Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →loulanyue/iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
Passed 19 of 21 test cases with the skill, and 14 of 21 without it.
and 3 more in the full report
5 fixed15 passed either way2 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.
When scoring candidate files during context evaluation, what score range represents medium relevance (files that contain relevant patterns or types but do not directly implement the feature)?
| Checked | Without skill | With skill |
|---|---|---|
| Defines the medium relevance score range as 0.5 to 0.7. | Missed | Passed |
The instructions your model reads when the skill loads.
解決多 agent 工作流程中的「上下文問題」，其中子 agents 在開始工作之前不知道需要什麼上下文。
子 agents 以有限上下文產生。它們不知道：
標準方法失敗：
一個漸進精煉上下文的 4 階段循環：
┌─────────────────────────────────────────────┐
│ │
│ ┌──────────┐ ┌──────────┐ │
│ │ DISPATCH │─────▶│ EVALUATE │ │
│ └──────────┘ └──────────┘ │
│ ▲ │ │
│ │ ▼ │
│ ┌──────────┐ ┌──────────┐ │
│ │ LOOP │◀─────│ REFINE │ │
│ └──────────┘ └──────────┘ │
│ │
│ 最多 3 個循環，然後繼續 │
└─────────────────────────────────────────────┘
初始廣泛查詢以收集候選檔案：
test cases passed, vs 14 / 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.