ralph-tui-prd
Generate a Product Requirements Document (PRD) for ralph-tui task orchestration. Creates PRDs with user stories that can be converted to beads issues or prd.json for automated execution. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
88
84%
Does it follow best practices?
Impact
96%
1.52xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 is a strong description that clearly communicates what the skill does and when to use it. It names specific outputs (PRDs, user stories, beads issues, prd.json) and provides explicit trigger phrases. The only minor weakness is that some trigger terms like 'plan this feature' and 'requirements for' are broad enough to potentially conflict with other planning-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Generate a Product Requirements Document (PRD)', 'Creates PRDs with user stories', 'converted to beads issues or prd.json for automated execution'. Multiple distinct outputs and formats are named. | 3 / 3 |
Completeness | Clearly answers both 'what' (generates PRDs with user stories convertible to beads issues or prd.json) and 'when' (explicit 'Triggers on:' clause with five specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes explicit natural trigger phrases users would say: 'create a prd', 'write prd for', 'plan this feature', 'requirements for', 'spec out'. These cover common variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is fairly specific to 'ralph-tui task orchestration' and PRD generation, but terms like 'plan this feature' and 'requirements for' are somewhat generic and could overlap with general planning or project management skills. The tool-specific context (ralph-tui, beads issues, prd.json) helps but the broader triggers introduce some conflict risk. | 2 / 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 well-structured, highly actionable skill that provides clear step-by-step guidance for PRD generation with excellent concrete examples. Its main weakness is verbosity—the full example conversation and PRD output, while valuable, make the document long, and some concepts (quality gates importance, AI agent optimization) are repeated across multiple sections. The workflow is clear with good validation via the final checklist.
Suggestions
Reduce redundancy around quality gates—the concept is explained in Step 1, Step 2 section 3, the example, and the checklist; consolidate to fewer mentions.
Consider trimming the full example PRD to 2-3 user stories instead of 4, and shorten the conversation flow to save tokens while preserving the pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but verbose for what it conveys. The full example conversation flow with the complete dark mode PRD output (~80 lines) is useful but lengthy. Some sections like 'Writing for AI Agents' restate what's already implied by the structure. The repeated emphasis on quality gates across multiple sections adds redundancy. | 2 / 3 |
Actionability | The skill provides highly concrete, copy-paste-ready guidance: exact question formats with lettered options, specific PRD section templates with markdown formatting, a complete end-to-end example conversation with full PRD output, and explicit output markers ([PRD]...[/PRD]). Every step is clearly specified with examples. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced: receive description → ask clarifying questions iteratively → ask about quality gates → generate PRD with markers. The adaptive questioning loop (ask → evaluate → ask more or generate) is explicitly described. The final checklist serves as a validation checkpoint before output. | 3 / 3 |
Progressive Disclosure | The content is entirely self-contained in one file with no bundle files. While the sections are well-organized with clear headers, the full example PRD output makes the file quite long. The example could potentially be in a separate reference file. However, for a standalone skill with no bundle, the organization is reasonable but the inline example is heavy. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- subsy/ralph-tui
- Commit
8191b80
- 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.