⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

web-router

@nimbleway⭐ 373 stars

>

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐⭐ 373 on GitHubGitHub ↗

Popular

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

WebRouter connects agents to search, extract, live data, answer, research and browsers through one typed interface, across many providers.

  • Agent web primitives. Find pages, read them, ask for an answer, run deep research, call a site's structured scraper, or drive a browser.
  • Smart routing. Static fallback and optional routers trade off cost, latency and coverage for each task and the providers you have keys for.
  • No vendor lock-in. Calls and results keep the same shape when you switch providers. WebRouter is Apache 2.0 and runs with your own keys.
  • Providers and vendor APIs. Use one call shape across web providers, then use the curated catalog for provider-specific APIs.
  • Governance and security. Control provider selection and routing, keep keys scoped to their provider, reject unsupported constraints, and require explicit opt-in for vendor writes.

Developer preview: the API may change before 1.0. Share feedback on Discord.

Quickstart

Install WebRouter and make a search with no API key:

pip install "webrouter[all]"
from web_router import WebRouter

response = WebRouter().search("what is retrieval augmented generation", max_results=5)

for result in response.results:
    print(result.title, result.url)

print(response.provider)  # which backend actually answered

pages = WebRouter().extract(response.urls[:3], format="markdown")
for document in pages.documents:
    print(document.url, len(document.content))

The full Quickstart adds a named provider, API keys, async usage, install extras and source setup.

Runnable examples cover each core method, routing, integrations and common errors. Most need no credentials.

Documentation

The docs site is the canonical guide for getting started and for the core methods. This README keeps the advanced and contributor-facing surfaces that have not moved there yet.

Provider support

Twelve search backends, seven extract backends, a live data catalogue, five answer backends, three agentic research backends (plus Exa's, retired upstream), five browser-session backends and three browser agents. One call each. Switching between them is one argument.

A provider name serves the methods it serves and no others: brave searches and cannot extract, oxylabs extracts and cannot search, nimble searches, extracts, runs live data and researches, and browserbase opens sessions, runs browse tasks and extracts. Ask a method for another's backend and it says so, naming the backends that method does serve.

Search

[search] installs all of these but AgentCore, which needs [aws]. The first column is what you pass to WebRouter(...) to pick one at runtime. The string beside it is the same value, and what response.provider and configured_providers() report back.

PassNameProviderBacked byOptions mapped
Provider.NIMBLEnimbleNimblenimble-pythonall but effort
Provider.TAVILYtavilyTavilytavily-pythonall but effort
Provider.YOUyouYou.comdirect HTTPall but effort
Provider.BRAVEbraveBravedirect HTTPall but effort; search_depth at lite only
Provider.EXAexaExadirect HTTPall but locale
Provider.PARALLELparallelParalleldirect HTTP (/v1/search, mode=fast unless effort sets it)all but locale; search_depth at lite and fast
Provider.PERPLEXITYperplexityPerplexitydirect HTTPall of them; search_depth at lite and fast
Provider.LINKUPlinkupLinkupdirect HTTPmax_results, include_domains, exclude_domains, recency, effort
Provider.WEBIQwebiqWebIQ (Microsoft AI Web Search)direct HTTPall but recency and effort
Provider.KEENABLEkeenableKeenabledirect HTTP; keyless with allow_keyless=True (rate-limited per IP)max_results, search_depth (lite, fast), include_domains (one), recency, effort
Provider.DEEPSEEKdeepseekDeepSeek Searchdirect HTTPmax_results (at most 50), search_depth (lite, deep), include_domains, exclude_domains, locale, recency, the last four sent inside the query, which must fit 128 characters
Provider.AGENTCOREagentcoreAWS AgentCore Web Search, through your own AgentCore Gateway (setup)MCP over HTTP, SigV4 via botocore ([aws])max_results (at most 25), include_domains, exclude_domains, recency (connector 1.2.0 or later). An end date is AgentCore's own provider_options={"filters": {"publishedDateFilter": {"to": ...}}}. Queries up to 200 characters. AWS's terms: show each result's citation, and do not store results in bulk
Provider.YOU_MCPyou-mcpYou.com MCPdirect HTTP, no keyall but effort
Provider.EXA_MCPexa-mcpExa MCP, its web_search_advanced_exa tooldirect HTTP, no keyall but locale

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • skills/web-router/SKILL.md4.2 KB24226afca1d8upstream ↗
    ---
    name: web-router
    description: >
      Search, read and research the web through web-router's MCP tools, choosing
      the cheapest method that answers. Use when a task needs live web data —
      finding pages, reading a known URL, multi-step research, or driving a
      browser — and the web-router MCP server is connected. Covers method
      selection, cost awareness, job polling, and browser-session hygiene.
    ---
    
    # web-router
    
    One typed interface over many web backends, six methods. The tools describe
    *your* install: their `provider` enums list only backends this machine holds
    keys for, and `search`/`extract` work with no key at all. Read the
    `web-router://capabilities` resource once to learn what is configured before
    planning around a paid method.
    
    ## Choose the cheapest method that answers
    
    Work up this ladder and stop at the first rung that serves the task:
    
    1. **`search`** — find pages. Ranked links with page text, about a second,
       free on the keyless tier. Most questions end here.
    2. **`extract`** — read pages you already have URLs for, about a second.
       Prefer `search` + `extract` over anything below: two cheap calls that you
       compose beat one expensive call you wait on.
       **`live_data`** sits beside it: when `live_data_sources` lists a vendor's
       ready-made scraper for the site and item at hand (pass `query` to search
       the catalogue), one run fetches the site now and returns its fields as
       records, one billed run. All three live data tools need `provider` named.
       Read `live_data_source` first — its `input_schema` says exactly what
       `inputs` to pass, a URL for some sources and an id or a search term for
       others.
    3. **`research`** — an agentic run that searches, reads and cross-checks over
       many turns. **Minutes, and it bills.** Use only when the question genuinely
       needs synthesis across many sources that iterative `search`/`extract`
       cannot reach in a few calls.
    4. **`browse`** — a hosted browser agent drives a real browser through a task.
       **Minutes, and it bills.** Use when the answer is behind interaction —
       forms, pagination, dynamic pages — and you can state the task in one
       sentence.
    5. **`browser_*`** — you drive the browser yourself. `local` is free; a cloud
       session **bills per minute until closed**. Use when the interaction needs
       your judgment step by step rather than a delegated task.
    
    ## Cost rules
    
    - Never start a second `research` or `browse` run for a question whose first
      run is still going: `research`/`browse` return a handle after ~25 seconds —
      poll `research_status`/`browse_status` (free) instead of calling the method
      again, which starts and bills a second run.
    - `fetch_raw` is free and instant: every result carries a `handle`, and the
      backend's full payload is already held for it. Reach for `fetch_raw` before
      re-calling a tool for more detail.
    - Close every browser session with `browser_close` the moment you are done.
      Prefer `provider="local"` unless the task needs stealth, a proxy country or
      CAPTCHA solving, which only billed cloud vendors serve.
    - Leave `provider` unset (`auto`) unless you have a reason: it prefers the
      backends configured here and falls back to the keyless tier.
    - `extract` with `provider="max"` reads the page through every configured
      backend at once and returns the first answer -- the fastest read possible,
      at one fetch per backend. Use it only when the user has asked for speed
      over cost, never by default.
    
    ## What the tools will and will not do
    
    - A parameter a backend cannot serve is refused by name, never silently
      dropped — on a refusal, drop the option or pick another provider; do not
      retry the same call unchanged.
    - Results are shaped to fit a context window and say when they were cut; the
      handle gets you the rest. Do not treat a truncation note as missing data.
    - Browser tools open only `http:`/`https:` pages and `about:blank`; refs from
      `browser_snapshot` go stale on the next snapshot or navigation — take a
      fresh snapshot after the page changes rather than retrying a stale ref.
    - The server never shows you a CDP URL, live-view URL or credential, and
      redacts them from every browse and browser output. Do not ask for them or
      try to reconstruct them.
    
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/nimbleway-webrouter-skills-web-router.md

// REPO STATS

373 stars