qwen3-asr-assistant

智能语音转文字助手，基于 Qwen3-ASR 模型，支持实时语音识别和智能文本改写。可以将录音转换为文字，并一键改写成邮件、笔记、社交媒体文案，支持复制、分享和录音拼接。适用于会议纪要、语音备忘、内容创作等多种场景。

Quality

77%

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/qwen3-asr-assistant/qwen3-asr-assistant/SKILL.md

Quality

Content

72%

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

A highly actionable, well-structured skill body with executable code, full API reference, and properly signaled one-level references. It loses points on conciseness (padded worked-output examples) and on workflow clarity (no validation checkpoint around the API success flag).

Suggestions

Trim the five fully-worked output examples (especially 示例 4 and 示例 5) to brief input→intent illustrations instead of complete generated text, since Claude can produce the output itself.

Add an explicit validation checkpoint after transcription, e.g. "检查 result['success']，失败时根据返回信息重试或提示用户" to lift workflow clarity to 3.

Consider moving the full API reference (类/方法签名) into the existing references/ folder and keeping only a quick-start snippet in SKILL.md to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with real executable code, but several fully-worked output examples (complete meeting notes, rewritten email, social-media post, placeholder splice output) restate output Claude can already produce and could be trimmed, keeping it below the lean level-3 anchor.	2 / 3
Actionability	Provides copy-paste-ready executable code ("from scripts.asr_transcriber import Qwen3ASRTranscriber") plus a full API reference with method signature, parameters, and return dict, matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	Steps are clearly sequenced (录音 → 语音转文字 → 文字改写 → 复制/分享 → 拼接) with a separate multi-segment flow, but there are no explicit validation checkpoints despite the API returning a "success" flag that should be checked, capping at the level-2 anchor.	2 / 3
Progressive Disclosure	Well-signaled one-level-deep references each carry explicit "何时读取" guidance and all referenced paths (scripts/asr_transcriber.py, references/asr-api-config.md, references/text-rewrite-guide.md) exist as real files, matching the clear-overview level-3 anchor.	3 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-triggered description with concrete actions and natural Chinese keywords. Its main gap is the absence of an explicit 'Use when...' trigger clause, leaving the 'when' as scenarios rather than crisp trigger conditions.

Suggestions

Add an explicit trigger clause such as "当用户提出语音转文字、录音转文字、语音备忘等需求时使用本 Skill" to lift completeness from scenario-stating to explicit-trigger guidance.

Tighten the scenario list into a single clear trigger sentence so Claude can match on user intent rather than broad use cases.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "实时语音识别", "一键改写成邮件、笔记、社交媒体文案", and "复制、分享和录音拼接", matching the multi-action anchor rather than the single-action level below.	3 / 3
Completeness	Clearly states what it does ("可以将录音转换为文字，并一键改写...") and gives applicable scenarios ("适用于会议纪要、语音备忘、内容创作等多种场景"), but lacks a crisp "Use when the user asks for X" trigger clause, so completeness caps at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Uses natural user phrasings like "语音转文字", "录音转文字", "语音备忘" and scenario terms "会议纪要、内容创作", giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The Qwen3-ASR speech-to-text-plus-rewriting niche is clear with distinct triggers ("语音转文字", "录音转文字"), making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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-asr-assistant/qwen3-asr-assistant/SKILL.md
Commit: f595e96

Reviewed: about 12 hours 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.