From claude-superskills
Performs structured multi-step web research using native WebSearch/WebFetch tools without external APIs. For market analysis, competitive landscaping, literature reviews, and technical due diligence.
npx claudepluginhub ericgandrade/claude-superskills --plugin claude-superskillsThis skill uses the workspace's default tool permissions.
Run structured, multi-step research with evidence-first synthesis.
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.
Performs multi-source web research using firecrawl and exa MCPs, synthesizes findings into cited reports. For deep dives, competitive analysis, technology evaluation, or due diligence.
Provides structured research methodology using query design, source vetting, verification, and synthesis phases for competitive analysis, market scans, historical investigations, and trend research.
Share bugs, ideas, or general feedback.
Run structured, multi-step research with evidence-first synthesis.
This skill is designed to work without Google/Gemini API or any paid provider setup.
Use this skill when:
WebSearch, WebFetch)No external API key is required.
Display a progress gauge at each research phase:
[████░░░░░░░░░░░░░░░░] 20% — Phase 1/5: Defining Objective & Scope
[████████░░░░░░░░░░░░] 40% — Phase 2/5: Collecting Sources
[████████████░░░░░░░░] 60% — Phase 3/5: Deep Analysis & Synthesis
[████████████████░░░░] 80% — Phase 4/5: Drafting Output
[████████████████████] 100% — Phase 5/5: Quality Review & Citations
Do NOT run searches sequentially. Launch one ResearchScout agent per query variant simultaneously in a single block.
| Agent | Query Type |
|---|---|
ResearchScout-Broad | Wide-scope 2–3 keyword query |
ResearchScout-Narrow | Specific 5+ keyword query |
ResearchScout-Comparative | "X vs Y" or "comparison of" framing |
ResearchScout-Opposing | Contrarian or critical viewpoints |
ResearchScout-Primary | Official docs, papers, government sources |
ResearchScout-Recent | Date-filtered to last 12 months |
Each agent prompt begins with:
# ResearchScout — Targeted Web Research Agent
Role: Execute a single search query using WebSearch/WebFetch, collect top results with URLs and key findings, return structured results.
Wait for all ResearchScout agents to complete. Deduplicate results by URL. Then proceed to synthesis/triangulation phase.
Choose one based on request:
| Error | Likely Cause | Action |
|---|---|---|
| WebSearch returns no results | Query too specific, misspelled, or topic very niche | Broaden query, try alternate phrasing, report low-coverage finding |
| WebFetch times out or blocked | Site is down, bot-blocking, or paywalled | Skip that source, note it as inaccessible, continue with other sources |
| Insufficient sources found | Topic has limited public information | Report coverage gaps; recommend user provide domain-specific sources |
| Conflicting information across sources | Different sources cite different facts | Flag the conflict explicitly; present both sides with sources |
| Query too broad | Research question covers too many sub-topics | Ask user to narrow the scope or prioritize specific dimensions |
| Paywalled content | Article requires subscription | Note the source as paywalled; use abstract/preview if available |