ralph-prompt-builder

Master orchestrator for generating Ralph Wiggum-compatible prompts. Analyzes task requirements and routes to appropriate generator (single-task, multi-task, project, or research). Use when you need to create any Ralph loop prompt and want automatic selection of the right generator.

Quality

66%

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 ./skills/ralph-prompt-builder/SKILL.md

Quality

Content

56%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 well-organized and actionable with concrete commands, templates, and checklists, but it is notably verbose with heavy repetition of the four task types and is monolithic with no progressive disclosure to separate reference files. The strongest dimension is actionability; the weakest is conciseness.

Suggestions

Consolidate the repeated four-task-type listings (Overview table, Classification table, Classification Examples, Decision Tree, Specialized Generators) into one routing table plus the decision tree, cutting the redundant restatements to reduce token load.

Move the per-generator structure/best-practice/iteration summaries into a separate reference file (e.g. references/generators.md) and link to it from SKILL.md, enabling progressive disclosure instead of inlining all four.

Trim the "Ralph Philosophy" explainer and the DO/DON'T section, which restate concepts and pad length without adding executable guidance that isn't already covered by the checklists.

Dimension	Reasoning	Score
Conciseness	At ~430 lines the body is noticeably verbose and restates the four task types repeatedly (Overview table, Classification table, Classification Examples, Decision Tree, Generator Summaries, Specialized Generators list), and the "Ralph Philosophy" explainer plus DO/DON'T sections pad length beyond what the action requires.	2 / 5
Actionability	Provides copy-paste-ready templates ("Use ralph-prompt-builder to create a prompt for: ...") and an executable bash invocation ("/ralph-wiggum:ralph-loop ... --completion-promise ... --max-iterations"), plus concrete numeric max-iteration tables and adjustment factors; the only gap is that actual prompt generation is delegated to sub-generators not shown in this file.	4 / 5
Workflow Clarity	The five-step workflow (Describe → Review Classification → Provide Inputs → Generate & Review → Execute) is clearly sequenced with review checkpoints in Step 2 ("Does this classification look correct?") and Step 4, plus Input/Output checklists, but it lacks an explicit validate-then-retry feedback loop on the generated prompt.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and all ~430 lines are inlined in SKILL.md with only section headers for structure; the per-generator structure summaries are content that could live in separate reference files but is instead inlined, so it sits at the "some structure but could be better organized" anchor rather than a 4.	3 / 5
	Total	13 / 20 Passed

Description

76%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, well-structured description that clearly answers both what and when with an explicit trigger clause and a distinctive niche. Its main weakness is narrow trigger-term coverage (only "Ralph" phrasing) and slightly abstract orchestration verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "generating Ralph Wiggum-compatible prompts", "Analyzes task requirements and routes to appropriate generator (single-task, multi-task, project, or research)" — naming all four routing targets, though the orchestration verbs ("analyzes", "routes") are more abstract than the anchor-5 file-operation example.	4 / 5
Completeness	Clearly states both what it does ("Master orchestrator for generating... prompts... routes to appropriate generator") and when to use it ("Use when you need to create any Ralph loop prompt and want automatic selection"), matching the anchor-5 example with an explicit "Use when" trigger.	5 / 5
Trigger Term Quality	Contains the core natural phrases ("Ralph loop prompt", "Ralph Wiggum-compatible prompts") but offers few synonyms or variations a user might say, matching the "some relevant keywords but missing common variations" anchor rather than the broad coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	The "Ralph Wiggum" / "Ralph loop prompt" niche is highly distinctive, but because it routes to four closely related named generators (single-task, multi-task, project, research) there is minor overlap risk with those sibling skills, placing it just below the minimal-conflict anchor 5.	4 / 5
	Total	16 / 20 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: fernandezbaptiste/Skrillz
Path: skills/ralph-prompt-builder/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.