Name: audio-transcriber
Rating: 45.6 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

audio-transcriber

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Quality

48%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/audio-transcriber/SKILL.md

The canonical home for this skill is audio-transcriber in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

42%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 skill body is action-oriented but suffers from significant verbosity, mojibake-decorated output blocks, undefined placeholder functions, a discontinuous and misnumbered workflow, and weak use of the existing bundle files. Batch operations lack the validation the rubric requires.

Suggestions

Resolve the mojibake emoji and trim the decorative echo/status-output blocks to drastically reduce token usage and improve readability.

Replace the placeholder summarization functions (call_ai_model, cluster_by_topic, extract_action_items) with executable implementations, or move them into scripts/transcribe.py and reference that file.

Fix the step numbering (fill in or remove the missing Steps 2 and 4, and the referenced-but-absent Step 0b) and add an explicit batch-validation checkpoint before writing batch outputs.

Link to references/tools-comparison.md for the engine trade-offs and move the large install-prompt bash into scripts/install-requirements.sh instead of inlining it.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: ~550 lines padded with decorative emoji echo blocks, redundant install-prompt boilerplate, and repeated status-output examples that add little actionable value and could be trimmed substantially.	2 / 5
Actionability	It provides concrete bash and Python snippets, but the core summarization logic relies on undefined placeholders (call_ai_model, cluster_by_topic, extract_action_items, extract_decisions), making the key path pseudocode rather than executable.	3 / 5
Workflow Clarity	Steps are listed but the sequence is discontinuous (Step 0, 1, 3, 5 with 2 and 4 missing) and references a nonexistent 'Step 0b'; batch processing appears in examples without any batch validation checkpoint, capping this score at 3.	3 / 5
Progressive Disclosure	Real bundle files exist (references/tools-comparison.md, scripts/transcribe.py, scripts/install-requirements.sh), but the body never points to tools-comparison.md and inlines large blocks (full install prompts, status output, summarization pseudocode) that belong in the bundled scripts or references.	3 / 5
	Total	11 / 20 Passed

Description

53%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 a clear purpose but is missing the explicit 'when to use' guidance and the most natural trigger terms users would actually say. It is specific enough to be distinct but not comprehensive enough to fully surface its capabilities.

Suggestions

Add a 'Use when ...' clause listing concrete user triggers such as 'transcribe audio', 'generate meeting minutes', or 'create captions from a recording'.

Include the most common file formats (MP3, WAV, M4A) and formats produced (Markdown, SRT) as trigger keywords in the description.

Mention the standout capabilities (speaker diarization, subtitle generation, executive summaries) so the description reflects the skill's full scope.

Dimension	Reasoning	Score
Specificity	The description names the domain ('audio recordings') and two concrete actions ('Transform ... into professional Markdown documentation' and 'intelligent summaries'), but does not enumerate the fuller capability set (speaker diarization, SRT/VTT, metadata extraction) that the body reveals.	3 / 5
Completeness	It gives a clear 'what' (audio-to-Markdown with summaries via LLM) but provides no 'when/Use when' clause, capping completeness at 3 per the rubric guidance.	3 / 5
Trigger Term Quality	It includes relevant keywords ('audio recordings', 'Markdown documentation', 'summaries', 'LLM') but omits the most natural user phrases such as 'transcribe', 'meeting minutes', 'speech-to-text', and common file extensions, which appear only in the body.	3 / 5
Distinctiveness Conflict Risk	The audio-to-Markdown-with-summaries niche is reasonably distinct and unlikely to trigger for unrelated skills, though the absence of explicit trigger phrases keeps it just short of a 5.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (555 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/audio-transcriber/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.