ralph
Specification-first AI development powered by Ouroboros. Socratic questioning exposes hidden assumptions before writing code. Evolutionary loop (Interview → Seed → Execute → Evaluate → Evolve) runs until ontology converges. Ralph mode persists until verification passes — the boulder never stops. Use when user says "ralph", "ooo", "don't stop", "must complete", "until it works", "keep going", "interview me", or "stop prompting".
83
83%
Does it follow best practices?
Impact
71%
2.02xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at trigger term coverage and distinctiveness with memorable, unique phrases like 'ralph' and 'ooo'. It includes an explicit 'Use when' clause making it complete. The main weakness is that the capabilities described are somewhat abstract (Socratic questioning, evolutionary loops) rather than concrete actions, though this may be appropriate for a methodology-focused skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (specification-first AI development) and describes a process (Interview → Seed → Execute → Evaluate → Evolve loop, Socratic questioning), but the actual concrete actions are abstract concepts rather than specific operations like 'extract text' or 'fill forms'. | 2 / 3 |
Completeness | Clearly answers both what (specification-first development with Socratic questioning and evolutionary loop) AND when (explicit 'Use when user says...' clause with multiple trigger phrases). The when clause is explicit and comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'ralph', 'ooo', 'don't stop', 'must complete', 'until it works', 'keep going', 'interview me', 'stop prompting'. These are specific, memorable phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique trigger terms like 'ralph', 'ooo', and the specific methodology (Ouroboros, evolutionary loop). Very unlikely to conflict with other skills due to the unusual terminology and specific trigger phrases. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, highly actionable skill with excellent workflow clarity and concrete executable guidance. The main weaknesses are verbosity (philosophical framing, extensive ASCII art) and lack of progressive disclosure—the monolithic structure could benefit from splitting advanced topics into separate files. The command reference and platform support matrices are particularly strong.
Suggestions
Move platform-specific installation details (hooks.json, Gemini settings, Codex setup) to a separate PLATFORMS.md file and link to it
Trim philosophical sections (Socrates quotes, Double Diamond explanation) to 1-2 sentences each—Claude doesn't need the conceptual framing
Extract the Nine Minds agent descriptions to an AGENTS.md reference file, keeping only a brief summary in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some verbose explanations (e.g., the philosophy sections, extensive ASCII diagrams) that could be tightened. The Double Diamond explanation and Socrates quote add flavor but consume tokens without adding actionable value. | 2 / 3 |
Actionability | Provides concrete commands, executable code examples, specific YAML schemas, JSON state file formats, and copy-paste ready installation commands. The command reference table and platform-specific setup instructions are highly actionable. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints (Interview → Seed → Execute → Evaluate). The Ralph loop includes verification stages, iteration tracking, and clear feedback loops for error recovery. Convergence thresholds and stagnation detection are well-defined. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline in one large document. Advanced topics like platform-specific hooks, the Nine Minds agents, and evolution mechanics could be split into separate reference files to reduce cognitive load. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (551 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- supercent-io/skills-template
- Commit
c033769
- 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.