audio-transcriber
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
37
23%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-audio-transcriber/SKILL.mdQuality
Discovery
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 clear domain (audio-to-documentation) but relies on buzzwordy language ('intelligent summaries', 'professional Markdown documentation', '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. The trigger terms are insufficient, missing common user phrases like 'transcribe', 'meeting notes', or audio file extensions.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks to transcribe audio, convert recordings to text, create meeting notes from audio files, or mentions .mp3, .wav, or .m4a files.'
Replace vague phrases like 'intelligent summaries using LLM integration' with concrete actions such as 'transcribe speech to text, generate section headings, extract action items, and summarize key discussion points.'
Include common user-facing trigger terms like 'transcribe', 'transcription', 'meeting notes', 'voice memo', 'speech-to-text', and specific audio file extensions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (audio recordings) and some actions (transform, summaries), but lacks specific concrete actions like 'transcribe speech', 'generate timestamps', 'extract key points', or 'format as meeting notes'. 'Professional Markdown documentation' and 'intelligent summaries' are somewhat vague. | 2 / 3 |
Completeness | It describes what the skill does (transforms 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 the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also somewhat weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'audio recordings', 'Markdown', and 'summaries', but misses common user terms like 'transcribe', 'transcription', 'meeting notes', 'voice memo', '.mp3', '.wav', 'speech-to-text', or 'recording'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of audio + Markdown + LLM summaries is somewhat distinctive, but 'professional Markdown documentation' could overlap with general documentation skills, and 'intelligent summaries using LLM integration' is vague enough to conflict with summarization skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
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, poorly organized, and incomplete in critical areas. The workflow has missing steps (the actual transcription is never defined), broken numbering, and key functions are left as undefined placeholders. The content mixes languages, includes unnecessary terminal UI mockups, and would benefit enormously from being split into multiple files with a concise overview in SKILL.md.
Suggestions
Add the missing Step 2 (actual transcription execution) and Step 4, and fix step numbering to create a complete, sequential workflow
Replace placeholder functions (call_ai_model, cluster_by_topic, extract_action_items) with actual executable implementations or remove them
Reduce SKILL.md to a concise overview (~50-80 lines) and move installation instructions, output templates, examples, and LLM processing details into separate referenced files
Add explicit validation checkpoints between steps, especially for batch processing (e.g., verify each file before proceeding, handle partial failures)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Explains obvious concepts (what audio formats are, how to check if a file exists), includes extensive UI mockups for terminal output, mixes languages (Portuguese/English), and repeats information. Much of this content (installation scripts, progress bar mockups, multiple example outputs) is unnecessary padding that Claude doesn't need. | 1 / 3 |
Actionability | Contains concrete bash and Python code snippets, 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 (Validate) to Step 3 (Generate Markdown). The LLM integration code references tools inconsistently. | 2 / 3 |
Workflow Clarity | The workflow is disorganized and incomplete. Step numbering is broken (Step 0, Step 1, Step 3, Step 5—missing Steps 2 and 4). The core transcription step is absent. Scenarios A appears without a Scenario B introduction. There are no validation checkpoints between steps, and batch processing is shown in examples but has no workflow guidance or error recovery. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite the content being far too long for a single SKILL.md. Installation instructions, output templates, multiple examples, and LLM processing details should all be in separate referenced files. The inline content is overwhelming and poorly organized. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
81%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
- boisenoise/skills-collections
- Commit
431bfad
- 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.