text-to-speech
Expert skill for implementing text-to-speech with Kokoro TTS. Covers voice synthesis, audio generation, performance optimization, and secure handling of generated audio for JARVIS voice assistant.
65
55%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/text-to-speech/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies the technology stack (Kokoro TTS, JARVIS) and general capability areas but lacks the explicit trigger guidance essential for skill selection. It uses appropriate third-person voice but relies on category labels rather than concrete actions, and omits common user phrasings that would help Claude match this skill to requests.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks to convert text to speech, generate voice audio, or mentions Kokoro, TTS, or JARVIS voice features'.
Include common user phrasings and variations such as 'TTS', 'speak text', 'voice output', 'speech synthesis', and file extensions like '.wav' or '.mp3'.
Replace generic category terms with specific actions like 'convert text strings to audio files', 'select from multiple voice profiles', or 'stream real-time speech output'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (text-to-speech, Kokoro TTS) and lists some actions (voice synthesis, audio generation, performance optimization), but these are somewhat generic categories rather than concrete specific actions like 'convert text to WAV files' or 'adjust speech rate and pitch'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. There is no indication of when Claude should select this skill over others. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'text-to-speech', 'Kokoro TTS', 'voice synthesis', 'audio generation', and 'JARVIS', but misses common user variations like 'TTS', 'speech synthesis', 'voice output', 'speak text', or 'generate speech'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Kokoro TTS' and 'JARVIS voice assistant' provides some distinctiveness, but 'text-to-speech' and 'audio generation' are broad enough to potentially overlap with other audio or voice-related skills. | 2 / 3 |
Total | 7 / 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 skill with excellent actionability through complete, executable code examples and clear TDD workflows with validation checkpoints. However, it suffers from being overly verbose with unnecessary framing ('You are an expert...') and could benefit from better progressive disclosure by moving detailed implementations to reference files as initially suggested.
Suggestions
Remove the 'You are an expert' framing and 'You excel at' lists - Claude doesn't need this context about itself
Move the full SecureTTSEngine implementation (Pattern 1) and detailed test file to referenced files, keeping only concise examples in the main skill
Consolidate the Performance Patterns section with Implementation Patterns to reduce redundancy between streaming/caching examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in the overview section explaining what Claude excels at and the 'You are an expert' framing. The content could be tightened by removing redundant explanations and consolidating similar patterns. | 2 / 3 |
Actionability | Provides fully executable Python code examples throughout, including complete test files, implementation patterns with BAD/GOOD comparisons, and copy-paste ready commands for verification. The SecureTTSEngine implementation is comprehensive and runnable. | 3 / 3 |
Workflow Clarity | Clear TDD workflow with explicit steps (write test → implement → refactor → verify), comprehensive checklists with validation checkpoints, and explicit verification commands. The pre-implementation checklist provides clear feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | The file mentions 'See references/ for detailed implementations' but then includes extensive inline content that could be split. The 400+ line document contains full implementations that would be better organized in separate reference files, making the main skill harder to scan. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 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 |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- Repository
- martinholovsky/claude-skills-generator
- Commit
1086ef2
- 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.