CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ralph-loop

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

56

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

80%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 content is lean and provides copy-paste-ready executable commands with good structure and a real script reference. Its main weakness is the absence of a sequenced workflow with validation checkpoints for a batch/destructive loop operation.

Suggestions

Add an explicit sequenced workflow (start -> advance via --next -> check --status -> stop/restart) with a validation step before forcing a restart or relying on auto state-file removal.

Document how to verify loop state and completion before the auto-removal of the state file on max_iterations, so users can recover gracefully.

Briefly note expected command outputs (--status, --next) so users can confirm an iteration succeeded.

DimensionReasoningScore

Conciseness

The body is efficient, using tight bullets and executable code with no over-explanation of concepts Claude already knows; only minor phrasing in 'Vibe compatibility' and 'Notes' could be trimmed.

4 / 5

Actionability

Usage provides fully executable, copy-paste-ready PowerShell commands with concrete paths and flags covering start, --next, --status, --force, and the --engine open case.

5 / 5

Workflow Clarity

Usage is shown as separate examples rather than a sequenced workflow, and the batch loop with automatic state-file removal has no validation/verification checkpoint, which per the guidelines caps workflow clarity at 3.

3 / 5

Progressive Disclosure

A short (~50-line), single-purpose skill with well-organized sections and a single, clearly signaled, one-level-deep script reference (scripts/ralph-loop.ps1, verified to exist).

5 / 5

Total

17

/

20

Passed

Description

46%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 concretely names the tool and its two engines but is written in technical jargon and omits any explicit 'Use when' trigger guidance. It is distinct but would benefit from natural-language trigger phrases.

Suggestions

Add a 'Use when...' clause with natural trigger phrases (e.g., 'Use when running an automated ralph-style task loop in Codex').

Replace or supplement jargon like 'open-ralph-wiggum backend' with user-facing synonyms so the description matches what a user would actually say.

Reframe component names as concrete actions the skill performs (e.g., 'Runs, advances, and reports on iterative task loops') to improve specificity.

DimensionReasoningScore

Specificity

Names the domain (loop runner) and a couple of concrete components ("dual engines", "compat local state loop", "open-ralph-wiggum backend"), but these are components rather than a comprehensive list of actions.

3 / 5

Completeness

The "what" is clear (a dual-engine loop runner), but there is no "Use when..." clause or equivalent trigger guidance, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like "Codex-compatible", "Ralph loop runner", and "open-ralph-wiggum backend" are technical jargon a user would rarely say naturally, and no common synonyms or natural phrases are included.

2 / 5

Distinctiveness Conflict Risk

The named tool ("ralph-loop", "open-ralph-wiggum") occupies a clear niche with distinct triggers and only minor overlap risk with related tooling skills.

4 / 5

Total

12

/

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

foryourhealth111-pixel/Vibe-Skills

Path

bundled/skills/ralph-loop/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.