cancel-ralph
Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.
76
95%
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.
This is a focused, well-structured description that clearly communicates a single specific action with explicit trigger guidance. It includes good synonym coverage for natural user language. The only minor weakness is that it describes just one action, but given the narrow scope of the skill, this is appropriate.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a specific action ('Cancel an active Ralph Loop') but only describes one action without elaborating on what cancellation entails or any related capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (cancel an active Ralph Loop) and 'when' (when the user wants to stop, cancel, or abort a running ralph loop) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'stop', 'cancel', 'abort', 'running ralph loop'. Good coverage of synonyms a user might use when wanting to end a loop. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — cancelling a 'Ralph Loop' is a distinct, named concept unlikely to conflict with other skills. The triggers are tightly scoped to this particular operation. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%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 clearly defines when to trigger, what to do, and what to output. The conditional logic is explicit, the bash command is executable, and the structure is clean. No improvements needed for a skill of this scope.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. No unnecessary explanations of what cancellation means or how bash works. The skill is lean and assumes Claude's competence. | 3 / 3 |
Actionability | Provides a concrete executable bash command (`rm -rf .cursor/ralph`), specifies the exact file to check and field to read (`iteration:` in `scratchpad.md`), and gives exact output messages to use. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose skill with a clear conditional workflow (file exists vs. doesn't exist). The steps are unambiguous and well-sequenced. For a non-destructive cancellation task (removing internal state files, not user data), the workflow is appropriately complete. | 3 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with no need for external references, the content is well-organized with clear sections (Trigger, Workflow, Output) and doesn't need additional files. | 3 / 3 |
Total | 12 / 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.