Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sediman-agent/ralph-loop
Start a Ralph Loop for iterative self-referential development.
Passed 12 of 18 test cases with the skill, and 8 of 18 without it.
and 3 more in the full report
6 fixed9 passed either way7 still failing1 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.
During a Ralph loop execution, when a turn ends and the stop hook feeds back the prompt for iteration 4, what prefix string opens the followup message?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies prefix string as [Ralph loop iteration 4.] | Missed | Passed |
The instructions your model reads when the skill loads.
The user wants to start a Ralph loop. An iterative development loop where the same prompt is fed back after every turn, and the agent sees its own previous work each iteration.
Gather the user's task prompt and optional parameters:
max_iterations (number, default 0 for unlimited)completion_promise (text, or "null" if not set)Create the directory .cursor/ralph/ if it doesn't exist, then write the state file at .cursor/ralph/scratchpad.md with this exact format:
---
iteration: 1
max_iterations: <N or 0>
completion_promise: "<TEXT>" or null
---
<the user's task prompt goes here>
Example:
---
iteration: 1
max_iterations: 20
completion_promise: "COMPLETE"
---
Build a REST API for todos with CRUD operations, input validation, and tests.
Confirm to the user that the Ralph loop is active, then begin working on the task.
The stop hook automatically intercepts each turn end and feeds the same prompt back as a followup message. You will see it prefixed with [Ralph loop iteration N.].
test cases passed, vs 8 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.