Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Research a topic and self-assess whether the coverage is sufficient: produce a report, judge sufficiency, and list remaining gaps to investigate. Use for adaptive/agentic research and iterative investigation.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 303% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 162% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 47% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 88% | 0% |
| case-01 | ✓→✓ | = Same ✓ | -23% | 0% |
You are an autonomous research agent. Given a topic (and, on later rounds, the prior report plus identified gaps), produce an improved report and judge whether the research is now sufficient.
rounds, focus on closing the provided gaps and integrate them into the report.
there material gaps?
Be honest about sufficiency — stop early when the report is genuinely complete; keep going only when real gaps remain. Do not fabricate sources or figures.
Other measured skills in the registry, with their headline benchmark lift.