Industry Signal Scout

Searches web sources with Tavily and Brave to filter noise and find authoritative evidence.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/sparkst/sparkry-claude-skills --skill industry-signal-scout-sparkst
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Industry Signal Scout
Source: https://github.com/sparkst/sparkry-claude-skills/tree/main/plugins/research-workflow/skills/research/industry-scout
Command: npx skills add https://github.com/sparkst/sparkry-claude-skills --skill industry-signal-scout-sparkst

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Web research is polluted by SEO spam, AI-generated content farms, and duplicate articles, making it hard to find canonical, primary, and independent sources for market data, technical documentation, and competitive intelligence. ## Core Features & Use Cases - Targeted Query Construction: Builds domain-specific search queries with site filters, freshness constraints, and noise-exclusion patterns for market data, technical specs, competitive intelligence, and customer insights. - Parallel Multi-Tool Search: Runs Tavily advanced search and Brave web search in parallel, then merges, deduplicates, and filters results by source tier. - Structured Source Output: Produces a sources.json file with metadata (author, date, excerpt, preliminary tier, relevance score) plus search quality metrics. - Use Case: When researching the AI coding tools market, use this Skill to query Gartner, IDC, and SEC filings while excluding affiliate review spam, yielding a curated list of Tier-1 sources ready for formal evaluation. ## Quick Start Use the industry signal scout to find authoritative sources on AI coding agents market size for 2025, filtering out SEO spam and content farms.

Frequently Asked Questions about Industry Signal Scout

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I filter out SEO spam and AI-generated content from web search results?▼

Use exclusion patterns like -inurl:review, -inurl:best, and -site:quora.com in queries, then check red flags such as missing authors, generic domain names, and duplicate text. Prefer domains with editorial standards and named, credentialed authors.

Tavily vs Brave Search: which should I use for research?▼

Use Tavily for deep research with advanced search depth, domain targeting, and freshness filters. Use Brave for broad discovery and news when target domains are unknown. Running both in parallel and merging results gives the widest high-quality coverage.

How do I find canonical sources for market data and technical documentation?▼

Target Tier-1 domains directly in queries: gartner.com and idc.com for market data, sec.gov for financials, arxiv.org for AI research, and official vendor docs or IETF RFCs for technical specifications. Site-restricted queries surface these primary sources.

What happens when Tavily hits rate limits during research?▼

Apply exponential backoff on 429 errors by waiting 2^retry_count seconds before retrying. If Tavily fails due to network errors, fall back to Brave Search so the research workflow continues without losing coverage.

What are the limitations of automated source discovery?▼

Preliminary tier classification is based only on domain reputation, not content quality, so a formal source evaluation step is still required. Generic queries and first-page-only results also miss signal, so specific queries and deep search are necessary.