ralph-plan

Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ralph-plan/SKILL.md

Quality

Content

50%

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

A well-structured conversational planning prompt with concrete examples and a clear sequence, but it is middling across the board due to redundancy, implicit rather than formalized checkpoints, and no progressive disclosure for a 160-line skill.

Suggestions

Tighten redundancy: the 'Starting the Conversation' section and several Guidelines restate the Role and Planning Process — consolidate them to reduce token cost.

Formalize validation checkpoints in the Planning Process (e.g., 'After drafting each section, confirm with the user before proceeding') rather than only showing a checkpoint inside the example dialogue.

Consider moving the Example Conversation Flow and the 9 Guidelines into a reference file to improve progressive disclosure for a skill of this length.

Dimension	Reasoning	Score
Conciseness	The custom ralph-command format is legitimately new information, but the 'Starting the Conversation' section and several Guidelines restate the Role and Planning Process, and the example conversation adds illustrative padding that could be tightened.	2 / 3
Actionability	Concrete good/bad task contrasts ('Create a '/processors' endpoint...') and a copy-paste XML template provide specific guidance, but the bulk of the skill is conversational/behavioral direction ('Be Inquisitive', 'Be Iterative') rather than fully executable instruction.	2 / 3
Workflow Clarity	The five-step Planning Process and section ordering give a clear sequence, but validation/confirmation checkpoints appear only implicitly inside the example dialogue rather than as prescribed workflow steps.	2 / 3
Progressive Disclosure	Headers organize the content well with no nested references, but at ~160 lines with no bundle files the 9 Guidelines and Example Conversation Flow are inline content that could be split out; the 'just well-organized sections' carve-out applies only to skills under 50 lines.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 competent, third-person description that names a specific niche, but it is middling across all dimensions because it lacks an explicit 'Use when' trigger, lists a single composite action, and leads with a generic planning-assistant framing.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when the user wants to build or refine a ralph-loop command') to answer when Claude should activate this skill and lift completeness.

Expand trigger-term coverage with natural phrasings users would actually say ('ralph command', 'plan a ralph loop', 'ralph-loop builder') rather than relying on the single 'ralph-loop commands' phrase.

Lead with the distinctive niche (ralph-loop command builder) rather than the generic 'Interactive planning assistant' framing to reduce overlap with general planning skills.

Dimension	Reasoning	Score
Specificity	'helps create focused, well-structured ralph-loop commands through collaborative conversation' names a domain and a composite action, but it is a single composite action rather than a list of multiple concrete actions.	2 / 3
Completeness	The description clearly states what the skill does but omits any 'Use when...' trigger clause, so the 'when' is missing rather than explicit (capping completeness at 2).	2 / 3
Trigger Term Quality	'ralph-loop commands' is a relevant natural term, but coverage is limited to that one phrase with no common variations such as 'ralph command', 'plan a ralph loop', or 'ralph-loop builder'.	2 / 3
Distinctiveness Conflict Risk	The 'ralph-loop commands' niche is reasonably distinct, but the leading 'Interactive planning assistant' framing is generic and could overlap with general planning skills absent a disambiguating trigger.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mastra-ai/mastra
Path: .claude/skills/ralph-plan/SKILL.md
Commit: 3b78ed9

Reviewed: about 22 hours 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.