CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

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 highly actionable and well-structured with properly signaled one-level references, but it is padded by verbose example outputs and lacks validation checkpoints in its transcription and splice workflows.

Suggestions

Trim the full sample outputs in 示例 1–5 to brief sketches or remove the ones that merely show formats Claude already knows, to reduce token cost.

Add explicit validation steps—check result['success'] and transcribed text length before proceeding to rewrite or splice, and retry/re-report on failure.

For the multi-segment splice flow, add a checkpoint that verifies each segment transcribed successfully before concatenating, with error-recovery guidance.

DimensionReasoningScore

Conciseness

Operational sections are efficient, but the five full example outputs (meeting notes, email, social-media post, splice, share) re-demonstrate formats Claude already knows how to produce, adding padded length that could be trimmed.

3 / 5

Actionability

Provides copy-paste-ready executable code for transcription ('from scripts.asr_transcriber import Qwen3ASRTranscriber ... transcriber.transcribe(...)') plus a concrete API reference documenting the method signature and return dict, fully covering the common cases.

5 / 5

Workflow Clarity

The standard and multi-segment flows are clearly numbered, but there are no validation checkpoints—the workflow never checks result['success'] or verifies transcription quality before splicing, and the batch splice operation triggers the validation cap.

3 / 5

Progressive Disclosure

A 资源索引 section signals one-level-deep references with explicit '何时读取' cues to scripts/asr_transcriber.py, references/asr-api-config.md and references/text-rewrite-guide.md (all real files), keeping the overview lean while details live in the bundle.

5 / 5

Total

16

/

20

Passed

Description

80%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 is specific and trigger-rich, clearly communicating the skill's concrete capabilities and applicable scenarios. Its main gap is the absence of an explicit 'Use when...' trigger clause and full synonym/extension coverage.

Suggestions

Add an explicit trigger clause such as 'Use when the user mentions 语音转文字、录音转文字、语音备忘、会议纪要 or wants to turn speech into emails/notes/social posts'.

Include audio file extensions (e.g. .wav, .mp3, .m4a) and synonyms like 听写 to broaden natural trigger coverage.

Rephrase '适用于...等多种场景' as a direct 'Use when...' instruction so the 'when' guidance is explicit rather than implied.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'实时语音识别', '录音转换为文字', '改写成邮件、笔记、社交媒体文案', '复制、分享和录音拼接'—covering the skill comprehensively, matching the level-5 anchor.

5 / 5

Completeness

Clearly states what it does and gives a scenario-based 'when' ('适用于会议纪要、语音备忘、内容创作等多种场景'), but this is phrased as applicable-scenarios rather than an explicit 'Use when...' trigger phrase, so it does not reach level 5.

4 / 5

Trigger Term Quality

Includes natural user phrases like '语音转文字', '录音转文字', '语音备忘', '会议纪要' with good coverage, but omits synonyms (e.g. 听写) and audio extensions (.wav/.mp3), so it sits below the comprehensive level-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The voice-to-text entry point is a clear niche with distinct triggers, but the text-rewriting component ('改写成邮件、笔记、社交媒体文案') could overlap with a dedicated rewrite skill, giving minor overlap risk rather than the minimal level-5 risk.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anbeime/skill
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.