ralph-prompt-research

Generate Ralph-compatible prompts for research, analysis, and planning tasks. Creates prompts with systematic research phases, synthesis requirements, and deliverable specifications. Use when analyzing codebases, creating migration plans, researching technologies, auditing security, or any task requiring investigation before action.

Quality

80%

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

Quality

Content

77%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.

Highly actionable and well-sequenced content with strong workflow scaffolding and validation checkpoints, but it is a verbose monolith that duplicates template structure across the generic guide and worked examples. Splitting examples and the full phase templates into separate reference files would materially improve progressive disclosure and token efficiency.

Suggestions

Move the two fully worked example prompts into a separate references/EXAMPLES.md and keep only a brief pointer inline, since they re-derive the same five-phase structure already documented.

Extract the detailed per-phase markdown templates into a references/phase-templates.md file, leaving the SKILL.md body as a concise overview of the five phases and their checkpoints.

Trim the 'Best Practices', 'DO', and 'DON'T' sections, which largely restate the per-phase success criteria and completion checklist already present.

Dimension	Reasoning	Score
Conciseness	The document is a long monolith where the two worked examples largely restate the generic five-phase template, and the 'Best Practices'/'DO'/'DON'T' sections repeat guidance already implied by the phase success criteria; it could be tightened substantially without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready markdown templates with explicit placeholders plus two fully worked example prompts (security audit, framework comparison) that cover the common cases end-to-end.	5 / 5
Workflow Clarity	A clearly sequenced five-phase workflow with per-phase success criteria, explicit checkpoints ('DISCOVERY COMPLETE', 'ANALYSIS COMPLETE'), a final verification checklist, and 'If Stuck' recovery guidance.	5 / 5
Progressive Disclosure	No bundle files exist and the entire guide — generic phase templates, two long worked examples, and best practices — is inlined into a single monolithic SKILL.md rather than split into one-level-deep reference files.	3 / 5
	Total	16 / 20 Passed

Description

83%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 description that clearly states both capability and trigger conditions with concrete, natural-language phrases. The Ralph-specific framing aids distinctiveness, though the trigger list is broad and the action set is effectively single-purpose with descriptive attributes.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete prompt components ('systematic research phases, synthesis requirements, and deliverable specifications'), though the underlying action is essentially one ('Generate Ralph-compatible prompts') with attributes rather than many distinct actions.	4 / 5
Completeness	Explicitly answers both what ('Generate Ralph-compatible prompts... Creates prompts with...') and when ('Use when analyzing codebases... or any task requiring investigation before action') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('analyzing codebases, creating migration plans, researching technologies, auditing security'), but lacks synonyms and file-extension-style variants that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'Ralph-compatible prompts' framing carves a clear niche, but the research/audit trigger terms ('analyzing codebases', 'auditing security') are broad enough to overlap with general research or audit skills.	4 / 5
	Total	17 / 20 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
skill_md_line_count	SKILL.md is long (736 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/ralph-prompt-research/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.