2.5k
GitHub Stars
2
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill openclaw/skills --skill web-searcher- _meta.json280 B
- SKILL.md2.6 KB
Overview
This skill is an autonomous web research agent that performs multi-step searches, follows links, extracts content, and synthesizes findings into structured reports. It is built to handle complex research requests that require cross-referencing multiple sources and producing verifiable summaries. Use it when you need consolidated, cited information from across the web rather than a single search result.
How this skill works
The agent parses your query into focused sub-queries, runs up to a limited number of targeted web searches, and selects promising pages for deep fetches. It prioritizes primary and recent sources, extracts content, cross-references claims, flags contradictions, and synthesizes results into a report with citations, confidence levels, and identified gaps. It enforces limits (max ~10 searches, max ~5 deep fetches) to stay efficient and avoid rate limits.
When to use it
- Research topics requiring multi-source verification
- Compare products, services, or market options across sources
- Compile lists, datasets, or directories from the live web
- Produce profiles for people or companies with cross-referenced facts
- Gather time-sensitive or evolving information that needs date checks
Best practices
- Provide a clear, specific query and any preferred sources or date ranges
- Indicate desired depth (brief summary vs full investigative report) to control search/fetch limits
- Ask to break very large tasks into sub-tasks to keep reports focused and fast
- Request citation format you prefer (inline bullets, numbered list, or markdown) for easier verification
- Specify freshness requirement (day/week/month/year) for time-sensitive topics
Example use cases
- Market comparison: evaluate 3 competing SaaS tools, gather pricing, features, and recent reviews
- Competitive intelligence: compile public information on a company’s product launches, funding, and news mentions
- Technical research: find official docs and community guides to synthesize a step-by-step how-to
- People research: build a short profile combining LinkedIn, company pages, and news coverage
- List compilation: crawl and consolidate top resources, datasets, or regulatory references for a topic
FAQ
I start with up to 3 targeted searches, reassess, and will not exceed about 10 searches total. I deep-fetch up to 5 pages to keep work focused.
Will you include links so I can verify claims?
Yes. Every report includes source URLs for key findings and a numbered sources section so you can inspect originals.
Can you handle very large research tasks?
For massive topics I recommend splitting into sub-tasks or spawning sub-agents; I’ll suggest a breakdown if the request is too big.