qwen3-asr-assistant

综合办公文员与内容创作者在需要整理会议纪要或创作社媒文案时，使用本技能将录音一键转写并智能改写为邮件、笔记或社媒文案，支持多段录音无缝拼接，秒出高质量结构化文本，让语音记录与内容产出效率翻倍！

Quality

68%

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

61%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 delivers executable transcription code, a usable API reference, and concrete rewrite templates organized into two flows with well-signaled bundle references. Its weaknesses are verbosity from repetitive examples, missing validation checkpoints, and an inline API section that belongs in references.

Suggestions

Add an explicit validation checkpoint after transcription (check result['success'] and handle errors) before proceeding to rewrite or splice, especially in the multi-segment flow.

Trim the five worked examples and remove UI-action sub-bullets ('点击录音按钮开始录音') that describe the app rather than the agent's actions.

Move the inline 'API 参考' section into references/ and link to it from the body to shorten the overview and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly task-focused but is padded by five full worked examples with complete output templates, repeated transcription snippets, and UI-clicking sub-bullets ('点击录音按钮开始录音') that describe the app rather than the agent; it could be tightened noticeably.	3 / 5
Actionability	Provides copy-paste-ready transcribe() calls, a concrete API reference with return shape, and concrete rewrite output templates for each format; minor gaps such as omitted api_key/base_url configuration keep it just below fully executable.	4 / 5
Workflow Clarity	Two clear numbered sequences (standard flow and multi-segment flow) exist, but there are no validation checkpoints — the result['success'] field is documented yet never checked, and the multi-segment (batch-like) flow has no verification before splicing.	3 / 5
Progressive Disclosure	A '资源索引' section points one level deep to the real references/asr-api-config.md, references/text-rewrite-guide.md and scripts/asr_transcriber.py with explicit '何时读取' read-triggers; the inline API-reference block at the bottom is the main organization gap that keeps it from 5.	4 / 5
	Total	14 / 20 Passed

Description

75%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 clearly conveys a distinctive capability (transcription plus rewriting into email/notes/social copy and multi-segment splicing) and includes a scenario-based 'when', using appropriate third-person voice. It is held back from top marks by marketing fluff and the lack of an explicit trigger-phrase clause.

Suggestions

Remove the over-claim tail '秒出高质量结构化文本，让语音记录与内容产出效率翻倍！' so the description stays concrete and verifiable.

Add an explicit 'Use when...' clause with natural trigger phrases such as '语音转文字' and '录音转文字' to raise completeness and trigger coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — '将录音一键转写', '智能改写为邮件、笔记或社媒文案', '多段录音无缝拼接' — giving comprehensive coverage of capabilities, though the marketing tail '秒出高质量结构化文本，让语音记录与内容产出效率翻倍！' is over-claim fluff that keeps it below 5.	4 / 5
Completeness	Both 'what' (transcribe, rewrite to three formats, splice) and 'when' ('在需要整理会议纪要或创作社媒文案时') are present, but the 'when' is audience-scoped rather than an explicit 'Use when...' trigger clause, so it could be more explicit.	4 / 5
Trigger Term Quality	Good coverage of natural terms a user would say ('会议纪要', '社媒文案', '录音', '邮件', '笔记'), but common variations like '语音转文字'/'录音转文字' that appear in the body are absent from the description, so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	The speech-to-text-plus-intelligent-rewriting niche with triggers like 会议纪要/录音转写/社媒文案 is mostly distinct from generic transcription or writing skills, with only minor overlap risk.	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/qwen3-asr-assistant/qwen3-asr-assistant/SKILL.md
Commit: d9e888d

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.