CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

84%

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

86%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.

The body is highly actionable with exact paths and a copy-paste example, and is well-structured for a simple skill. Minor gains are available from deduplicating the confirm instruction and adding an explicit verification checkpoint after writing the state file.

Suggestions

Remove the duplicate 'confirm the loop is active' instruction — keep it only in the Output section to tighten the Workflow.

Add an explicit verification step after writing `.cursor/ralph/scratchpad.md` (e.g., confirm the file exists with the expected frontmatter) before beginning work, to give the workflow a clear validate-then-proceed checkpoint.

Consider noting what to do if `.cursor/ralph/scratchpad.md` already exists from a prior run (resume vs. reset) to close a small actionability gap.

DimensionReasoningScore

Conciseness

The body is lean and gives an exact state-file format plus a worked example without explaining concepts Claude already knows; it is not 5 because the 'confirm the loop is active' instruction appears in both the Workflow and Output sections, a minor redundancy that could be trimmed.

4 / 5

Actionability

Provides exact directory (`.cursor/ralph/`), exact file path, an exact YAML frontmatter format with placeholders, and a fully copy-paste-ready example covering the common case.

5 / 5

Workflow Clarity

A clearly sequenced 4-step workflow with guardrails acting as checkpoints; it is not 5 because there is no explicit validate-then-proceed feedback loop (e.g., confirming the scratchpad was written correctly before starting), and not 3 because the sequence and guardrails are otherwise complete.

4 / 5

Progressive Disclosure

A simple, single-purpose skill under 50 lines with no need for external references; it is well-organized into Trigger, Workflow, Guardrails, and Output sections, satisfying the simple-skill exception for a top score.

5 / 5

Total

18

/

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.

The description is concise, third-person, and clearly states both the capability and explicit trigger conditions. Its only weakness is that it enumerates just one concrete action, leaving specificity slightly behind the rest.

DimensionReasoningScore

Specificity

Names the domain ('Ralph Loop for iterative self-referential development') and one concrete action ('Start a Ralph Loop'), matching the 'names domain and 1-2 concrete actions' anchor; it is not 4 because only a single action is enumerated and the phrasing stays somewhat abstract.

3 / 5

Completeness

Explicitly answers both what ('Start a Ralph Loop for iterative self-referential development') and when ('Use when the user asks to run a ralph loop, start an iterative loop, or wants repeated autonomous iteration on a task until completion') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes several natural phrases a user would say ('run a ralph loop', 'start an iterative loop', 'repeated autonomous iteration on a task until completion'); it is not 5 because the niche has limited synonym/extension coverage beyond these variations.

4 / 5

Distinctiveness Conflict Risk

'Ralph Loop' is a distinct named concept with its own trigger vocabulary, giving it a clear niche and minimal overlap with other skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cursor/plugins
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.