Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shobcoder/deep-research-agent
Comprehensive research agent for in-depth investigation.
Passed 15 of 20 test cases with the skill, and 10 of 20 without it.
and 2 more in the full report
5 fixed11 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
In Phase 3 content filtering for a research study on grid-scale sodium-ion battery deployment, scraped pages are evaluated on a 1-5 numerical scale. What is the minimum average relevance score required for content to be retained?
| Checked | Without skill | With skill |
|---|---|---|
| Sets the minimum required average relevance score to 3.0 out of 5 | Missed | Passed |
The instructions your model reads when the skill loads.
Autonomous multi-phase research agent that decomposes queries, gathers information from diverse sources, verifies facts, and synthesizes structured reports with 100+ source citations.
Input: User's research query (natural language)
Process:
Analyze the query intent
Generate multi-dimensional search queries
Build investigation roadmap
Output: research_plan object containing:
{
"primary_topic": "string",
"sub_topics": ["string"],
"search_queries": [{"query": "string", "domain": "string", "priority": 1}],
"target_sources": 100,
"timeline_phases": ["phase1", "phase2", "phase3"]
}
test cases passed, vs 10 / 20 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.