Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vibeeval/iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
Passed 21 of 22 test cases with the skill, and 7 of 22 without it.
and 14 more in the full report
14 fixed7 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
After running iterative search cycles over a codebase to prepare context for an agent task, what minimum relevance score threshold determines whether a file is included in the final returned context set?
| Checked | Without skill | With skill |
|---|---|---|
| The returned context set only includes files with a relevance score of at least 0.7. | Missed | Passed |
The instructions your model reads when the skill loads.
Solves the "context problem" in multi-agent workflows where subagents don't know what context they need until they start working.
Subagents are spawned with limited context. They don't know:
Standard approaches fail:
A 4-phase loop that progressively refines context:
┌─────────────────────────────────────────────┐
│ │
│ ┌──────────┐ ┌──────────┐ │
│ │ DISPATCH │─────▶│ EVALUATE │ │
│ └──────────┘ └──────────┘ │
│ ▲ │ │
│ │ ▼ │
│ ┌──────────┐ ┌──────────┐ │
│ │ LOOP │◀─────│ REFINE │ │
│ └──────────┘ └──────────┘ │
│ │
│ Max 3 cycles, then proceed │
└─────────────────────────────────────────────┘
Initial broad query to gather candidate files:
test cases passed, vs 7 / 22 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.