audio-transcriber

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

Quality

46%

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/agentic-awesome-skills

Quality

Content

40%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 a clean overview that delegates the real procedure to the detailed guide, but it provides no executable guidance or sequenced workflow itself — only illustrative input/output mockups. Progressive disclosure is good yet incomplete because tools-comparison.md and the scripts are not linked from the overview. Tightening the mockup examples and surfacing the orphaned bundle files would raise the score.

Suggestions

Add a brief "Quick start" with the actual invocation command(s) or a one-line pointer to the executable script (e.g. scripts/transcribe.py), so the body is actionable without forcing a full guide read.

Link the remaining bundle files from the body: a "Tool selection" pointer to references/tools-comparison.md and a "Setup" pointer to scripts/install-requirements.sh.

Trim the emoji/progress-bar decoration in the example outputs to reduce token cost while preserving the input→output shape, and add an explicit validation/verify step for batch runs.

Dimension	Reasoning	Score
Conciseness	No padding with concepts Claude already knows, but the example blocks are long mockup terminal outputs decorated with emoji progress bars and separator lines that could be trimmed. Not 4 because the decorated mockups exceed minor over-explanation.	3 / 5
Actionability	The body contains only illustrative `copilot>` user inputs and mock outputs — no executable code or real commands — with all actual execution delegated to the referenced guide. Matches anchor 2 (minimal concrete guidance, missing specific steps) and not 3 because no executable or pseudocode steps appear in the body itself.	2 / 5
Workflow Clarity	No sequenced steps or validation checkpoints are present in the body; the skill performs batch operations (Example 3) yet shows no validation, and the batch-cap guideline would limit this to 3 even if steps existed. Not 3 because the body lists no actual workflow steps, only example shapes.	2 / 5
Progressive Disclosure	A clear one-level-deep pointer to references/detailed-guide.md is present, but references/tools-comparison.md and the scripts/ files are never signaled from the body, leaving bundle files orphaned from overview navigation. Not 5 because not all bundle files are well-signaled from the overview.	4 / 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 domain and purpose but is missing an explicit "Use when…" trigger clause and the natural terms users would actually say (notably "transcribe"). Buzzwords like "intelligent summaries" and "LLM integration" slightly dilute specificity. Adding concrete trigger phrases and action verbs would lift the completeness and trigger-term scores.

Suggestions

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

Swap buzzwords ("intelligent summaries using LLM integration") for concrete actions like "generates meeting minutes, executive summaries, and SRT/VTT captions with speaker diarization".

Include natural terms and file extensions users say: "transcribe", "audio to text", "speech-to-text", "MP3, WAV, M4A".

Dimension	Reasoning	Score
Specificity	"Transform audio recordings into professional Markdown documentation" names the domain with ~2 concrete actions (convert to Markdown, summarize), but "intelligent summaries using LLM integration" is buzzword-flavored and coverage is thin (no diarization, subtitles, batch). Not 4 because it does not list several specific concrete actions.	3 / 5
Completeness	Gives a clear "what" (transform audio into Markdown docs with summaries) but no "Use when…" trigger clause; the rubric caps completeness at 3 when explicit trigger guidance is absent. Not 4 because "when" is fully missing rather than merely imprecise.	3 / 5
Trigger Term Quality	Contains "audio recordings", "summaries", and "Markdown documentation" but omits the most natural user terms ("transcribe", "audio to text", "meeting minutes", "speech-to-text") and any file extensions. Not 4 because natural phrasings users actually say are missing.	3 / 5
Distinctiveness Conflict Risk	Audio-to-Markdown transcription is a distinct niche with low conflict risk, though "intelligent summaries using LLM integration" lightly overlaps general summarization skills. Not 5 because the description lacks explicit distinct trigger phrases.	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: 652629d

Reviewed: ~12 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.