elevenlabs-transcribe

Transcribe audio to text using ElevenLabs Scribe. Supports batch transcription, realtime streaming from URLs, microphone input, and local files.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tiles/elevenlabs/skills/elevenlabs-transcribe/skill/SKILL.md

Quality

Content

76%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 actionable and well-structured with executable commands pointing to real bundle scripts, but it lacks explicit verification steps for a batch operation. Adding an output-validation checkpoint would raise workflow clarity.

Suggestions

Add an explicit verification step for batch runs, e.g. 'Check the script's exit status before using the output; on non-zero exit, review the stderr message and retry.'

Consolidate the Examples and 'When to Use Each Mode' table to remove redundancy and tighten conciseness.

Surface the key output sanity-checks (non-empty text, expected language_code) so Claude can confirm a transcription succeeded before returning it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what audio or transcription is), with only minor redundancy between the Examples section and the closing 'When to Use Each Mode' table that could be trimmed.	4 / 5
Actionability	Commands like '{baseDir}/scripts/transcribe.sh recording.mp3 --diarize --json' are fully executable, reference real bundle scripts, and the examples cover the common cases (batch, diarize, JSON, URL, mic, realtime, quiet).	5 / 5
Workflow Clarity	Usage is well illustrated and an Error Handling section exists, but this batch-processing skill has no explicit validation/verification checkpoint (e.g. confirm output, check exit status before use), so workflow clarity is capped at 3 per the rubric guidelines.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-organized sections and one-level-deep references to real bundle scripts ({baseDir}/scripts/transcribe.sh), with the heavy logic appropriately split out; minor organization gaps (Examples vs. When-to-Use redundancy) keep it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

66%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 clearly states what the skill does and names several concrete capabilities, but lacks any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause with natural synonyms would lift completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when transcribing audio, generating speech-to-text output, or when the user mentions transcription, subtitles, or voice recordings.'

Include natural synonyms like 'speech-to-text' and 'voice' to broaden trigger-term coverage.

Tighten the capability list into distinct actions (e.g. 'transcribe files, stream live audio, capture microphone input') to push specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'batch transcription, realtime streaming from URLs, microphone input, and local files' — giving broad coverage of input modes, though they read more as modes than distinct actions, leaving minor gaps versus the comprehensive anchor 5.	4 / 5
Completeness	The 'what' is clear ('Transcribe audio to text using ElevenLabs Scribe'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Natural terms like 'transcribe', 'transcription', and 'audio to text' are present, but common synonyms such as 'speech-to-text' and 'voice' that users would also say are missing.	4 / 5
Distinctiveness Conflict Risk	The ElevenLabs Scribe branding carves a clear niche, though it could still overlap with other speech-to-text/transcription skills, leaving minor conflict risk.	4 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: neil-tessl/skill-index-evals-dev
Path: tiles/elevenlabs/skills/elevenlabs-transcribe/skill/SKILL.md
Commit: 2bad92e

Reviewed: 10 days 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.