawl/map` only when search snippets are insufficient.
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Stores agent memory and cross-skill state as a typed, constraint-checked knowledge graph.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.