audio-transcriber

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

Quality

53%

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/antigravity-audio-transcriber/SKILL.md

The canonical home for this skill is audio-transcriber in sickn33/antigravity-awesome-skills

Quality

Content

50%

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

The skill supplies concrete tooling and a workable transcription flow, but it is verbose, leans on placeholder functions for the LLM summarization step, and has a workflow with missing step numbers and weak linkage to its own bundle files.

Suggestions

Replace the placeholder functions (call_ai_model, cluster_by_topic, extract_action_items) with concrete, runnable implementations or explicitly justify them as integration points.

Fix the step sequence to include the actual transcription step (currently Step 2 is missing) and add per-file validation/checkpoints for the batch path.

Trim the mock terminal-output blocks and link tools-comparison.md and transcribe.py from the body so the bundle structure is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body provides executable code but is padded with lengthy mock terminal output blocks (emoji success messages, boxed prompt previews) and some non-essential prose (Plaud inspiration, platform-agnostic restatement) that could be trimmed without losing clarity.	2 / 3
Actionability	It includes concrete, runnable bash and python snippets (ffprobe, ffmpeg, faster-whisper detection), but the summarization path relies on undefined placeholders like call_ai_model(), cluster_by_topic(), and extract_action_items() rather than executable code.	2 / 3
Workflow Clarity	Steps are labeled and some validation exists (file existence, format conversion, install verification), but the step numbering skips (Step 0, 1, 3, 5 with no Step 2 transcription step) and the batch example lacks per-file validation checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	Bundle files exist (references/tools-comparison.md, scripts/transcribe.py, scripts/install-requirements.sh) and install-requirements.sh is referenced, but tools-comparison.md and transcribe.py are not linked from the body, and large inline mock-output content that could be separated keeps organization at the partial anchor.	2 / 3
	Total	8 / 12 Passed

Description

57%

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, specific purpose and a distinct niche, but it lacks an explicit use-when trigger clause and is missing the most natural user trigger terms like "transcribe".

Suggestions

Append a "Use when..." clause listing natural triggers (e.g., transcribe audio, convert audio to text, generate meeting notes from a recording, MP3/WAV/M4A files).

Add the word "transcribe" and common file-format keywords to the description so trigger-term quality reaches the natural-coverage anchor.

Expand the action list slightly (diarization/speaker identification, SRT/VTT captions) to make the capability set more comprehensive.

Dimension	Reasoning	Score
Specificity	Names the audio domain and concrete actions ("Transform audio recordings into professional Markdown documentation" and "intelligent summaries") but the action set is compressed rather than comprehensive (no mention of diarization, captions, or batch).	2 / 3
Completeness	It clearly states what the skill does but provides no explicit "Use when..." trigger clause, so the "when" guidance is only implied; per the rubric a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some relevant terms ("audio recordings", "Markdown documentation", "summaries") but omits the most natural trigger words users would say, notably "transcribe" and common formats like "MP3" or "meeting notes".	2 / 3
Distinctiveness Conflict Risk	The audio-to-Markdown transcription niche with LLM summaries is clearly scoped and unlikely to fire for unrelated skills, matching the distinct-niche anchor.	3 / 3
	Total	9 / 12 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: boisenoise/skills-collections
Path: skills/antigravity-audio-transcriber/SKILL.md
Commit: 04c2ce5

Reviewed: about 6 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.