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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/audio-transcriber/SKILL.md

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 provides a workable, concrete workflow but is held back by verbosity, placeholder Python helpers, a step numbering gap, missing batch-validation feedback loops, and a failure to route detail into the bundled reference/script files that already exist.

Suggestions

Replace the undefined Python helper placeholders (cluster_by_topic, extract_action_items, extract_decisions, call_ai_model) with concrete implementations, or defer to the bundled scripts/transcribe.py with an explicit reference.

Add per-file validation and an error-recovery feedback loop for the batch-processing path, and renumber the steps to eliminate the missing Step 2 and Step 4.

Trim decorative terminal-output/progress-bar examples and consolidate the duplicated inline logic by pointing to scripts/transcribe.py and references/tools-comparison.md instead of restating them.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, padding the instructions with lengthy decorative terminal-output blocks, emoji progress bars, redundant examples (Example 1, 3, 5), and mixed Portuguese/English strings that do not advance Claude's understanding.	2 / 5
Actionability	Bash detection/validation snippets are executable, but the core Python summarization logic relies on undefined placeholder functions (cluster_by_topic, extract_action_items, extract_decisions, call_ai_model), leaving it incomplete rather than copy-paste ready.	3 / 5
Workflow Clarity	Steps are listed but the sequence skips from Step 1 to Step 3 to Step 5 (Step 2 and Step 4 are absent), and the batch-processing capability has no per-file validation or error-recovery feedback loop, which caps this at 3.	3 / 5
Progressive Disclosure	The body references scripts/install-requirements.sh but ignores the existing scripts/transcribe.py implementation and references/tools-comparison.md, instead inlining equivalent code that belongs in those bundled files; structure exists but content is not well split.	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 and a distinct niche but omits explicit trigger guidance and the natural 'transcribe/transcription' vocabulary users would say, leaving it at a middling level across most dimensions.

Suggestions

Add an explicit 'Use when ...' clause with concrete trigger phrases (e.g., 'Use when the user asks to transcribe audio, generate meeting notes, or convert recordings to text').

Include natural user vocabulary such as 'transcribe', 'transcription', 'speech-to-text', 'meeting minutes', and file extensions (mp3, wav, m4a) to improve trigger-term quality.

Expand the action list to cover the skill's actual capabilities (speaker diarization, SRT/VTT subtitles, batch processing) for more comprehensive specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('audio recordings') and 1-2 actions ('Transform ... into professional Markdown documentation', 'intelligent summaries') but does not list the broader concrete capabilities (diarization, SRT/VTT, meeting minutes) it actually supports, so it is not comprehensive.	3 / 5
Completeness	It clearly states 'what' the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('audio recordings', 'summaries', 'LLM integration') but the natural terms users actually say — 'transcribe', 'transcription', 'speech-to-text', 'meeting notes' — are absent despite being the skill's core verbs.	3 / 5
Distinctiveness Conflict Risk	The audio-to-Markdown transcription niche is mostly distinct from other skills with only minor overlap risk with general summarization/documentation skills; it is not yet a fully distinct set of triggers.	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 (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	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/audio-transcriber/SKILL.md
Commit: 1f67c44

Reviewed: about 16 hours 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.