CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

A well-structured, mostly lean help skill: concrete start syntax, exact promise-tag format, and clear use/not-use guidance. The main gaps are duplicated mechanism explanations and slightly vague cancel/output instructions.

Suggestions

Merge the 6-step iteration list and the 'How it works' list under 'Starting a Ralph Loop' into one description of the stop-hook cycle to remove the duplicated explanation (conciseness).

Give an explicit example phrase for cancelling (e.g. "Stop the ralph loop") and state where the <promise> tag should appear in the agent's output (actionability).

Replace the vague Output section with a concrete note on answer structure — e.g. lead with a one-line definition of the Ralph Loop, then address the user's specific question (workflow_clarity).

DimensionReasoningScore

Conciseness

The body is lean and the self-referential-loop concept is genuinely non-obvious, so its explanation earns its tokens. One clear redundancy: the stop-hook/feed-same-prompt cycle is described twice (the 6-step iteration list and the 5-step 'How it works' list), which could be merged. Mostly efficient with minor trimmable duplication — anchor 4, not 5.

4 / 5

Actionability

The start command is copy-paste ready with both flags documented, and the completion promise is shown as an exact `<promise>TASK COMPLETE</promise>` tag. Anchor 4 rather than 5 because cancelling is given only as a paraphrased instruction ("Ask the agent to cancel the ralph loop") without an example phrasing, and where to place the promise tag is implied rather than stated.

4 / 5

Workflow Clarity

Both the loop lifecycle (numbered 1–6) and the start procedure (numbered 1–5) are clearly sequenced, and no destructive or batch operations exist to require validation checkpoints. Falls short of anchor 5 because the closing Output section ("Present the above information clearly to the user, tailored to their specific question") is directionally vague about structure or ordering of the answer.

4 / 5

Progressive Disclosure

A well-organized single file with clear section headers and external links inline; no bundle files exist, and none are needed. It exceeds 50 lines, so the simple-skill 5-exception does not apply, and the 'When to Use Ralph' and detailed mechanics sections slightly pad what a leaner overview would carry — good structure with minor organization gaps, anchor 4.

4 / 5

Total

16

/

20

Passed

Description

82%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concise, with an explicit and natural 'Use when' trigger clause. Its only weakness is that the capability list stays at the level of 'explain/understand' rather than naming the full scope of guidance the skill provides.

DimensionReasoningScore

Specificity

"Explain the Ralph Loop plugin, how it works, and available skills" names the domain with a few actions, but they all reduce to a single verb ("explain") and coverage is not comprehensive — it omits starting/cancelling loops and configuration options that the skill actually covers. Fits anchor 3 ("names domain and 1-2 concrete actions, but not comprehensive") better than anchor 4.

3 / 5

Completeness

A clear third-person "what" ("Explain the Ralph Loop plugin, how it works, and available skills") is paired with an explicit "Use when" clause containing three concrete trigger scenarios. Both what and when are explicit with concrete trigger phrases, matching the anchor-5 example; anchor 4's weaker 'when' does not apply.

5 / 5

Trigger Term Quality

Natural user phrasings are present — "help with ralph loop", "understand the technique", "needs usage examples" — giving good keyword coverage. Not anchor 5 because common synonyms like "Ralph Wiggum", "how does the ralph loop work", or "ralph loop plugin setup" are missing.

4 / 5

Distinctiveness Conflict Risk

"Ralph Loop" is a highly distinct niche term with dedicated trigger phrasing; no realistic overlap with generic skills. The explain-vs-execute intent ("Explain the... plugin") further separates it from a skill that runs loops — clear niche, minimal conflict risk.

5 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

cursor/plugins

Path

ralph-loop/skills/ralph-loop-help/SKILL.md

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.