textual-builder
Build Text User Interface (TUI) applications using the Textual Python framework (v0.86.0+). Use when creating terminal-based applications, prototyping card games or interactive CLIs, or when the user mentions Textual, TUI, or terminal UI. Includes comprehensive reference documentation, card game starter template, and styling guides.
83
78%
Does it follow best practices?
Impact
87%
1.35xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./textual-builder/SKILL.mdQuality
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 clearly communicates what the skill does, when to use it, and what resources it includes. It uses third-person voice, provides specific trigger terms, and carves out a distinct niche around the Textual framework for terminal-based applications. The inclusion of version information and specific use cases (card games, interactive CLIs) further strengthens its utility for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and artifacts: 'Build Text User Interface (TUI) applications', 'prototyping card games or interactive CLIs', 'comprehensive reference documentation, card game starter template, and styling guides'. It names the specific framework (Textual), version, and included resources. | 3 / 3 |
Completeness | Clearly answers both 'what' (build TUI applications using Textual framework, with reference docs, templates, and styling guides) and 'when' (explicit 'Use when' clause covering creating terminal-based apps, prototyping card games, interactive CLIs, or mentioning Textual/TUI/terminal UI). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'TUI', 'terminal-based applications', 'Textual', 'terminal UI', 'interactive CLIs', 'card games'. These cover multiple natural variations of how a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: the Textual Python framework for TUI apps. The specific framework name, version number, and domain (terminal UIs) make it very unlikely to conflict with other skills like general Python coding or web UI skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has strong progressive disclosure with clear navigation to reference files, and a useful Quick Start example. However, it suffers from some verbosity (explaining what Textual is, listing obvious best practices), and the workflow sections lack concrete executable guidance and validation checkpoints. The version information is also contradictory ('v0.86.0+' vs 'latest is v6.6.0').
Suggestions
Replace the abstract workflow steps (e.g., 'Design layout', 'Add widgets') with concrete code snippets showing each step building on the previous one.
Remove the overview paragraph explaining what Textual is and the best practices that Claude already knows (type hints, progressive development), keeping only Textual-specific guidance like CSS separation and message bubbling.
Add validation steps to workflows, such as 'Run `python app.py` to verify the app launches' after key steps, and error recovery guidance for common issues.
Fix the contradictory version information ('v0.86.0+' vs 'v6.6.0') — either remove version numbers or clarify the discrepancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'This skill helps you build sophisticated Text User Interfaces...', 'a Python framework for creating terminal and browser-based applications with a modern web-inspired API') and the best practices section states things Claude already knows (progressive development, type hints). The reference navigation section is useful but somewhat verbose in its 'Covers:' bullet lists. | 2 / 3 |
Actionability | The Quick Start provides executable code which is good, but the Common Workflows sections are vague step lists without concrete code or commands (e.g., 'Design layout', 'Add widgets'). The card game template copy command is concrete, but most workflow guidance is abstract rather than executable. | 2 / 3 |
Workflow Clarity | Workflows are listed as numbered steps but lack validation checkpoints, error handling, or feedback loops. For example, 'Creating a New TUI App' is just a sequence of 'read this file' steps with no verification that the app runs correctly at each stage. No testing or validation steps are mentioned. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: the SKILL.md provides a clear overview with well-signaled, one-level-deep references to specific reference files (basics.md, widgets.md, layout.md, styling.md, interactivity.md) with clear guidance on when to read each one. The 'When to Read Reference Documentation' section is particularly well-organized. | 3 / 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
- YPares/agent-skills
- Commit
84b1da5
- 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.