ralph-tui-create-json
Convert PRDs to prd.json format for ralph-tui execution. Creates JSON task files with user stories, acceptance criteria, and dependencies. Triggers on: create prd.json, convert to json, ralph json, create json tasks.
88
82%
Does it follow best practices?
Impact
100%
1.21xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 skill description that concisely covers all key dimensions. It specifies concrete actions (converting PRDs, creating JSON task files with specific components), provides explicit trigger terms, and occupies a clearly distinct niche around the ralph-tui tool. The description uses proper third-person voice and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Convert PRDs to prd.json format', 'Creates JSON task files with user stories, acceptance criteria, and dependencies'. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (converts PRDs to prd.json format, creates JSON task files with user stories, acceptance criteria, and dependencies) and 'when' (explicit 'Triggers on:' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'create prd.json', 'convert to json', 'ralph json', 'create json tasks'. These cover multiple natural phrasings a user might use, including the tool name 'ralph'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: specific to 'ralph-tui' tool, 'prd.json' format, and PRD conversion. The combination of tool name, file format, and domain makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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 with excellent concrete examples including a complete input→output transformation and clear anti-patterns. Its main weaknesses are verbosity (redundant information across sections, overly detailed anti-patterns) and lack of a validation step for the generated JSON before it's consumed by ralph-tui. The monolithic structure could benefit from splitting detailed reference material into separate files.
Suggestions
Add an explicit validation step (e.g., 'Validate the generated JSON: check that root has "name" and "userStories" keys, no circular dependencies in dependsOn, all referenced IDs exist') to create a proper feedback loop before saving.
Move the anti-patterns section and the full example to a separate reference file (e.g., EXAMPLES.md) and link to it, keeping only the correct schema and a brief example inline.
Consolidate the 'Conversion Rules' section with the earlier step-by-step instructions — most rules are already stated elsewhere in the document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~250 lines) with some redundancy. The anti-patterns section, while useful, is verbose with four separate wrong examples. The conversion rules section largely repeats information already covered in other sections. However, most content is domain-specific and not explaining things Claude already knows. | 2 / 3 |
Actionability | Highly actionable with a complete JSON schema, a full input-to-output example (PRD markdown → prd.json), specific field names and values, anti-patterns with concrete examples, and clear sizing guidelines. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The steps are listed (extract quality gates → parse stories → append gates → set dependencies → output), and there's a checklist at the end, but there's no explicit validation step for the generated JSON (e.g., validate against schema, check for circular dependencies programmatically). For a file-generation task that feeds into an automated system, a validation checkpoint would be important. | 2 / 3 |
Progressive Disclosure | The content is entirely monolithic — everything is in one file with no references to external documentation. The anti-patterns section, the full example, and the detailed dependency/sizing guidance could be split into separate reference files. However, the sections are well-organized with clear headers and the content flows logically. | 2 / 3 |
Total | 9 / 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
1d4670f
- 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.