New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Keirouter Web Search

by mydisha in mydisha/keirouter

Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity.

MITAuto-check passedProductivity & Automation

Install Keirouter Web Search

skills CLI
$ npx skills add mydisha/keirouter --skill keirouter-web-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mydisha/keirouter keirouter-web-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mydisha/keirouter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/keirouter-web-search .claude/skills/keirouter-web-search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
keirouter-web-search
GitHub stars
147
Token cost
~771 tokens
SKILL.md length
121 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity.

  • The user wants to search the web
  • SKILL.md covers Discover, Endpoint, Examples and Response shape, plus 1 more section
  • Calls curl and jq; needs KEIROUTER_KEY
  • Look up information

What it does

Keirouter Web Search is an agent skill from mydisha/keirouter. Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Web search. It works with Tavily and Perplexity. The repository describes itself as: Your friendly, blazing-fast, self-hostable AI gateway. The licence is MIT.

When your agent uses it

  • The user wants to search the web
  • Look up information
  • Query a search engine

Example prompts

  • “/keirouter-web-search”

Requirements

  • A credential in KEIROUTER_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 3d8b702. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • KEIROUTER_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Keirouter Web Search loads about 771 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 121 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~771

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mydisha/keirouter at commit 3d8b702, republished under its MIT licence (© mydisha). 121 words, ~771 tokens.

Download SKILL.mdSave it as .claude/skills/keirouter-web-search/SKILL.md (or your agent's skills folder).
name
keirouter-web-search
description
Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.

Requires KEIROUTER_URL (and KEIROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/mydisha/keirouter/main/skills/keirouter/SKILL.md for setup.

Discover

bash
curl $KEIROUTER_URL/v1/models/web | jq '.data[] | select(.kind=="webSearch") | .id'
# Per-provider params (searchTypes, maxResults, required options like cx for google-pse)
curl "$KEIROUTER_URL/v1/models/info?id=tavily/search"

IDs end in /search (e.g. tavily/search). Combos (owned_by:"combo") chain providers with auto-fallback.

Endpoint

POST $KEIROUTER_URL/v1/search

FieldRequiredNotes
model (or provider)yesfrom /v1/models/web (e.g. tavily or brave)
queryyessearch query
max_resultsnodefault 5
search_typenoweb (default) / news
country, language, time_range, domain_filternoprovider-dependent

Examples

bash
curl -X POST $KEIROUTER_URL/v1/search \
  -H "Authorization: Bearer $KEIROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tavily","query":"KeiRouter open source","max_results":5}'

JS:

js
const r = await fetch(`${process.env.KEIROUTER_URL}/v1/search`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.KEIROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "tavily", query: "latest LLM benchmarks", max_results: 10 }),
});
console.log(await r.json());

Response shape

json
{
  "provider": "tavily",
  "query": "KeiRouter open source",
  "results": [
    {
      "title": "...", "url": "https://...", "display_url": "github.com/...",
      "snippet": "...", "position": 1, "score": 0.92,
      "published_at": null, "favicon_url": null, "content": null,
      "metadata": { "author": null, "language": null, "source_type": null, "image_url": null },
      "citation": { "provider": "tavily", "retrieved_at": "2026-...", "rank": 1 }
    }
  ],
  "answer": null,
  "usage": { "queries_used": 1, "search_cost_usd": 0.008 },
  "metrics": { "response_time_ms": 850, "upstream_latency_ms": 700, "total_results_available": 12 },
  "errors": []
}

Provider quick reference

All accept query + max_results. Optional fields vary:

ProviderSupportsRequired extras
tavilycountry, domain_filter, news topic—
exadomain_filter (incl/excl), news category—
brave-searchcountry, language—
serpercountry, language, news endpoint—
perplexitycountry, language, domain_filter—
google-psecountry, language, time_range, offsetcx required (providerOptions)
searxnglanguage, time_rangeSelf-hosted, noAuth

Provider IS the model — "provider":"tavily" ≡ "model":"tavily".

© mydisha, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/keirouter-web-search of mydisha/keirouter.

Open the folder on GitHubat commit 3d8b702

Compare with similar skills

Keirouter Web Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Keirouter Web Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Keirouter Web Search this skillmydisha/keirouter147—~771Automated safety check: PassMIT
Web SearchEXboys/skilllite1702 repos~1kAutomated safety check: PassMIT
Web Search PlusCraftOS-dev/CraftBot3921 repos~2.4kAutomated safety check: NotesMIT
Web SearchOpenMinis/MinisSkills444—~984Automated safety check: PassMIT
9Router Web Searchdecolua/9router30k—~1kAutomated safety check: PassMIT
Mysearchskernelx/MySearch-Proxy159—~3kAutomated safety check: NotesNone

Similar skills

  • Web Search

    EXboys/skilllite

    Web search and content extraction with Tavily and Exa via inference.sh CLI.

    170 GitHub starsUsed in 2 repos~1k tokens
    Productivity & AutomationAuto-check passed

  • Web Search Plus

    CraftOS-dev/CraftBot

    Unified search skill with Intelligent Auto-Routing. An agent skill from CraftOS-dev/CraftBot.

    392 GitHub starsUsed in 1 repo~2.4k tokens
    Productivity & AutomationAuto-check: notes

  • Web Search

    OpenMinis/MinisSkills

    General web search skill that uses browser automation with multiple search engines and selects the priority chain based on search intent.

    444 GitHub stars~984 tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed

  • 9Router Web Search

    decolua/9router

    Runs web, news and public X searches through a 9Router gateway's search endpoint, choosing among providers such as Tavily, Exa, Brave and Perplexity.

    30k GitHub stars~1k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

  • Mysearch

    skernelx/MySearch-Proxy

    Install, verify, debug, and use MySearch MCP/Skill. An agent skill from skernelx/MySearch-Proxy.

    159 GitHub stars~3k tokensUpdated 6 mo ago
    Productivity & AutomationAuto-check: notes

  • Perplexity Improver

    ThomasHoussin/Claude-Book

    Improve chapter perplexity score by rewriting AI-suspect sentences.

    120 GitHub stars~959 tokensUpdated 8 mo ago
    Productivity & AutomationAuto-check passed

More from mydisha/keirouter

All 8 skills in this repo

  • Keirouter

    mydisha/keirouter

    Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

    147 GitHub stars~995 tokensUpdated 29 days ago
    Auto-check passed

  • Keirouter Chat

    mydisha/keirouter

    Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos.

    147 GitHub stars~859 tokensUpdated 29 days ago
    Auto-check passed

  • Keirouter Embeddings

    mydisha/keirouter

    Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity.

    147 GitHub stars~577 tokensUpdated 29 days ago
    Auto-check passed

  • Keirouter Image

    mydisha/keirouter

    Generate images via KeiRouter /v1/images/generations using OpenAI DALL-E / Gemini Imagen / FLUX / MiniMax / Stability AI / Fal.ai models.

    147 GitHub stars~691 tokensUpdated 29 days ago
    Auto-check passed

  • Keirouter Stt

    mydisha/keirouter

    Speech-to-text via KeiRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI models.

    147 GitHub stars~680 tokensUpdated 29 days ago
    Auto-check passed

  • Keirouter Tts

    mydisha/keirouter

    Text-to-speech via KeiRouter /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Inworld voices.

    147 GitHub stars~599 tokensUpdated 29 days ago
    Auto-check passed

Works with

Categories

Questions about Keirouter Web Search

What does Keirouter Web Search do?

Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity. Keirouter Web Search is an agent skill from mydisha/keirouter. Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity.

When should I use Keirouter Web Search?

Keirouter Web Search fits situations like: the user wants to search the web; look up information; query a search engine.

How do I install Keirouter Web Search in Claude Code?

Run `npx skills add mydisha/keirouter --skill keirouter-web-search -a claude-code`. Or copy the skill folder (skills/keirouter-web-search in mydisha/keirouter) into .claude/skills/keirouter-web-search in your project. Claude Code loads it when a task matches its description.

How do I install Keirouter Web Search in Codex?

Run `npx skills add mydisha/keirouter --skill keirouter-web-search -a codex`. Or copy the skill folder (skills/keirouter-web-search in mydisha/keirouter) into .agents/skills/keirouter-web-search in your project. Codex loads it when a task matches its description.

Can I use Keirouter Web Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mydisha/keirouter --skill keirouter-web-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/keirouter-web-search, .gemini/skills/keirouter-web-search, .github/skills/keirouter-web-search and .opencode/skills/keirouter-web-search in your project.

What does Keirouter Web Search need to run?

Going by SKILL.md and its folder, Keirouter Web Search needs the command-line tools its instructions call (curl and jq) and credentials named KEIROUTER_KEY. Our summary lists: A credential in KEIROUTER_KEY.

Does Keirouter Web Search access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Keirouter Web Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Keirouter Web Search use?

Keirouter Web Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Keirouter Web Search use?

About 771 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Keirouter Web Search?

Skills that share tags, products or a category with Keirouter Web Search: Web Search (EXboys/skilllite, 170 stars), Web Search Plus (CraftOS-dev/CraftBot, 392 stars), Web Search (OpenMinis/MinisSkills, 444 stars) and 9Router Web Search (decolua/9router, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Keirouter Web Search?

mydisha (a GitHub user) maintains it in mydisha/keirouter, which has 147 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 11, 2026.

Source: mydisha/keirouter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.