ralph-loop

Codex-compatible Ralph loop runner with dual engines (compat local state loop + optional open-ralph-wiggum backend).

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/ralph-loop/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

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

The body is concise and highly actionable with concrete executable commands and a well-organized, one-level-deep reference to a real script. The only gap is the absence of explicit validation/feedback steps for the iterative workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean (~50 lines) and mostly bullets plus executable commands; it does not pad with concepts Claude already knows, and every section earns its place.	3 / 3
Actionability	The Usage section provides complete, copy-paste-ready PowerShell invocations with real flags (--next, --status, --force, --engine open, --max-iterations, --completion-promise) for each mode.	3 / 3
Workflow Clarity	The invocation modes are listed and sequenced via examples, but there are no explicit validation checkpoints or feedback loops for the iterative/run-to-completion behavior.	2 / 3
Progressive Disclosure	Content is organized into clear sections (Engine model, Script, Usage, Vibe compatibility, Notes) with a single, real one-level-deep reference (scripts/ralph-loop.ps1) that exists in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

42%Weight 40%Scale 1-3

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 conveys a clear, distinctive niche and names the engine model, but it relies on project-specific jargon and omits any explicit 'when to use' guidance. Adding natural trigger terms and a usage-trigger clause would materially improve it.

Suggestions

Add a 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when running or auto-iterating a Codex ralph-loop, or when the user asks to run/continue a ralph loop').

Replace or augment jargon ('compat', 'open-ralph-wiggum backend') with natural trigger terms a user would actually say, such as 'loop', 'iterate', 'auto-iterate', or 'ralph loop'.

Spell out one or two concrete actions the runner performs (e.g., 'runs iterative Codex tasks, tracks completion promises, and advances iterations') to lift specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Ralph loop runner') and concrete structural components ('dual engines', 'compat local state loop', 'open-ralph-wiggum backend'), but does not enumerate multiple distinct actions the skill performs.	2 / 3
Completeness	It answers 'what' (a loop runner with two engines) but provides no 'Use when...' clause or equivalent trigger guidance, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	The terms used ('Codex-compatible', 'compat', 'open-ralph-wiggum', 'dual engines') are project-specific jargon rather than natural keywords a user would say when they need this skill.	1 / 3
Distinctiveness Conflict Risk	The uniquely named tool ('ralph-loop', 'open-ralph-wiggum') carves a clear niche that is unlikely to trigger for the wrong skill or conflict with others.	3 / 3
	Total	8 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/ralph-loop/SKILL.md
Commit: f627ab5

Reviewed: 7 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.