← 返回 Skills 市场
23235
总下载
100
收藏
170
当前安装
59
版本数
在 OpenClaw 中安装
/install web-search-plus
功能描述
Unified multi-provider web search and URL extraction skill with intelligent auto-routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, Perple...
安全使用建议
Install only if you are comfortable sending searches and extraction URLs to the selected third-party providers. Use an explicit provider for sensitive work, disable or clear the cache when queries may contain confidential terms, avoid extracting private/internal URLs, and prefer environment variables or locked-down file permissions for API keys on shared machines.
能力评估
Purpose & Capability
The artifacts coherently implement multi-provider web search, URL extraction, provider fallback, and research mode; sending queries and URLs to configured provider APIs is central to that purpose and is disclosed.
Instruction Scope
The skill instructions are focused on web search and extraction workflows, with narrow trigger phrases and no hidden role changes, unrelated agent commands, or deceptive runtime instructions found.
Install Mechanism
The interactive setup wizard collects provider choices and may write API keys to local config.json; this is purpose-aligned and disclosed in setup, though one SKILL.md privacy bullet overstates that API keys are never persisted.
Credentials
Environment and network access are proportionate to the stated integrations: provider API keys, SearXNG settings, WSP cache/security toggles, listed provider hosts, and user-configured SearXNG instances.
Persistence & Privilege
Search queries, results, and provider failure history are cached locally by default with 0700/0600 cache permissions plus --no-cache, WSP_DISABLE_CACHE, clear-cache, and cache-stats controls; config.json credential storage should be protected on shared systems.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install web-search-plus - 安装完成后，直接呼叫该 Skill 的名称或使用
/web-search-plus触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v3.2.0
## What's new in v3.2.0
Feature sync with hermes-web-search-plus v2.3.0/v2.4.0 plus fixes for all SkillSpector scan findings.
Added: research mode, canonical-source intent reranking, quality reports, ProviderSpec registry, retry jitter and locked provider-health writes.
Security: narrow triggers, third-party transmission disclosure, local caching disclosure/hardening, SSRF guard for user URLs, permissions metadata, credential redaction.
Fixed: Exa deep/deep-reasoning auto-routing propagation and Docker SearXNG SSRF validation handling.
Verification: python3 -m unittest discover -s tests -p test_*.py — 53/53 passing.
v3.1.0
- Added SerpBase as an explicit/fallback-only Google SERP provider (requires prepaid credits).
- Now supports 11 search providers, with SerpBase opt-in via flag or config.
- Updated provider priority and routing documentation to reflect SerpBase's explicit usage.
- Expanded configuration and setup docs for SerpBase, including new environment variable.
- Minor updates to tags, README, and configuration examples to reflect the additional provider.
v3.0.3
web-search-plus 3.0.3
- Added test-auto-routing.sh script for automatic routing verification.
- Updated documentation (SKILL.md, CHANGELOG.md) to reflect latest changes.
- Bumped version and metadata in package.json and SKILL.md.
v3.0.2
- Improved documentation in SKILL.md and related files.
- Minor updates to scripts and metadata for clarity and maintainability.
- Removed deprecated test script (test-auto-routing.sh).
- No breaking changes to the skill's core functionality.
v3.0.1
- Improved documentation and provider credential examples in SKILL.md.
- Minor package metadata and config updates.
- No functional changes to core features or interfaces.
v3.0.0
**Major update: Adds support for new providers and unified content extraction.**
- Expanded from 7 to 10 search providers including Brave, Linkup, and Firecrawl.
- Introduced a new unified extraction script (`extract.py`) with automatic fallback across five providers.
- Enhanced provider auto-routing with improved query analysis and routing logic.
- All documentation updated for new providers, extraction capabilities, and usage examples.
- Configuration, environment variable, and security documentation improved; `.env.example` and `config.example.json` updated.
- Added tests for routing and extraction flows.
v2.9.3
- Added Docker environment detection script (`scripts/docker_detect.py`) to improve environment awareness.
- Updated package metadata and documentation for the new version (2.9.3).
- Minor documentation and metadata improvements across files.
v2.9.2
Docs portability cleanup: replaced hardcoded temp cache path examples with portable TMP_DIR placeholders.
v2.9.0
Web Search Plus v2.9.0 introduces Querit as a new multilingual search provider.
- Added Querit integration for AI-powered, multilingual/international search.
- Expanded auto-routing and documentation to cover 7 providers (Serper, Tavily, Querit, Exa, Perplexity, You.com, SearXNG).
- Updated configuration, API key info, and usage examples to include Querit.
- Refreshed provider comparison and quick start documentation.
v2.8.6
Documented Perplexity Sonar Pro usage and refreshed release docs.
v2.8.5
web-search-plus 2.8.5
- Updated package version to 2.8.5.
- Minor updates in CHANGELOG.md and scripts/search.py.
- No changes to SKILL.md; user-facing documentation is unchanged.
v2.8.4
Security: SSRF protection added to setup.py SearXNG connection test
v2.8.3
Fix: Perplexity provider returned 0 results — answer now mapped as primary result
v2.8.2
Fix SKILL.md metadata inconsistencies: add KILOCODE_API_KEY to env declarations, update all provider references to include Perplexity
v2.8.1
Detailed changelog + docs for Perplexity provider and routing rebalance
v2.8.0
Add Perplexity provider via Kilo Gateway + rebalance routing (Tavily for research, Exa for discovery, Perplexity for direct answers)
v2.7.2
Security: Implement actual SSRF protection - resolve hostnames and block private/internal IPs (loopback, RFC1918, link-local, cloud metadata). Add SEARXNG_ALLOW_PRIVATE=1 escape hatch for intentional self-hosted setups.
v2.7.1
Security fix: Add SSRF protection for SearXNG instance URL validation. Enforce http/https scheme, prevent prompt injection from redirecting to internal endpoints.
v2.7.0
**Version 2.7.0 (web-search-plus):**
- Documentation fully updated across README, FAQ, SKILL, and TROUBLESHOOTING for clarity and completeness.
- Improved instructions and API key setup guides.
- Enhanced configuration examples and usage explanations.
- No changes to provider support or algorithm logic.
- Version updated in metadata and docs.
v2.6.5
Fix: SKILL.md metadata env vars now correctly marked optional (was array format interpreted as required by registry)
元数据
常见问题
Web Search Plus 是什么？
Unified multi-provider web search and URL extraction skill with intelligent auto-routing across Serper, Brave, Tavily, Querit, Linkup, Exa, Firecrawl, Perple... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 23235 次。
如何安装 Web Search Plus？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web-search-plus」即可一键安装，无需额外配置。
Web Search Plus 是免费的吗？
是的，Web Search Plus 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Web Search Plus 支持哪些平台？
Web Search Plus 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Web Search Plus？
由 Robby（@robbyczgw-cla）开发并维护，当前版本 v3.2.0。
推荐 Skills