transcribe

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

4.42x

Quality

85%

Does it follow best practices?

Impact

93%

4.42x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

82%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, highly actionable, and uses progressive disclosure with a clearly signaled reference file and a bundled CLI. The main weaknesses are minor repetition of API-key guidance and slightly vague validation criteria in the workflow.

Suggestions

Consolidate the OPENAI_API_KEY guidance into a single Environment section instead of restating it in Workflow step 2 and the Environment bullets.

Make the workflow's validation step more concrete, e.g. specify how to inspect diarized_json output for empty segments or mislabeled speakers before iterating.

Consider moving the detailed model/flag decision rules into references/api.md and keeping a one-line default in the body to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with well-organized sections and executable examples, but the OPENAI_API_KEY guidance is repeated across the Workflow, Environment, and related sections, a minor instance of over-explanation that could be consolidated.	4 / 5
Actionability	Copy-paste-ready CLI commands cover the common cases (single-file text, diarization with up to four known speakers, explicit plain text), and decision rules give specific model names and flags, matching the fully-executable top anchor.	5 / 5
Workflow Clarity	The five-step workflow includes a validation checkpoint ("Validate the output... iterate with a single targeted change if needed") with a feedback loop, but the validation criteria ("transcription quality, speaker labels, and segment boundaries") are somewhat vague about how to check them.	4 / 5
Progressive Disclosure	A "Reference map" section clearly signals the one-level-deep references/api.md, and the CLI script is kept in scripts/; structure is good, though some inlined decision rules and examples could arguably live in the reference file.	4 / 5
	Total	17 / 20 Passed

Description

87%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 is third-person, concise, and clearly answers both what the skill does and when to use it, with strong natural trigger phrases. Minor gaps in specificity (no exhaustive action enumeration) and trigger terms (no file extensions) keep two dimensions at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	"Transcribe audio files to text with optional diarization and known-speaker hints" names the domain plus several concrete actions (transcribe, diarize, known-speaker hints), with only minor coverage gaps; not as comprehensive as the score-5 anchor's exhaustive action list.	4 / 5
Completeness	It explicitly states both what it does ("Transcribe audio files to text with optional diarization and known-speaker hints") and when to use it ("Use when a user asks to transcribe speech from audio/video...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases like "transcribe speech from audio/video", "extract text from recordings", and "label speakers in interviews or meetings" give good keyword coverage with synonyms, though file extensions (.mp3, .wav) are absent.	4 / 5
Distinctiveness Conflict Risk	The transcription/speaker-labeling niche with triggers like "label speakers in interviews or meetings" is clearly distinct from other skills and carries minimal overlap risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/transcribe/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.