live-research
SkillProduce a deep, multi-source, cited research brief on a topic from live web data using Bright Data's Discover API (intent-ranked web search + parsed page content). Use when the user wants "live research", to "research <topic> deeply", "research the latest on", "write a report on", "give me a briefin
Install
git clone https://github.com/brightdata/skills.git ~/.claude/skills/live-researchWhat is live-research?
Produce a deep, multi-source, cited research brief on a topic from live web data using Bright Data's Discover API (intent-ranked web search + parsed page content). Use when the user wants "live research", to "research <topic> deeply", "research the latest on", "write a report on", "give me a briefing / literature review / market scan", "find and synthesize everything about", or otherwise wants a synthesized, source-grounded answer rather than a list of links. Decomposes the question into multiple intent-ranked Discover queries, pulls page content, deduplicates and ranks by relevance, then synthesizes a structured brief with inline citations. Built on the `discover-api` skill. For competitor-specific intel use `competitive-intel`; for social/brand sentiment use `brand-listening`; for a retrieval *system* (not a one-off report) use `rag-pipeline`.
What this can do
Capabilities declared in this component's own frontmatter — not inferred.
Inherit all session tools
Declares no tool restrictions — inherits every session tool
~214 tokens of context used while enabled, before you invoke anything
Documentation
README · ~4 min readBright Data — Live Research
Turn one research question into a cited, synthesized brief by fanning out
intent-ranked Discover queries, reading the best sources, and writing up findings
with inline citations. This is a workflow on top of the discover-api skill
— read that for the API mechanics, modes, and parameters.
Use this when the deliverable is understanding (a report/briefing), not a link
list (that's search/discover-api) and not a standing system (that's
rag-pipeline).
Setup gate
Discover must be reachable. Quick check (CLI path):
Reviews
Log in to leave a review.
No reviews yet — be the first.
Explore related
Other things in this space — across every part of the ecosystem, not just skills.
Skillssimilar to this one
All skills →build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development
32.8K stars
build-mcp-app
This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "app
32.8K stars
agent-skills
Vercel's official collection of agent skills
29.6K stars
Plugins
All plugins →mcp-tunnels
Connect Claude to a private MCP server through an Anthropic MCP tunnel. The /create-docker-mcp-tunnel command drives the Docker Compose quickstart end to end: certificates, proxy config, cloudflared, and a verifiable sample server.
32.9K stars
mcp-server-dev
Skills for designing and building MCP servers that work seamlessly with Claude. Guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.
32.9K stars
exa
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers, and more.
4.8K stars
MCP Servers
All mcp servers →Subagents
All subagents →agentic-flow
Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it lets you take what you've created and deploy fully hosted agents for real business purposes. Use Claude Code to get the agent working, then deploy it in your favorite cloud.
783 stars
deploy-guardian
Deployment safety specialist for blast-radius analysis, downstream dependency checks, and cross-team coordination planning.
1 stars
pipeline_orchestrator_agent
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases
Commands
All commands →create-docker-mcp-tunnel
Stand up an Anthropic MCP tunnel locally with Docker Compose so Claude can call a private MCP server (manual-credentials quickstart).
32.8K stars
setup-devops-agent
Set up the AWS DevOps Agent MCP connection
2.2K stars
quick-build
Creates a WordPress block theme from a description with an index.html landing page template and deploys it to a local Studio site