Name: ralph-loop-help
Rating: 72 (1 reviews)
Author: cursor

ralph-loop-help

Explain the Ralph Loop plugin, how it works, and available skills. Use when the user asks for help with ralph loop, wants to understand the technique, or needs usage examples.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured, actionable, and clearly sequenced for a single-purpose help skill. The only weakness is mild redundancy between the two iteration explanations, which affects conciseness.

Suggestions

Collapse the 'Each iteration' (6-step) and 'How it works' (5-step) lists into a single explanation to remove the overlap and tighten token use.

Consider noting where the state file (.cursor/ralph/scratchpad.md) lives only once rather than restating the stop-hook mechanism twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concepts Claude already knows, but the six-step 'Each iteration' list and the five-step 'How it works' list under 'Starting a Ralph Loop' overlap substantially, which could be tightened.	2 / 3
Actionability	Concrete, copy-paste-ready guidance is given: a startup command with flags ('--max-iterations', '--completion-promise'), the '<promise>TASK COMPLETE</promise>' tag, and a cancel instruction, matching the level-3 anchor.	3 / 3
Workflow Clarity	The loop lifecycle (start, iterate, detect promise or hit max, cancel) is clearly sequenced; as an explanatory skill with no destructive batch operation, the simple-skill allowance applies and the single flow is unambiguous.	3 / 3
Progressive Disclosure	A single, well-organized file with clearly labeled sections (What is, Starting, Cancelling, Completion Promises, When to Use, Learn More) and no nested references; no bundle files are needed or provided.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 clearly states both purpose and usage triggers in a concise, third-person voice with natural trigger terms. It is slightly light on enumerating specific capabilities, which keeps specificity at 2.

Dimension	Reasoning	Score
Specificity	Names the domain ('Ralph Loop plugin') and some actions ('Explain... how it works, and available skills') but does not enumerate multiple distinct concrete capabilities, so it stops short of the level-3 anchor.	2 / 3
Completeness	It states what the skill does ('Explain the Ralph Loop plugin, how it works, and available skills') and gives an explicit 'Use when...' clause with concrete triggers, satisfying both what and when.	3 / 3
Trigger Term Quality	Natural phrases a user would say ('help with ralph loop', 'understand the technique', 'usage examples') are well covered, matching the level-3 anchor for good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	'Ralph Loop' is a clear niche with distinct triggers unlikely to overlap with other skills, matching the level-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cursor/plugins
Commit: 0452e08

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

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.