product-competitor-intelligence

Research competitor products, SKUs, pricing, packaging, positioning, feature comparisons, product catalogs, category pages, retailer listings, marketplace…

npx skills add https://github.com/tavily-ai/use-case-skills --skill product-competitor-intelligence

Product Competitor Intelligence

Workflow

Use search and extract for product, pricing, SKU, feature, and competitor intelligence; use map or crawl for known catalogs and large competitor sites. Keep this skill focused on query construction, site navigation, source filtering, and synthesis; execution mechanics should come from companion endpoint skills.

Treat the guidance below as base guidance; adapt it to the user's request when appropriate.

  • Clarify the category, competitors, geography, target customer, price band, feature set, and desired output format.
  • Split broad questions into short subqueries under 400 characters: competitors, product category, pricing, alternatives, reviews, SKUs, specs, marketplaces, and recent launches.
  • Search for relevant competitors, product pages, category pages, retailer listings, pricing pages, reviews, docs, and official sources.
  • Filter by relevance score, domain trust, page type, and freshness before extracting.
  • Extract only selected pages that can support the requested comparison, table, or brief.
  • Use site mapping before broad collection on known competitor, retailer, manufacturer, marketplace, docs, or catalog domains.
  • Collect multiple pages only after choosing relevant path patterns and a tight scope.

Research Budget

  • Start with a small focused search set covering competitors, category, pricing, features/specs, reviews, or launches.
  • Extract only the strongest product, pricing, catalog, marketplace, docs, or review pages before drafting.
  • Add more searches only for named gaps, such as missing pricing, missing SKU evidence, or missing official competitor pages.
  • Do not use map unless a known competitor, retailer, manufacturer, marketplace, docs, or catalog domain needs URL discovery.
  • Do not use crawl until map has identified a narrow product, pricing, category, docs, or catalog section.

Capability Guidance

  • Use search for competitor discovery, pricing checks, feature comparisons, product claims, reviews, and launch signals.
  • Use extract on selected product, pricing, docs, catalog, marketplace, review, or changelog pages.
  • Use map when the domain is known but the relevant product, pricing, changelog, docs, category, or catalog pages are hard to find.
  • Use crawl for SKU/catalog discovery only after narrowing to relevant sections.
  • Use research only when the user asks for a market report rather than product-level evidence.

Query And Source Guidance

  • Include product category, buyer segment, geography, price band, SKU/model terms, competitor names, and feature terms in separate subqueries.
  • Prioritize official product pages, pricing pages, docs, catalogs, retailer listings, marketplaces, review sites, customer stories, changelogs, and credible launch coverage.
  • For known sites, look for paths such as products, pricing, category, collections, docs, blog, changelog, customers, or case studies.
  • Avoid irrelevant paths such as login, cart, checkout, account, admin, tag archives, and unrelated content.
  • Dedupe near-identical product pages, regional variants, and syndicated listings before synthesis.
  • Report failed or inaccessible sources when they affect pricing, specs, availability, or competitor coverage.

Output Template

Use this markdown structure and adapt columns to the user's request:

# Product And Competitor Intelligence: <category/company>

## Scope
- Category:
- Geography:
- Competitors covered:
- Source coverage limits:

## Product Comparison
| Product/SKU | Company | Category | Pricing/availability | Key features/specs | Positioning | Source |
| --- | --- | --- | --- | --- | --- | --- |

## Competitor Notes
### <Competitor>
- Positioning:
- Product/pricing evidence:
- Strengths:
- Gaps or uncertainty:

## Market Signals
- Launches or changes:
- Review/customer signals:
- Distribution or channel signals:

## Follow-Up Searches
- <query idea>

Keep each claim tied to a source. Mark pricing, availability, or specs as unavailable when they are not visible.

More skills from tavily-ai

research
tavily-ai
Comprehensive research on any topic with automatic source gathering, analysis, and citations. Conducts multi-source web research with explicit citations, ideal for comparisons, current events, market analysis, and detailed reports Offers three model options: mini for targeted single-topic research (~30s), pro for comprehensive multi-angle analysis (~60-120s), and auto for API-driven complexity detection Authenticates via OAuth through Tavily MCP server with automatic browser-based login on...
official
search
tavily-ai
Web search with LLM-optimized results, relevance scoring, and flexible filtering. Supports four search depth modes (ultra-fast, fast, basic, advanced) with configurable latency and relevance tradeoffs Includes domain filtering, time range constraints, date ranges, country boosting, and raw content extraction Returns results with title, URL, content snippet, and relevance score; optional image results and favicons Automatic OAuth authentication via Tavily MCP server or API key configuration;...
official
tavily-best-practices
tavily-ai
Web search API for LLMs with real-time data access, content extraction, site crawling, and AI-powered research. Five core methods: search() for web results, extract() for URL content, crawl() for site-wide extraction, map() for URL discovery, and research() for end-to-end AI synthesis Supports Python and JavaScript SDKs with async clients for parallel queries and configurable search depth (ultra-fast/fast/basic/advanced) Crawl method accepts semantic instructions to focus extraction on...
official
tavily-cli
tavily-ai
Web search, content extraction, site crawling, and deep research via Tavily CLI. Five command modes covering search, extraction, URL discovery, bulk crawling, and multi-source research with citations All commands support JSON output and file saving for structured, agentic workflows Escalation pattern guides you from simple search through extraction, mapping, crawling, to comprehensive research based on your needs Requires tavily-cli installation and API key authentication via tvly login
official
tavily-crawl
tavily-ai
Multi-page website crawler with semantic filtering and markdown export. Crawl entire site sections with depth and breadth control; filter by path regex, domain, or natural language instructions to focus results Save each page as local markdown files via --output-dir , or return structured JSON for agentic processing Use semantic instructions with chunk extraction to prevent context bloat when feeding results to LLMs; use full-page extraction for offline documentation downloads Supports...
official
tavily-dynamic-search
tavily-ai
Search the web, filter results, and extract content so that raw search data never enters your context window . Only your curated print() output comes back.
official
tavily-extract
tavily-ai
Extract clean markdown or text from up to 20 URLs, with JavaScript rendering and query-focused chunking support. Handles JavaScript-rendered pages with configurable extraction depth (basic for simple pages, advanced for dynamic SPAs and tables) Supports query-focused extraction to return only relevant content chunks instead of full pages Returns LLM-optimized markdown by default, with options for plain text format and structured JSON output Processes up to 20 URLs in a single call;...
official
tavily-map
tavily-ai
Fast URL discovery on websites without extracting content, ideal for finding specific pages on large sites. Returns structured lists of all URLs on a domain with configurable depth and breadth, regex path filtering, and natural language instructions for semantic filtering Supports depth control (1–5 levels), breadth limits per page, external link inclusion/exclusion, and domain filtering via regex patterns Designed as step 1 in a workflow: map to find the right page, then use extract or...
official