Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →wasabeef/專用代理自主執行調查分析任務
專用代理自主執行調查分析任務。「用 Task 調查」「調查一下」「分析一下」「搜尋」等觸發。
Passed 13 of 21 test cases with the skill, and 11 of 21 without it.
and 4 more in the full report
4 fixed10 passed either way7 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am trying to decide between Event Sourcing and CQRS for our high-throughput financial ledger. I don't need code searches or log parsing, just deep architectural evaluation of existing trade-offs. What mechanism is best suited for this structured conceptual judgment?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends ultrathink or sequential-thinking tools rather than an autonomous search agent | Missed | Passed |
| Provides an architectural trade-off evaluation between Event Sourcing and CQRS | Passed | Passed |
The instructions your model reads when the skill loads.
啟動專用代理，自主執行復杂的搜索、調查和分析任務。通過組合多個工具進行大規模資訊處理，重視上下文效率。
# 向 Claude 請求 Task
「用 Task 調查[课題]」
自主執行
高效資訊處理
質量保證
# 復杂代碼庫調查
「用 Task 調查這個功能在哪些文件中實現」
# 大規模文件搜索
「用 Task 識別配置文件的不一致」
test cases passed, vs 11 / 21 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.