Claude Skill

tavily

AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.

LLM Mart · 0 points · 18 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download kcnyu-clawock-skills_tavily-search-97181ee.zip · 14 KB
kcnyu/clawock 15 0 forks MIT Updated 7h ago
Part of kcnyu/clawock — 17 skills

Install

skills CLI npx skills add https://github.com/KCNyu/clawock/tree/master/skills/tavily-search
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install kcnyu-clawock@llmmart
Git git clone https://github.com/KCNyu/clawock.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole kcnyu/clawock collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Tavily Search

AI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.

Search

node {baseDir}/scripts/search.mjs "query" --bucket research
node {baseDir}/scripts/search.mjs "query" -n 10 --bucket research
node {baseDir}/scripts/search.mjs "query" --deep --bucket research
node {baseDir}/scripts/search.mjs "query" --topic news --bucket research

Options

  • -n <count>: Number of results (default: 5, max: 20)
  • --deep: Use advanced search for deeper research (slower, more comprehensive)
  • --topic <topic>: Search topic - general (default) or news
  • --days <n>: For news topic, limit to last n days
  • --bucket <name>: Which monthly budget bucket to charge — brief / report / intraday / research / extract / default. Ad-hoc/manual research uses --bucket research. Omitting it charges the small default bucket (60/mo), which is exhausted quickly on purpose.

Budget (免费档 1000 credits/月, 全局共享)

basic 搜索 1 credit，--deep 2，extract 1/5 URL。硬护栏在 lib/ledger.mjs（本地月度账本，reservation 式扣费，超限 exit 0 优雅降级返回 "unavailable" — 别当报错，退回内置搜索）。账本在仓库外 /root/.openclaw/tavily-credit-ledger.json；查真实账单：curl -H "Authorization: Bearer $TAVILY_API_KEY" https://api.tavily.com/usage（注意有延迟，不能当实时闸）。

Extract content from URL

node {baseDir}/scripts/extract.mjs "https://example.com/article" --bucket extract

--bucket works the same as for search (charges that monthly bucket; omit → default). extract costs 1 credit per 5 URLs.

Notes:

  • Needs TAVILY_API_KEY from https://tavily.com
  • Tavily is optimized for AI - returns clean, relevant snippets
  • Use --deep for complex research questions
  • Use --topic news for current events
Files (clawock)
  • lib
    • ledger.mjs 14.2 KB · in bundle
    • ledger.test.mjs 5 KB · in bundle
  • scripts
    • extract.mjs 2.7 KB · in bundle
    • search.mjs 5.3 KB · in bundle
    • search.test.fetchmock.mjs 1.1 KB · in bundle
    • search.test.mjs 2.9 KB · in bundle
  • SKILL.md 2.1 KB 
    ---
name: tavily
description: AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
homepage: https://tavily.com
metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["node"],"env":["TAVILY_API_KEY"]},"primaryEnv":"TAVILY_API_KEY"}}
---

# Tavily Search

AI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.

## Search

```bash
node {baseDir}/scripts/search.mjs "query" --bucket research
node {baseDir}/scripts/search.mjs "query" -n 10 --bucket research
node {baseDir}/scripts/search.mjs "query" --deep --bucket research
node {baseDir}/scripts/search.mjs "query" --topic news --bucket research
```

## Options

- `-n <count>`: Number of results (default: 5, max: 20)
- `--deep`: Use advanced search for deeper research (slower, more comprehensive)
- `--topic <topic>`: Search topic - `general` (default) or `news`
- `--days <n>`: For news topic, limit to last n days
- `--bucket <name>`: **Which monthly budget bucket to charge** — `brief` / `report` / `intraday` / `research` / `extract` / `default`. Ad-hoc/manual research uses `--bucket research`. **Omitting it charges the small `default` bucket (60/mo)**, which is exhausted quickly on purpose.

## Budget (免费档 1000 credits/月, 全局共享)

basic 搜索 1 credit，`--deep` 2，extract 1/5 URL。硬护栏在 `lib/ledger.mjs`（本地月度账本，reservation 式扣费，超限 **exit 0** 优雅降级返回 "unavailable" — **别当报错**，退回内置搜索）。账本在仓库外 `/root/.openclaw/tavily-credit-ledger.json`；查真实账单：`curl -H "Authorization: Bearer $TAVILY_API_KEY" https://api.tavily.com/usage`（注意有延迟，不能当实时闸）。

## Extract content from URL

```bash
node {baseDir}/scripts/extract.mjs "https://example.com/article" --bucket extract
```

`--bucket` works the same as for search (charges that monthly bucket; omit → `default`). extract costs 1 credit per 5 URLs.

Notes:
- Needs `TAVILY_API_KEY` from https://tavily.com
- Tavily is optimized for AI - returns clean, relevant snippets
- Use `--deep` for complex research questions
- Use `--topic news` for current events
  • _meta.json 132 B 
    {
  "ownerId": "kn7azq5e6sw0fbwwzdpcwvvjzd7z0x4z",
  "slug": "tavily-search",
  "version": "1.0.0",
  "publishedAt": 1768114920544
}

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related

Claude Prompt
Tighten-my-prose editing prompt
Claude Skill
Adversarial code-review skill for Claude
Claude Workflow
Deep-research workflow (fan-out + verify)
Claude Skill
Conventional-commit writer for Claude