Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/Subagent-Driven Literature Review
Use parallel subagents for large-scale paper screening and deep dive analysis
Passed 15 of 20 test cases with the skill, and 8 of 20 without it.
and 14 more in the full report
9 fixed8 passed either way5 still failing1 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.
We are running 2 parallel subagents to query PubMed abstracts. What request delay should be assigned to each subagent to respect rate limits?
| Checked | Without skill | With skill |
|---|---|---|
| Sets a request delay of 1.0 second per PubMed request when running 2 parallel subagents. | Missed | Passed |
The instructions your model reads when the skill loads.
Core principle: Fresh subagent per batch + consolidation between batches = fast parallel screening with quality control
For large literature reviews (50+ papers), dispatching parallel or sequential subagents dramatically speeds up screening while maintaining quality through consolidation checkpoints.
Use subagent-driven approach when:
Do NOT use when:
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.