ralph-loop
Start a Ralph Loop for iterative self-referential development. Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated autonomous iteration on a task until completion.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has strong trigger terms, explicit 'Use when' guidance, and a highly distinctive skill name that minimizes conflict risk. Its main weakness is that the actual capabilities are somewhat vague—'iterative self-referential development' and 'repeated autonomous iteration on a task' don't clearly explain what concrete actions the skill performs or what outputs it produces.
Suggestions
Add specific concrete actions describing what happens during a Ralph Loop iteration (e.g., 'Executes a task, evaluates output, refines approach, and repeats until quality criteria are met').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('iterative self-referential development') and one action ('Start a Ralph Loop'), but doesn't list multiple concrete actions or explain what the loop actually does beyond vague 'iterative self-referential development' and 'repeated autonomous iteration on a task until completion'. | 2 / 3 |
Completeness | Clearly answers both 'what' (start a Ralph Loop for iterative self-referential development) and 'when' (explicit 'Use when' clause with multiple trigger scenarios: run a ralph loop, start an iterative loop, repeated autonomous iteration until completion). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'ralph loop', 'iterative loop', 'repeated autonomous iteration', 'until completion'. These cover the likely phrases a user would say when requesting this specific functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The term 'Ralph Loop' is highly distinctive and unlikely to conflict with other skills. The specific naming convention creates a clear niche that wouldn't be confused with general iteration or looping constructs. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides clear, actionable instructions for setting up a Ralph loop. Its main weakness is the lack of validation or error-recovery steps—there's no checkpoint to verify the scratchpad file was written correctly or guidance on handling edge cases like a missing stop hook. Overall it's a strong skill that efficiently communicates a novel workflow.
Suggestions
Add a validation step after writing the scratchpad file (e.g., 'Read back `.cursor/ralph/scratchpad.md` and verify the YAML frontmatter parses correctly before proceeding').
Include brief error-recovery guidance for when the stop hook doesn't trigger or the loop appears stuck.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what iterative loops are or how agents work—it assumes Claude's competence and focuses only on the specific file format, workflow, and guardrails unique to this skill. | 3 / 3 |
Actionability | Provides the exact file path, exact markdown format with YAML frontmatter, a concrete example, and specific guardrails including the promise tag syntax. Everything needed to execute is present and copy-paste ready. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced (gather params → create file → confirm → begin work), but there's no validation checkpoint for the scratchpad file format, no error recovery if the file write fails, and no explicit guidance on what to do if the stop hook doesn't fire or the loop gets stuck. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single focused task, the content is well-organized into clear sections (Trigger, Workflow, Guardrails, Output) with no need for external references. The structure is appropriate for the complexity. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cursor/plugins
- Commit
b8f2564
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.