CtrlK
BlogDocsLog inGet started
Tessl Logo

audio2txt

从音频文件中提取文字(语音转文字),需要腾讯云 API 凭据。当用户提到音频转文字、语音识别、ASR、音频转字幕时使用。

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/video/audio2txt/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.

A concise, actionable, well-structured simple skill whose main weakness is the absence of validation and error-recovery around a batch API transcription call. Adding a verify/retry checkpoint and documenting the result/failure path would raise the workflow score.

Suggestions

Add a verification step after the transcription call (e.g. confirm the returned text is non-empty and handle API errors with a retry/fallback) to satisfy the batch-operation validation requirement.

Document the actual return value or how transcription results are surfaced to the caller instead of just listing `None`.

Remove the redundant "功能描述" + blockquote lines that repeat the frontmatter description to tighten conciseness further.

DimensionReasoningScore

Conciseness

The body is lean with minimal padding, though the "功能描述" line and blockquote echo the frontmatter description and could be trimmed.

4 / 5

Actionability

A concrete, copy-paste-ready Python call plus a full parameter table gives executable guidance; the only gap is the bare `None` return value with no failure/output handling.

4 / 5

Workflow Clarity

Although single-purpose, the audio-to-text API call is a batch-style operation with no validation, error-handling, or verify step, which caps workflow clarity at 3 per the batch-operation guideline.

3 / 5

Progressive Disclosure

Under 50 lines, single-task, well-organized into clear sections, with no external bundle files present or needed, satisfying the simple-skill exception.

5 / 5

Total

16

/

20

Passed

Description

77%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 communicates a single capability (audio-to-text via Tencent Cloud ASR) with strong, natural trigger terms and an explicit when-to-use clause. It is held back from a top score by the one-action specificity and a slightly mechanical when-clause.

DimensionReasoningScore

Specificity

Names the audio-transcription domain and one concrete action ("从音频文件中提取文字"), but offers only that single action with no comprehensive list of capabilities.

3 / 5

Completeness

Explicitly states both what it does (extracts text from audio, needs Tencent Cloud credentials) and when to use it ("当用户提到...时使用"), though the when-clause is mechanical rather than richly specific.

4 / 5

Trigger Term Quality

Covers natural user phrases plus synonyms and an acronym ("音频转文字、语音识别、ASR、音频转字幕"), giving comprehensive trigger coverage.

5 / 5

Distinctiveness Conflict Risk

The narrow ASR niche with an explicit trigger list (音频转文字/语音识别/ASR/字幕) makes it mostly distinct, with only minor overlap risk against generic media skills.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CoderWanFeng/python-office
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.