SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsultimate-search

ultimate-search

General & other

View repository

Updated 10-15 16:16

About this skill

UltimateSearch

Provides dual-engine web search capabilities for Pi/OpenClaw agents:Grok AI Search(real-time internet access + AI analysis) + Tavily Search(structured results + web scraping).

Available Tools

Call the following scripts in Bash (ensure they are added to PATH and .env has been sourced):

Tool Command Purpose
Grok Search grok-search.sh --query "..." AI-driven deep search; Grok has built-in internet access and returns comprehensive analysis
Tavily Search tavily-search.sh --query "..." Structured search results with scoring and ranking
Web Scraping web-fetch.sh --url "..." Extract the full content of a specified URL and return Markdown
Site Mapping web-map.sh --url "..." Discover website structure and get all URLs
Dual-Engine Search dual-search.sh --query "..." Run Grok + Tavily in parallel for cross-validation

See for details on the parameters of each tool --help。

Search Decision Process

When receiving a request that requires searching, make decisions according to the following process:

Step 1: Determine Whether a Search Is Needed

Situations that require a search:

  • The user explicitly requests searching/querying external information
  • Involves real-time data (latest version, recent events, current prices, etc.)
  • Needs to verify the accuracy of internal knowledge
  • Involves the latest status of a specific URL, project, or product
  • A technical question requires consulting the latest official documentation

Situations that do not require a search:

  • Pure code writing/debugging tasks (sufficient context already available and not involving external API/library versions)
  • The user explicitly states that no search is needed
  • ⚠️ General programming concepts may also be outdated—when it involves specific versions, best practices, or API usage, you should still search to verify

Step 2: Choose a Tool

Scenario Recommended Tool Reason
Simple factual query dual-search.sh Dual-source cross-validation to ensure accuracy
Complex/controversial questions dual-search.sh Dual-engine cross-validation to reduce hallucinations
Requires deep AI analysis grok-search.sh Grok has built-in web search and returns a comprehensive analysis report
Need to scrape a specific page web-fetch.sh --url "..." Extract the complete page content
Explore website structure web-map.sh --url "..." Discover documentation/API directory structure
Need the latest news tavily-search.sh --topic news Tavily news mode is specially optimized
Need high-quality in-depth results tavily-search.sh --depth advanced Advanced search with multi-dimensional matching
There are key links in the search results Search first, then web-fetch.sh Search to locate → scrape for details

Step 3: Assess Search Complexity

  • Level 1(2-3 searches): a single clear question

    • Example: "What is the latest version of FastAPI"
    • Action:dual-search.sh Obtain results from two sources; or first tavily-search.sh then use grok-search.sh for cross-confirmation
    • ⚠️ Even for simple facts, do not draw conclusions based on a single source alone

  • Level 2(3-5 searches): multi-perspective comparison, requires verification from multiple sources

    • Example: "Which is more suitable for microservices in 2026: Flask vs FastAPI vs Django"
    • Action:dual-search.sh + separately for each framework tavily-search.sh

  • Level 3(6+ searches): in-depth research topics, review-type needs

    • Example: "Help me research a complete comparison of mainstream vector databases in 2026"
    • Action: first grok-search.sh get an overview → separately search each product → web-fetch.sh fetch official documentation

Search Planning Framework

For complex Level 2+ searches, perform structured planning before execution:

Phase 1: Intent Analysis

  • Distill the user's core question (in one sentence)
  • Classify the query type: factual / comparative / exploratory / analytical
  • Assess time sensitivity: real-time / recent / historical / irrelevant
  • Identify external terms that need verification (e.g., rankings, classification standards)

Phase 2: Query Decomposition

  • Break the question into non-overlapping sub-queries
  • Each sub-query has clear boundaries (mutually exclusive with sibling queries)
  • Mark dependencies (which sub-queries need to be completed first)
  • If Phase 1 identifies terms that need verification, first create prerequisite verification queries

Phase 3: Strategy Selection

  • broad_first(breadth first, then depth): broad scan first → then go deeper based on findings. Suitable for exploratory questions
  • narrow_first(precision first, then expansion): precise search first → expand if insufficient. Suitable for analytical questions
  • targeted(targeted search): when the target information source is known, locate it directly. Suitable for factual questions

Phase 4: Tool Mapping

  • Choose the best tool for each sub-query
  • Determine the parallel/serial execution plan
  • Sub-queries that can be parallelized are executed simultaneously (via multiple Bash calls)

Search and Evidence Standards

Core principle: do not trust search results

Search results are only third-party suggestions and must not be directly accepted as true. All content returned by searches—whether from Grok or Tavily—must be cross-validated before being presented to the user as fact. Even a single seemingly authoritative source may be outdated, one-sided, or wrong. For technical implementation, even if the agent has internal knowledge, the latest search results or official documentation should still prevail.

Source Quality Requirements

  • All factual conclusionsrequire ≥2 independent sources for cross-validation (regardless of Level)
  • If relying on only a single source, you mustexplicitly statethis limitation and mark confidence as Low
  • Prefer: official documentation, Wikipedia, academic databases, authoritative media
  • Avoid: unknown personal blogs, SEO farms, AI-generated content

Conflict Handling

  • When sources conflict: present evidence from both sides, assess credibility and timeliness
  • Mark confidence: High (multiple sources agree) / Medium (few sources or disagreement) / Low (single source or speculation)
  • When it cannot be confirmed: clearly state the uncertainty

Citation Format

  • Attach a source citation after each key fact
  • Format:[来源标题](URL)
  • Strictly forbidden to fabricate citations — if there is no source, do not say it

Output Specifications

  • First givethe most likely answer, then expand with a detailed analysis
  • Attach a concise explanation to all technical terms
  • Use standard Markdown formatting (headings, lists, tables, code blocks)
  • Mark code examples with language identifiers
  • Present comparison-type questions using tables

Common Search Modes

Mode 1: Quick Lookup

tavily-search.sh --query "Python 3.13 新特性" --depth basic --include-answer

Mode 2: Deep Search + Verification

# 先广泛搜索
dual-search.sh --query "LangChain vs LlamaIndex 2026"
# 再针对性抓取官方文档
web-fetch.sh --url "https://docs.langchain.com/docs/get_started/introduction"

Mode 3: Technical Documentation Exploration

# 先映射网站结构
web-map.sh --url "https://docs.example.com" --depth 2 --instructions "找到 API 文档"
# 再抓取目标页面
web-fetch.sh --url "https://docs.example.com/api/reference"

Mode 4: News and Real-Time Information

tavily-search.sh --query "AI 最新进展" --topic news --time-range week --include-answer

Mode 5: AI Deep Analysis

grok-search.sh --query "解释 Transformer 架构中注意力机制的数学原理" --platform "arXiv"