Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →loulanyue/deep-research
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution.
Passed 11 of 17 test cases with the skill, and 5 of 17 without it.
and 7 more in the full report
7 fixed7 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the targeted total range of unique web sources to gather across multi-source searches when performing a deep research report?
| Checked | Without skill | With skill |
|---|---|---|
| Aims for a total target volume of 15 to 30 unique sources across sub-question searches. | Missed | Passed |
The instructions your model reads when the skill loads.
Produce thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools.
At least one of:
firecrawl_search, firecrawl_scrape, firecrawl_crawlweb_search_exa, web_search_advanced_exa, crawling_exaBoth together give the best coverage. Configure in ~/.claude.json or ~/.codex/config.toml.
Ask 1-2 quick clarifying questions:
If the user says "just research it" — skip ahead with reasonable defaults.
Break the topic into 3-5 research sub-questions. Example:
test cases passed, vs 5 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.