Install any skill in seconds. Free to start, no credit card required.
Get Started Free →feiskyer/deep-research
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregate results into a polished report file.
Passed 9 of 15 test cases with the skill, and 7 of 15 without it.
and 5 more in the full report
6 fixed8 passed either way7 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
After finishing sub-tasks for a research run on synthetic biology, invoke the aggregated report generation script `scripts/aggregate.py`. What file is produced by default?
| Checked | Without skill | With skill |
|---|---|---|
| Generates aggregated_raw.md in the research directory | Missed | Passed |
The instructions your model reads when the skill loads.
主控负责界定问题、拆分、核验与综合;子任务负责互不重叠的采集或局部分析。完成标准是用户需要的报告和证据覆盖,不是子进程退出或材料聚合成功。
--model,不覆盖无关配置。workspace-write;只有确实需要 shell 网络访问时才启用 runner 的 --network。--dangerously-bypass-approvals-and-sandbox。.research/<name>/ 目录。准备运行子任务时读 references/runner.md,其中包含目录、manifest、命令与恢复约束。两个脚本均只依赖 Python 标准库;--help 给出参数真源。
results.json、子报告和关键原始来源。失败、空输出、缺失引用或未覆盖的问题仍是未完成;按 runner 参考中的恢复约束有限重试,不重跑已验证成功的任务。缺少权限或需要扩大范围时停止相应操作并说明阻塞。aggregate.py 整理内部材料,再综合为 polished_report.md(用户指定位置优先)。消除重复、核对关键数据、区分来源冲突和证据强弱;aggregated_raw.md 不是成品。交付报告绝对路径、关键结论和剩余缺口,说明实际使用的权限例外。必要证据仍缺失时,报告已完成范围、具体阻塞及恢复条件,不把部分材料称为完整报告;不要发送内部 Prompt 或调度日志充当成品。
test cases passed, vs 7 / 15 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.