What makes tavily-search-pro-native-node notable?

1.6K downloads. Trust evidence available

How should tavily-search-pro-native-node be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

tavily-search-pro-native-node

Research-grade Tavily web search for OpenClaw using native Node.js with zero dependencies. Use for deep web research, multi-URL content extraction, estimated Tavily credit tracking, response caching, usage-log review, and 429 backoff. Includes search, extract, stats, and cache subcommands. Requires TAVILY_API_KEY in the process environment. For minimal search-only use, prefer tavily-search-native-node.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.6k

Updated

Oct 10, 2026

Version

1.0.36

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.6K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.36release · observed Sep 11, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s177the448m6rk54wz8gse0jnd8587yq:tavily-search-pro-native-node

Install using `clawhub skill install s177the448m6rk54wz8gse0jnd8587yq:tavily-search-pro-native-node` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/jwestburg/tavily-search-pro-native-node before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-jwestburg-tavily-search-pro-native-node/snapshot"

Documentation

CLAWHUB

145,758 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: tavily-search-pro-native-node
description: Research-grade Tavily web search for OpenClaw using native Node.js with zero dependencies. Use for deep web research, multi-URL content extraction, estimated Tavily credit tracking, response caching, usage-log review, and 429 backoff. Includes search, extract, stats, and cache subcommands. Requires TAVILY_API_KEY in the process environment. For minimal search-only use, prefer tavily-search-native-node.
version: 1.0.36
metadata:
  openclaw:
    requires:
      env:
        - TAVILY_API_KEY
    primaryEnv: TAVILY_API_KEY
    envVars:
      - name: TAVILY_API_KEY
        required: true
        description: Tavily API key used for authenticated search and extract requests.
risk_class: external-research-api-credit-cache-log-local-delete
---

# Tavily Search Pro (Native Node)

Version: 1.0.36 / public ClawHub utility candidate with external API, cache, usage-log, and approval-gated local cache deletion behavior.

Research-grade Tavily web search helper: one dependency-free Node script with `search`, `extract`, `stats`, and `cache` subcommands.

## Risk / invocation class

Risk class: **external research API / credit usage / plaintext query logging / local cache deletion**.

Use deliberately. This skill sends search queries or URLs to Tavily over HTTPS, may append plaintext queries/URLs to a local usage log unless `--no-log` is used, and exposes `cache clear` as approval-gated local deletion of cached response JSON files.

## Input packet

Required:

- `task`: search, extract, usage stats, or cache inspection.
- `query_or_urls`: search query or URL list when applicable.
- `privacy_sensitivity`: normal, sensitive, client/private, or unknown. `unknown` is a fail-closed state for `search` and `extract`: classify sensitivity first or obtain explicit approval for external Tavily transmission before running an outbound command.
- `freshness_need`: normal cache ok, fresh/no-cache, or news/freshness-critical.
- `depth`: basic unless advanced is justified.

Optional:

- `trusted_domains`: include/exclude domains.
- `max_results`: default 5; avoid broad high-result searches unless needed.
- `logging_preference`: normal log, `--no-log`, or unknown.
- `output_format`: human summary or `--json`.

Stop or switch tools if the query is privacy-sensitive and sending it to Tavily is not appropriate. If `privacy_sensitivity` is `unknown`, do not run `search` or `extract` until sensitivity is classified as normal or explicit approval resolves the external-send ambiguity. For one known URL, prefer `web_fetch` unless extraction quality matters.

## Output packet

Return compactly:

- command used or planned, redacted as needed
- whether cache/logging was enabled
- freshness/depth choice
- sources/results with URLs
- estimated credits used or expected when known
- limitations/caveats
- next safe research step

## Security behavior

- Reads `TAVILY_API_KEY` from the process environment only.
- Does not read credential files

_meta.json

{
  "ownerId": "kn78bc0rnqe8pnvd4azdnjvmmd858m3q",
  "slug": "tavily-search-pro-native-node",
  "version": "1.0.36",
  "publishedAt": 1789093027632
}

references/tavily-pro-contract.md

# Tavily Search Pro Contract

Use only when the compact `SKILL.md` is not enough.

## Commands

Script: `scripts/tavily-pro.mjs`

Subcommands:

- `search`
- `extract`
- `stats`
- `cache`
- `help`

## Quick reference

```powershell
node "<skill-dir>\scripts\tavily-pro.mjs" search "OpenClaw skills ecosystem"
node "<skill-dir>\scripts\tavily-pro.mjs" extract https://example.com/ https://www.iana.org/help/example-domains
node "<skill-dir>\scripts\tavily-pro.mjs" stats
node "<skill-dir>\scripts\tavily-pro.mjs" cache info
node "<skill-dir>\scripts\tavily-pro.mjs" cache      # defaults to cache info
node "<skill-dir>\scripts\tavily-pro.mjs" cache clear # local deletion - requires explicit approval
node "<skill-dir>\scripts\tavily-pro.mjs" help
```

## Search flags

| Flag | Values | Default | Purpose |
|---|---|---|---|
| `--topic` | `general` / `news` | `general` | `news` biases to fresh articles |
| `--depth` | `basic` / `advanced` | `basic` | `advanced` = 2 credits |
| `--max` | 1-20 | `5` | Results to return |
| `--days` | integer | `7` news only | Age window |
| `--include` | comma list | none | Domains to include |
| `--exclude` | comma list | none | Domains to exclude |
| `--raw-content` | flag | off | Include full page text per result |
| `--json` | flag | off | Raw JSON output |
| `--no-cache` | flag | off | Skip cache |
| `--no-log` | flag | off | Skip usage log |
| `--no-retry` | flag | off | No backoff on 429 |
| `--ttl` | seconds | 24h general, 1h news | Override cache TTL |
| `--timeout-ms` | integer | 30000 | Per-attempt network timeout |

## Extract flags

Wraps Tavily's `/extract` endpoint. Takes one or more public HTTP(S) URLs. The CLI requires raw conventional `http://` or `https://` URLs with a host, rejects malformed/non-HTTP(S)/raw-backslash/credential-bearing URL arguments, and refuses localhost, loopback, unspecified IPv4/IPv6, link-local, RFC1918/private-address URLs, and private/local IPv4-mapped IPv6 forms before sending anything to Tavily. Credential-bearing and local/private URL errors are sanitized and do not echo the supplied URL.

```powershell
node ".\scripts\tavily-pro.mjs" extract https://example.com
node ".\scripts\tavily-pro.mjs" extract https://a.com https://b.com https://c.com
node ".\scripts\tavily-pro.mjs" extract --depth advanced https://spa-site.com
```

Flags: `--depth`, `--json`, `--no-cache`, `--no-log`, `--no-retry`, `--ttl`, `--timeout-ms`.

Estimated credits: Tavily bills extract in batches of 5 URLs - 1 credit per 5 URLs basic, 2 per 5 advanced. The usage log estimates this locally; it is not a Tavily-returned billing value.

## Stats

```powershell
node ".\scripts\tavily-pro.mjs" stats
node ".\scripts\tavily-pro.mjs" stats --days 7
node ".\scripts\tavily-pro.mjs" stats --json
```

Output includes total calls, searches vs extracts, cache hit rate, errors, estimated credits used, and estimated credits avoided by cache.

## Cache

```powershell
node ".\scripts\tavily-pro.mjs" cache info
node ".\scripts\tav

skill-card.md

## Description:

Research-grade Tavily web search for OpenClaw using native Node.js with zero dependencies, supporting deep web research, multi-URL extraction, estimated credit tracking, response caching, usage-log review, and 429 backoff.

This skill is ready for commercial/non-commercial use.

## Publisher:

[jwestburg](https://clawhub.ai/user/jwestburg)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and research agents use this skill to run Tavily-backed web searches, extract content from public URLs, inspect usage statistics, and manage response cache behavior while tracking estimated credit use.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Search queries and accepted public URLs are sent to Tavily with the configured API key.

Mitigation: Use this skill only for queries and URLs approved for external Tavily processing, and classify privacy sensitivity before outbound search or extract use.

Risk: Usage logs may contain plaintext queries or URLs, and cached responses may persist under the skill-specific OpenClaw cache directory.

Mitigation: Use --no-log --no-cache for sensitive or client/private research that is approved for external processing.

Risk: Cached responses are not scoped by Tavily account when multiple accounts share one OS profile.

Mitigation: Use separate OS profiles for account isolation or disable caching with --no-cache.

Risk: The cache clear subcommand deletes local cached response files.

Mitigation: Run cache clear only when deletion is intentional; the skill limits deletion to expected cache files under its own cache directory and reports partial failures.

## Reference(s):

- [Tavily Search Pro Contract](references/tavily-pro-contract.md)
- [ClawHub Skill Page](https://clawhub.ai/jwestburg/skills/tavily-search-pro-native-node)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown or JSON command output with source URLs, cache/logging status, freshness and depth choices, estimated credit use, caveats, and next-step guidance.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May emit raw JSON when requested; normal usage returns compact human-facing text.]

## Skill Version(s):

1.0.36 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 15h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.