audio-transcriber

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

Quality

23%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/audio-transcriber/SKILL.md

Quality

Content

14%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is excessively verbose and poorly organized, with missing critical workflow steps (the actual transcription step is absent), inconsistent step numbering, undefined placeholder functions, and mixed languages. While it demonstrates ambition in scope (metadata extraction, diarization, meeting minutes, batch processing), the content fails to deliver actionable, well-structured guidance that Claude can reliably follow. The skill would benefit from a complete rewrite focused on the core workflow with proper step sequencing and concrete implementations.

Suggestions

Add the missing Step 2 (actual transcription execution) and Step 4, and fix step numbering to be sequential—the core transcription logic is entirely absent from the workflow.

Replace placeholder functions (call_ai_model, cluster_by_topic, extract_action_items, extract_decisions) with concrete implementations or remove them and describe the actual approach Claude should take.

Reduce content by 60-70%: remove terminal UI mockups, trim examples to 1-2 representative cases, eliminate installation flows (move to a separate INSTALL.md), and remove explanations of obvious concepts.

Split content into supporting files: move the output template to TEMPLATE.md, installation to INSTALL.md, and examples to EXAMPLES.md, keeping SKILL.md as a concise overview with clear references.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Explains obvious concepts (what audio formats are, how file validation works), includes extensive UI mockups for terminal output, mixes languages (Portuguese/English), and repeats information. Much of this content (installation flows, progress bar displays, batch processing examples) is unnecessary for Claude, who already understands these patterns.	1 / 3
Actionability	Contains concrete bash and Python code snippets for detection, validation, and processing, but critical pieces are pseudocode or placeholders (e.g., `call_ai_model()`, `cluster_by_topic()`, `extract_action_items()` are undefined). The actual transcription step (Step 2) appears to be missing entirely—it jumps from Step 1 (validation) to Step 3 (generate output), leaving the core transcription logic absent.	2 / 3
Workflow Clarity	The workflow is disorganized: steps are numbered inconsistently (Step 0, 1, 3, 5—missing Steps 2 and 4), the core transcription step is absent, and scenarios (custom prompt, LLM processing) are introduced mid-flow without clear sequencing. There are no validation checkpoints between transcription and output generation, and the batch processing example lacks any error handling or verification steps.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files despite mentioning scripts like `scripts/install-requirements.sh`. The massive output templates, multiple usage examples, and installation flows should be split into separate reference files. No bundle files are provided to support the referenced paths, and the inline content is overwhelming.	1 / 3
	Total	5 / 12 Passed

Description

32%

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 identifies a specific workflow (audio to Markdown) but relies on buzzword-heavy language ('professional', 'intelligent', 'LLM integration') rather than concrete actions. It critically lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill, and misses common trigger terms users would naturally use like 'transcribe' or 'meeting notes'.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to transcribe audio files, convert recordings to text, or generate meeting notes from audio.'

Include natural trigger terms users would say, such as 'transcribe', 'transcription', 'meeting notes', 'voice memo', '.mp3', '.wav', 'speech-to-text'.

Replace vague qualifiers ('professional', 'intelligent') with concrete actions, e.g., 'Transcribes audio files to text, generates structured Markdown notes with section headings, and produces concise summaries of key points.'

Dimension	Reasoning	Score
Specificity	Names the domain (audio recordings to Markdown documentation) and mentions some actions (transform, summaries, LLM integration), but lacks specific concrete actions like 'transcribe speech', 'generate timestamps', 'extract key points', etc.	2 / 3
Completeness	Describes what the skill does (transform audio to Markdown with summaries) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately clear, warranting a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'audio recordings', 'Markdown documentation', and 'summaries', but misses common user-facing terms like 'transcribe', 'transcription', 'meeting notes', 'voice memo', '.mp3', '.wav', or 'speech-to-text'.	2 / 3
Distinctiveness Conflict Risk	The combination of audio-to-Markdown is somewhat distinctive, but 'professional Markdown documentation' and 'intelligent summaries' are broad enough to potentially overlap with general documentation or summarization skills.	2 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (560 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: sickn33/antigravity-awesome-skills
Commit: 9431b67

Reviewed: 3 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.