zero-api-key-web-search

OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. No API keys required by default; optional providers can be enabled for stronger coverage. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "zero-api-key-web-search" with this command: npx skills add wd041216-bit/openclaw-free-web-search

Zero-API-Key Web Search for OpenClaw

This skill gives OpenClaw a practical verification workflow:

  • zero-search for live search results (7 engines via Bright Data)
  • zero-search providers for provider discovery
  • zero-browse for reading pages (auto-unlocks blocked content)
  • zero-verify for support/conflict classification
  • zero-report for a citation-ready summary with next steps
  • zero-setup for interactive provider configuration

Install

pip install zero-api-key-web-search

Minimum verification

zero-search "OpenAI API pricing" --type news --timelimit w
zero-search providers
zero-browse "https://docs.python.org/3/whatsnew/"
zero-verify "Python 3.13 is the latest stable release" --deep --max-pages 2 --json
zero-report "Python 3.13 stable release" --claim "Python 3.13 is the latest stable release" --deep --json

Provider paths

ProfileProvidersBest for
freeddgsZero-setup local search
free-verifiedddgs, searxngFree cross-validation
productionbrightdataProduction reliability and geo-targeting
production-unlockbrightdata, web_unlockerProduction SERP + blocked page access
max-evidenceddgs, searxng, brightdataMaximum provider diversity

Recommended flow

  1. Run zero-search for factual or recent questions.
  2. Use zero-browse on the most relevant source when snippets are not enough.
  3. Use zero-verify when a concrete claim needs a support/conflict summary.
  4. Use zero-report when you want a compact evidence package with citations and next steps.
  5. Use --deep when the claim matters enough to justify page-aware verification.
  6. Cite the returned URLs in the final answer.
  7. Use optional brightdata only when configured or explicitly requested.

Multi-engine search (Bright Data)

zero-search "AI regulation" --provider brightdata --engine google --region us-en --json
zero-search "AI regulation" --provider brightdata --engine bing --region gb-en --json
zero-search "news" --provider brightdata --engine yandex --region ru-ru --json

Supported engines: google, bing, duckduckgo, yandex, baidu, yahoo, naver.

Web Unlocker (blocked pages)

# Auto-fallback (default) — direct fetch, then unlocker on 403/429
zero-browse "https://protected-site.com/article"

# Force Web Unlocker
zero-browse "https://protected-site.com/article" --use-unlocker always

Optional Bright Data provider

# Interactive setup wizard
zero-setup

# Or set environment variables
export ZERO_SEARCH_BRIGHTDATA_API_KEY="..."
export ZERO_SEARCH_BRIGHTDATA_ZONE="serp_api1"
export ZERO_SEARCH_BRIGHTDATA_UNLOCKER_ZONE="web_unlocker1"

New Bright Data users can sign up at https://get.brightdata.com/h21j9xz4uxgd.

What success looks like

  • the verdict is explicit
  • the result includes support and conflict scores
  • page_aware is true when deep verification ran
  • the recommended free path is ddgs + self-hosted searxng
  • optional production path is brightdata + web_unlocker via ZERO_SEARCH_BRIGHTDATA_API_KEY
  • source URLs are ready to cite

Limits

  • zero-verify is heuristic and evidence-aware, not a proof engine.
  • The default provider path is ddgs.
  • The recommended free upgrade path is self-hosted searxng via ZERO_SEARCH_SEARXNG_URL.
  • Bright Data is optional and should not receive queries unless configured or requested.
  • Conflicting sources are surfaced, not automatically reconciled.

License

MIT License.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

yula-web-search

Yula's custom web search - NO API KEY required. Uses multiple fallback search methods with public services that allow anonymous access. Works by direct curl...

Registry SourceRecently Updated
2101Profile unavailable
General

GLM MCP Server Use

GLM MCP Server Use for OpenClaw. Configure and use the 4 official Z.AI / GLM MCP servers (vision, web search, web reader, zread) with environment-variable AP...

Registry SourceRecently Updated
1480Profile unavailable
Web3

Veroq

Provide verified AI intelligence on markets, assets, sentiment, and economic data with live prices, signals, analysis, and fact-checking from 1,000+ tickers...

Registry SourceRecently Updated
1580Profile unavailable
General

xiaohongshu-mcp-openclaw

当用户提到小红书/XHS/Rednote 并需要关键词搜笔记、看笔记详情、抓评论、统计点赞与评论数时使用。通过 xpzouying/xiaohongshu-mcp + mcporter 提供统一查询流程。

Registry SourceRecently Updated
2610Profile unavailable