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.
Install with Tessl CLI
npx tessl i github:subsy/ralph-tui --skill ralph-tui-create-jsonOverall
score
87%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 well-crafted skill description that excels across all dimensions. It clearly specifies the concrete actions (PRD conversion, JSON task file creation), includes explicit trigger terms users would naturally use, and has a distinct niche around the ralph-tui tool that minimizes conflict risk with other skills.
| 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 clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (converts PRDs to JSON format, creates task files with specific components) and when (explicit 'Triggers on:' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes explicit natural trigger terms that users would say: 'create prd.json', 'convert to json', 'ralph json', 'create json tasks'. Good coverage of variations including the tool name. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool name 'ralph-tui', specific file format 'prd.json', and domain-specific terms like 'PRDs' and 'user stories'. Unlikely to conflict with generic JSON or document skills. | 3 / 3 |
Total | 12 / 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 guidance for converting PRDs to JSON format. Its main strength is the comprehensive examples and explicit anti-patterns that prevent common mistakes. The primary weakness is verbosity - the content could be more concise by reducing redundancy in the anti-patterns section and trusting Claude to infer some system behaviors.
Suggestions
Consolidate the anti-patterns section - show one wrong example with a brief note instead of four separate subsections explaining similar issues
Move the detailed example (Input PRD → Output prd.json) to a separate EXAMPLES.md file and reference it from the main skill
Remove explanatory text about ralph-tui's internal behavior (agent context windows, iteration mechanics) - focus on what Claude needs to do, not why the system works that way
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy - the anti-patterns section repeats concepts multiple times, and explanations like 'Ralph-tui spawns a fresh agent instance per iteration with no memory of previous work' explain system behavior Claude could infer. The content could be tightened by ~30%. | 2 / 3 |
Actionability | Excellent actionability with complete, copy-paste ready JSON examples, specific field names and values, concrete acceptance criteria examples (good vs bad), and a full end-to-end example showing input PRD to output JSON transformation. | 3 / 3 |
Workflow Clarity | Clear 5-step process at the top, explicit validation checklist at the end, and well-defined sequence (extract gates → parse stories → append gates → set dependencies → output). The checklist provides explicit verification before saving. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but it's a monolithic ~300 line file. The anti-patterns section, detailed examples, and conversion rules could be split into separate reference files. No external file references are provided for deeper dives. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 13 / 16 Passed | |
- 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.