audio-transcriber

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

Quality

43%

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

Quality

Content

32%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 body is well-structured as an overview and correctly delegates the procedure to a real, one-level-deep reference, but it spends most of its tokens on simulated terminal output instead of executable guidance. A user following the body alone would know when to invoke the skill but not a single concrete command to run.

Suggestions

Replace or drastically trim the mock terminal transcripts; keep one short input/output example and move the rest to an examples reference file.

Include at least one executable entry point in the body, e.g. `python scripts/transcribe.py input.mp3` or the guide's key command, so the skill is actionable without loading the reference.

Add a reference to references/tools-comparison.md (e.g. "**Tool selection**: See [tools-comparison.md](references/tools-comparison.md)") so the bundle file is discoverable, and surface the batch error/validation behavior (what happens when file 3 of 5 fails).

Dimension	Reasoning	Score
Conciseness	Roughly two-thirds of the body is simulated terminal output — "[████████████████████] 100%", "✅ Transcription Complete!", "🎯 Next steps:" — padded mock transcripts that teach little Claude cannot infer. Not a 3 because multiple full example blocks (Examples 1, 3, 5) repeat the same padding pattern rather than a few isolated instances.	2 / 5
Actionability	The only instruction is "Read [the detailed guide](references/detailed-guide.md) before executing this skill"; the body contains no executable command, code, or concrete step, and the example "user inputs" are Copilot CLI prompts rather than anything Claude can run. Not a 3 because the body offers only high-level pointers — all executable content lives in the reference file, and even a one-line example command or the script path (`scripts/transcribe.py`) is absent.	2 / 5
Workflow Clarity	No step sequence appears in the body — the workflow exists only in the referenced guide, and validation is absent here even though the skill demonstrates batch processing ("📦 Batch mode: 5 files found"), which caps workflow_clarity at 3. Not a 3 because beyond "read the guide first" there is no enumerated sequence, no checkpoints, and no per-file error-recovery guidance for the batch case.	2 / 5
Progressive Disclosure	The body is a genuine overview with well-labeled sections (Detailed Guide, When to Use, Example Usage, Limitations) and a clearly signaled, one-level-deep reference to references/detailed-guide.md, which exists and holds the full procedure; scripts/transcribe.py and scripts/install-requirements.sh are real bundle files used by the guide. Not a 5 because references/tools-comparison.md is present in the bundle but never linked from SKILL.md, leaving it undiscoverable, and the oversized examples section is content that belongs in a separate examples file.	4 / 5
	Total	10 / 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 communicates a clear, single-sentence capability statement in third person, but it omits any "when to use" trigger guidance and lacks the natural keywords (transcribe, speech-to-text, meeting minutes) that would help activation. It sits at the midpoint: accurate but under-specified relative to the good examples.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to transcribe audio, convert speech to text, or generate meeting minutes from recordings."

Include natural synonyms and concrete artifacts in the description — transcribe, speech-to-text, meeting minutes, subtitles (SRT/VTT), and common formats (MP3, WAV, M4A).

Replace the vague "intelligent summaries using LLM integration" with a concrete capability such as "generates speaker-identified meeting minutes and executive summaries".

Dimension	Reasoning	Score
Specificity	"Transform audio recordings into professional Markdown documentation" and "intelligent summaries using LLM integration" name the domain plus two concrete actions, but coverage is not comprehensive — diarization, subtitles, and supported formats named in the body are absent. Not a 4 because the actions described are few and "intelligent summaries using LLM integration" leans toward generic phrasing rather than a specific capability.	3 / 5
Completeness	The "what" is clear (audio → professional Markdown documentation with summaries), but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not a 4 because the "when" is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	"audio recordings" is a natural user term, but the common phrases users actually say — "transcribe", "speech-to-text", "meeting minutes/notes", file extensions like .mp3 — are missing from the description. Not a 4 because the keyword set is thin and lacks synonyms or variations beyond the single phrase "audio recordings".	3 / 5
Distinctiveness Conflict Risk	Audio transcription to Markdown reports is a clear niche with limited overlap against generic document or summarization skills. Not a 5 because "intelligent summaries using LLM integration" could overlap with general summarization skills and no distinct trigger phrases sharpen the boundary.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: boisenoise/skills-collections
Path: skills/antigravity-audio-transcriber/SKILL.md
Commit: 690de8f

Reviewed: 5 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.