CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

audio-transcription

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

68

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 lean, highly actionable instruction-only skill body: exact tool names, commands, and parameter values with a well-sequenced workflow and an availability-check feedback loop. The only minor gap is a lack of concrete verification at the workflow's edges (attachment path resolution, empty-transcript handling).

DimensionReasoningScore

Conciseness

Every line delivers non-obvious information Claude could not infer: the exact MCP tool name, that 'language: "auto"' is the only supported value, path/symlink restrictions, and the npm-vs-desktop-app installer distinction. There is no concept explanation or padding to trim, matching the lean 5 anchor.

5 / 5

Actionability

The guidance is fully concrete and executable: an exact install command ('npm --prefix "<PilotDeck directory>" run install:asr'), the exact tool to call ('mcp__funasr__transcribe_audio'), the exact parameter value, and precise path-handling instructions. For an instruction-only skill, this is copy-paste-ready actionable guidance covering the common cases.

5 / 5

Workflow Clarity

A clear 5-step numbered sequence exists with an explicit feedback loop (check tool availability → run installer → retry the tool in the same session). It falls short of 5 only because step 1 ('Identify the registered audio attachment path in the session message') and the post-transcription steps lack concrete verification checkpoints, e.g. confirming the attachment path resolves before calling the tool or checking the transcript is non-empty before summarizing.

4 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections (Workflow, Constraints) and appropriately defers troubleshooting detail to a clearly signaled one-level reference ('For platform, cache, download-source, and network troubleshooting details, read ../../docs/funasr-installation.md'). No bundle files exist to inline, so the structure fully satisfies the simple-skill guideline.

5 / 5

Total

19

/

20

Passed

Description

71%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.

A specific, distinct description with concrete capability language and natural trigger terms, weakened only by the absence of explicit 'when to use' guidance. Adding a Use-when clause with trigger phrases and a few synonyms would raise it to top-tier.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to transcribe audio or a recording, create subtitles/captions, or generate meeting notes from an audio file.'

Include common synonyms and extensions users would naturally mention: 'captions', 'voice memo/recording', '.mp3', '.wav', '.m4a'.

Optionally signal scope boundaries in the description (project-local files only) to further reduce overlap with cloud-transcription or note-taking skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions — 'Transcribe a project-local audio recording, generate subtitles, analyze a recording, or produce meeting notes' — giving comprehensive coverage of the domain with no vague filler. This matches the anchor for multiple specific concrete actions with comprehensive coverage, and there are no minor gaps that would justify a 4.

5 / 5

Completeness

The 'what' is clear (transcription, subtitles, analysis, meeting notes), but there is no 'Use when...' clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3 even with a clear statement of capabilities.

3 / 5

Trigger Term Quality

Natural user phrasings like 'transcribe', 'subtitles', 'meeting notes', and 'audio recording' are present, but common synonyms and file extensions ('captions', 'voice memo', '.mp3', '.wav') are missing. Good keyword coverage with a few natural terms absent matches the 4 anchor, falling short of the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche — local FunASR transcription of project-local audio — anchored by distinct terms like 'transcribe' and 'local FunASR'. However, 'subtitles' and 'meeting notes' could overlap with video-editing or general note-taking skills, matching 'mostly distinct; minor overlap risk' rather than the minimal-conflict 5 anchor whose example also carries explicit when-triggers.

4 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

OpenBMB/PilotDeck

Path

skills/audio-transcription/SKILL.md

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.