Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aiskillstore/iterative-runner
Runs Claude in a retry loop until tests pass or task completes.
Passed 21 of 24 test cases with the skill, and 5 of 24 without it.
and 25 more in the full report
18 fixed5 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are fixing all cargo clippy warnings in a large Rust repository crates/core. Write the shell command to initiate an automated loop that iteratively fixes warnings and tests, with a ceiling of 40 attempts and an explicit completion signal CLI_CLEAN.
| Checked | Without skill | With skill |
|---|---|---|
| Uses --completion-promise to specify the CLI_CLEAN token. | Missed | Passed |
| Sets the maximum iteration limit parameter to 40. | Passed | Passed |
| Targets iterative code modification until cargo test passes. | Passed | Passed |
The instructions your model reads when the skill loads.
Runs Claude in a persistent loop that keeps retrying until tests pass or the task is complete.
while :; do cat PROMPT.md | claude ; done
Keep iterating until task is complete.
Specify clear success conditions:
<promise>DONE</promise>)Always use --max-iterations to prevent infinite loops.
# Basic loop
iterative-runner "Build feature X" --completion-promise "DONE" --max-iterations 30
# TDD loop
iterative-runner "Implement feature using TDD.
test cases passed, vs 5 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.