audio-transcriber
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill audio-transcriber50
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 85%
↑ 2.17xAgent success when using this skill
Validation for skill structure
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 conversion) but suffers from missing explicit trigger guidance and incomplete natural keyword coverage. It would benefit significantly from a 'Use when...' clause and more specific action verbs and file type mentions to help Claude reliably select this skill.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user wants to transcribe audio, convert voice recordings to text, or create meeting notes from audio files'
Include natural file type keywords users would mention: '.mp3', '.wav', 'voice memo', 'meeting recording', 'podcast', 'transcription'
List more specific concrete actions: 'transcribe speech', 'generate timestamps', 'extract action items', 'format speaker labels'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (audio recordings, Markdown documentation) and mentions some actions (transform, summaries), but lacks comprehensive concrete actions like 'transcribe', 'format timestamps', 'extract key points', or specific documentation features. | 2 / 3 |
Completeness | Describes what it does (transform audio to documentation) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms ('audio recordings', 'Markdown documentation', 'summaries') but misses common user variations like 'transcribe', 'meeting notes', 'voice memo', 'audio file', '.mp3', '.wav', or 'speech-to-text'. | 2 / 3 |
Distinctiveness Conflict Risk | The audio-to-documentation niche is somewhat specific, but 'Markdown documentation' and 'summaries' could overlap with general documentation or summarization skills. The audio focus provides some distinction but lacks explicit file type triggers. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity, including excessive inline code, redundant examples, and explanations of concepts Claude already knows. The workflow is fragmented with missing steps (Step 2 not present) and inconsistent numbering. While it provides some actionable code, key functions are undefined placeholders, and the lack of progressive disclosure makes it difficult to navigate.
Suggestions
Reduce content by 60%+ by removing redundant bash examples, consolidating similar code patterns, and eliminating explanations of basic concepts like file validation
Fix workflow numbering (Steps 0, 1, 3, 5 are present but Step 2 is missing) and provide a clear sequential flow with explicit validation checkpoints
Move lengthy code examples to separate reference files (e.g., SCRIPTS.md, EXAMPLES.md) and keep SKILL.md as a concise overview with links
Replace placeholder functions like `call_ai_model()`, `cluster_by_topic()`, and `extract_action_items()` with actual implementations or explicit references to where they're defined
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with excessive bash/Python code examples that repeat similar patterns, unnecessary explanations of basic concepts (file validation, format checking), and redundant workflow descriptions. The content could be reduced by 60-70% while maintaining clarity. | 1 / 3 |
Actionability | Contains executable code snippets and concrete commands, but many are incomplete or pseudocode (e.g., `call_ai_model()`, `cluster_by_topic()` are undefined placeholders). The workflow jumps from Step 1 to Step 3, missing Step 2 entirely. | 2 / 3 |
Workflow Clarity | Steps are numbered but inconsistent (jumps from Step 1 to Step 3, then Step 5), and validation checkpoints are present but scattered. The batch processing example lacks explicit validation between files, and the overall flow is hard to follow due to length and fragmentation. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite mentioning scripts like `install-requirements.sh`. All content is inline including lengthy code examples that should be in separate reference files. No clear navigation structure. | 1 / 3 |
Total | 6 / 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 (556 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 | |
- 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.