CtrlK
BlogDocsLog inGet started
Tessl Logo

audio-transcription

Transcribe a project-local audio recording, generate subtitles, analyze a recording, or produce meeting notes from audio using local FunASR.

63

Quality

74%

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/audio-transcription/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 content is concise, actionable, and well-structured with a clear workflow and one-level reference to installation docs. Main improvements are adding an explicit transcription-output validation checkpoint and a concrete example tool invocation.

Suggestions

Add an explicit validation step after transcription (e.g. verify segments are non-empty and timestamps are monotonic) before proceeding to summarize or translate.

Provide one complete example `mcp__funasr__transcribe_audio` invocation with a concrete `audio_path` and expected output shape.

Format the docs reference as a markdown link (e.g. `[funasr-installation.md](../../docs/funasr-installation.md)`) to make navigation explicit.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, providing only operational detail (install command, tool name, path handling) without explaining what audio or ASR is; every line earns its place.

5 / 5

Actionability

It gives concrete executable commands (`npm --prefix "..." run install:asr`, `mcp__funasr__transcribe_audio` with `language: "auto"`) but the PilotDeck directory is a placeholder and a full example invocation is not shown.

4 / 5

Workflow Clarity

The five-step workflow is clearly sequenced with an install/retry checkpoint, but it lacks an explicit validation/verification step for the transcription output before downstream summarization.

4 / 5

Progressive Disclosure

Content is well-organized into sections with a single clearly signaled one-level-deep reference to `../../docs/funasr-installation.md` for troubleshooting detail; minor gap is the absence of inline-link formatting for the reference.

4 / 5

Total

17

/

20

Passed

Description

66%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 conveys concrete capabilities in a distinct niche but lacks an explicit 'Use when...' trigger clause, capping its completeness. Trigger-term coverage is good but could add common synonyms and file extensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when the user asks to transcribe audio, generate subtitles or captions, or produce meeting notes from a recording').

Include common synonyms and file extensions such as 'captions', 'audio file', '.wav', '.mp3', and 'speech-to-text' to broaden trigger coverage.

Replace or qualify the generic 'analyze a recording' phrase with a more specific capability to reduce overlap with general analysis skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Transcribe a project-local audio recording, generate subtitles, analyze a recording, or produce meeting notes from audio'), though 'analyze a recording' is slightly generic, leaving minor coverage gaps.

4 / 5

Completeness

It has a clear 'what' but no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like 'transcribe', 'subtitles', 'meeting notes', and 'recording' are present, but common synonyms/extensions (e.g. 'captions', 'audio file', '.wav', 'speech to text') are missing.

4 / 5

Distinctiveness Conflict Risk

The audio/FunASR niche is distinct with specific triggers, though 'analyze a recording' introduces minor overlap risk with general analysis skills.

4 / 5

Total

15

/

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
OpenBMB/PilotDeck
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.