tts-voice-synthesis

智能语音合成服务，支持音色克隆、拟人化语义适配配音、流式实时生成、多语言与方言支持，提供 1.7B/0.6B 双模型选择

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/tts-voice-synthesis/SKILL.md

Quality

Content

72%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 a well-structured, mostly executable overview with excellent progressive disclosure to real reference and script files. Its main weakness is vague validation/verification steps across the modes, which caps workflow clarity at 3 given the batch/streaming nature of the work.

Suggestions

Replace vague validation steps ("检查...质量", "验证情感表达") with concrete verification commands or checks, and add an explicit validate→fix→regenerate loop for streaming/batch generation to lift workflow_clarity above 3.

Tighten agent-narration padding (e.g. "智能体将分析文本情绪", "智能体自动完成") and drop self-evident sub-bullets like "确认待合成的文本内容" to push conciseness toward 5.

Provide exact per-step commands inside each operating mode (not only in the consolidated 使用示例) so every mode is fully copy-paste executable, raising actionability toward 5.

Dimension	Reasoning	Score
Conciseness	The body is efficient with short imperative steps and no explanation of concepts Claude already knows, but mild padding remains (e.g. "智能体将分析文本情绪" narration and steps like "确认待合成的文本内容"); not a 5 because a few steps restate the obvious, and not a 3 because it is clearly lean rather than containing several unnecessary explanations.	4 / 5
Actionability	Concrete copy-paste bash commands with real flags (--text, --emotion, --speed, --pitch, --streaming, --reference_audio) cover basic, clone, emotion, and streaming cases and point to real scripts; not a 5 because the per-mode numbered steps are descriptive prose without exact per-step commands, and not a 3 because genuinely executable examples are present.	4 / 5
Workflow Clarity	Each of the four modes has a clear numbered sequence, but validation checkpoints are vague ("检查生成的音频质量", "验证情感表达是否准确") with no validate→fix→retry loop or concrete verification command; streaming/batch generation caps this at 3 per the rubric, and it is not a 2 because the sequence is well-structured rather than rough with many gaps.	3 / 5
Progressive Disclosure	A clear 资源索引 section points one level deep to three real references (model_config, emotion_guide, usage_examples) and two real scripts, all verified to exist and signaled with markdown links plus parenthetical descriptions; not a 4 because organization is genuinely clean with appropriately split content and easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

71%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 gives a strong, specific account of what the service does across five concrete capabilities but omits any explicit "Use when..." trigger guidance, which caps completeness. It is distinctive within a clear TTS niche.

Suggestions

Append an explicit "Use when..." clause naming the natural trigger phrases (e.g. 将文本转为语音、克隆音色、生成情感化配音) to raise completeness above 3.

Add common synonyms/extensions such as "TTS", "朗读", and a sample output format to broaden natural keyword coverage toward a 5 on trigger_term_quality.

Use third-person imperative phrasing consistently (e.g. "Synthesizes speech from text...") to keep specificity tight and avoid any voice drift.

Dimension	Reasoning	Score
Specificity	Names the domain plus five concrete capabilities — "音色克隆", "拟人化语义适配配音", "流式实时生成", "多语言与方言支持", and "1.7B/0.6B 双模型选择" — giving comprehensive multi-action coverage; not a 4 because coverage is clearly concrete and multi-action rather than having only minor gaps.	5 / 5
Completeness	A clear and detailed "what" is present (智能语音合成服务 plus five capabilities) but the "when" is entirely absent with no "Use when..." clause, capping completeness at 3 per the rubric guideline; not a 2 because the "what" is detailed and not a 4 because trigger guidance is missing rather than merely weak.	3 / 5
Trigger Term Quality	Natural domain terms like "语音合成", "配音", and "音色克隆" are present, but synonym/extension breadth (e.g. "TTS", "朗读", a file extension) is missing; a 5 would require comprehensive synonym coverage, while a 3 would mean only "some relevant keywords" — these terms are clearly natural and well-chosen.	4 / 5
Distinctiveness Conflict Risk	TTS with voice cloning and explicit dual model sizes is a clear niche with only minor overlap risk against adjacent audio skills; not a 5 because explicit trigger phrases do not further sharpen the niche, and not a 3 because it is clearly specific rather than broadly overlapping.	4 / 5
	Total	16 / 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/tts-voice-synthesis/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.