qwen3-tts-local

真正的本地语音合成服务，使用 Edge-TTS 引擎，零依赖、零配置、完全离线可用，支持多语言和多种音色

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/qwen3-tts-local/qwen3-tts-local/SKILL.md

Quality

Content

46%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with real referenced bundle files and a concrete voice table, but it is padded with marketing/conceptual sections, repeats over-claims ('完全离线', '零依赖') that the 技术说明 section itself contradicts (Edge-TTS uses an online reverse-engineered API), and never shows how to actually run the generator. Workflow steps are sequenced but abstract with only vague validation.

Suggestions

Remove the '技术说明/工作原理' and '与 API 调用的区别' marketing sections, and reconcile the false '完全离线/零依赖' claims with the fact that Edge-TTS calls an online service and requires edge-tts (plus soundfile) dependencies.

Add an executable example showing how to run the generator (e.g. a `python scripts/tts_generator.py --text ... --voice ...` invocation or a short code snippet) so guidance is copy-paste ready.

Make the 工作流程 steps concrete with the actual commands/checks performed, and deduplicate the voice table against references/voice-guide.md by summarizing inline and pointing to the guide for the full list.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the '技术说明/工作原理' section explains Edge-TTS internals Claude already knows, the '与 API 调用的区别' ❌/✅ block is marketing padding, and the '零依赖/离线' claims are repeated across 核心功能, 注意事项, and 安装说明; not a 3 because several sections are pure padding.	2 / 5
Actionability	Provides concrete install commands, a real voice-name table, and references executable scripts that exist, but the body never shows how to actually invoke the generator (no code snippet or CLI call), leaving the key execution step missing — matches the 3 anchor's 'incomplete' guidance.	3 / 5
Workflow Clarity	The 工作流程 lists four sequenced steps including a '结果验证' checkpoint, but the steps are abstract ('识别语言', '自动选择音色') with no concrete commands and the validation is vague ('验证音频质量和完整性'), fitting the 3 anchor of steps present but checkpoints implicit.	3 / 5
Progressive Disclosure	Clear sections with a dedicated 资源索引 pointing one level deep to real files (scripts/tts_generator.py, scripts/audio_processor.py, references/voice-guide.md, all verified present); the only gap is voice-table duplication between the body and voice-guide.md, keeping it just below 5.	4 / 5
	Total	12 / 20 Passed

Description

48%Weight 40%Scale 1-5

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 states a clear TTS niche but leans on marketing attributes ('真正的', '完全离线', '零依赖') instead of concrete actions and omits any 'Use when...' trigger guidance. It is distinct enough to avoid most conflicts but lacks the trigger completeness that would raise its score.

Suggestions

Replace marketing attributes ('真正的本地', '完全离线', '零依赖') with concrete actions, e.g. '将文本合成为语音音频，支持多语言和多种预设音色'.

Add an explicit trigger clause such as 'Use when the user asks to read text aloud, generate voice-overs/dubbing, or produce TTS audio'.

Include common natural trigger terms users actually say ('朗读', '配音', '文字转语音', 'TTS').

Dimension	Reasoning	Score
Specificity	Names the TTS domain and the Edge-TTS engine, but the concrete action is limited to '语音合成' while the rest are marketing attributes ('真正的本地', '零依赖', '零配置', '完全离线') rather than specific actions; below the 3 anchor which expects 1-2 concrete actions.	2 / 5
Completeness	The 'what' is clear (a local voice-synthesis service using Edge-TTS with multi-language/voice support), but there is no 'Use when...' clause or equivalent trigger guidance, so per the guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes relevant natural terms like '语音合成' and '音色' but misses common user phrasings such as '朗读', '配音', '文字转语音', or 'TTS' synonyms, matching the anchor with some keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	The 'Edge-TTS 引擎' + local/offline framing carves a clear TTS niche with minimal overlap risk; only minor overlap with other audio/TTS skills, so it sits above the 3 anchor.	4 / 5
	Total	12 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/qwen3-tts-local/qwen3-tts-local/SKILL.md
Commit: 7054767

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.