Stats
Actions
Tags
Multi-tool research methodology with automatic depth routing. Routes queries through free tools first (web search, page scraping), escalates to paid tools only when needed (Perplexity, Gemini Deep Research). Includes caching, source verification, and structured output. Use when researching companies, topics, markets, competitors, or any question requiring web information. Triggers: research, look into, find out about, investigate, what do we know about, deep research, company research, market analysis.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-blueprint-skills:research-agentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A multi-tool research methodology with automatic depth routing. Start cheap,
A multi-tool research methodology with automatic depth routing. Start cheap, escalate when needed, cache everything, cite every claim.
Assess the query and pick the right tool. Always start with the cheapest tool that can plausibly answer.
| Depth | Tool | When to use | Speed | Cost |
|---|---|---|---|---|
| Quick | WebSearch (native) | Single fact, recent news, quick lookup | Seconds | Free |
| Scrape | WebFetch (native) | Read a specific URL the user provides | Seconds | Free |
| Better scrape | Firecrawl (MCP) | JS-heavy pages, structured extraction, WebFetch fails | Seconds | ~$0.01 |
| Broader | Brave Search (MCP) | WebSearch results thin, need more results or domain filtering | Seconds | Free tier |
| Medium | Perplexity Ask (MCP) | AI-synthesized answer with citations, multi-faceted questions | 5-10s | Small |
| Deep | Perplexity Research (MCP) | Comprehensive multi-source investigation, company profiles | ~30s | Moderate |
| Ultra-deep | Gemini Deep Research (API) | Market landscapes at extreme breadth, when Perplexity is thin | 10-20 min | $2-5 |
Use Quick (WebSearch/Brave) when:
Use Medium (Perplexity Ask) when:
Use Deep (Perplexity Research) when:
Escalation pattern: Start with the cheapest tool that can plausibly answer. If results are thin, escalate one level. Tell the user before escalating to paid tiers.
After the primary research call, run targeted follow-ups to fill gaps. These are cheap/free and take about a minute total. Run as many in parallel as possible.
| Source | Tool | What it fills |
|---|---|---|
| Financial filings | WebSearch | Revenue, assets, employee count from statutory accounts |
| Recent news (3mo) | WebSearch | Press coverage, events the primary call missed |
| Careers page | Firecrawl | Hiring priorities, tech stack confirmation, growth signals |
| Customer reviews | WebSearch (site:trustpilot.com, g2.com) | Customer sentiment, pain points |
| Competitive moves | WebSearch per competitor | What competitors are doing |
When to run supplementals:
How to use findings: Merge into the primary output organized by section (not by source). Flag anything that contradicts the primary research. Note gaps that remain even after supplementals.
Cache research results to avoid redundant queries.
Filename: {slugified-subject}-{date}.md
# Research: {Subject}
Researched: {date}
Depth: {quick|medium|deep}
Tools used: {list}
## Findings
{content}
## Sources
- {url} -- {description}
## Gaps
- {anything still unknown}
| Depth | Fresh for |
|---|---|
| Quick | 24 hours |
| Medium | 3 days |
| Deep | 7 days |
| Ultra-deep | 14 days |
Before starting research, check if a cache file exists. If fresh, use it. If stale, re-research (but reference old results for comparison).
Present findings in a clean, scannable format:
## Research: {Subject}
Depth: {level} | Sources: {count} | {date}
### Key Findings
- {finding 1} -- source: {url}
- {finding 2} -- source: {url}
### Details
{structured content organized by relevance}
### Gaps
- {anything you couldn't find or verify}
Lead with what matters most. Don't pad.
| Issue | Fix |
|---|---|
| Thin WebSearch results | Try different query terms, escalate to Brave/Perplexity |
| Firecrawl returns empty | Page may be JS-rendered. Try with waitFor: 5000. Or try firecrawl_map first. |
| Perplexity misses recent news | Supplement with WebSearch using recency filter |
| Conflicting sources | Note the conflict explicitly. Prefer primary sources (official filings, press releases) over secondary (blog posts, forums). |
This skill references several MCP servers. Use what you have available:
The methodology is tool-agnostic. The routing table is a recommendation, not a requirement. Use the best tools you have access to.
Built by Agent Blueprint -- AI advisory for enterprise agent deployment.
npx claudepluginhub agent-blueprint/agent-blueprint-skills --plugin agent-blueprint-skillsMulti-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution.
Conducts multi-source web research with firecrawl and exa MCPs: searches, scrapes pages, synthesizes cited reports. For deep dives, competitive analysis, tech evaluations, or due diligence.
Multi-source deep research using firecrawl and exa MCPs to search, scrape, and synthesize cited reports with source attribution. Use for in-depth topic exploration.