fal-audio

Text-to-speech and speech-to-text using fal.ai audio models

Quality

25%

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 ./skills/fal-audio/SKILL.md

Quality

Content

11%Scale 1-5

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

This skill is essentially a placeholder with no actionable content. It repeats its description three times across three sections and provides no code, commands, API details, model names, or workflow steps. The only useful element is a link to an external repository, making this skill nearly useless as standalone guidance.

Suggestions

Add concrete code examples for both TTS and STT using fal.ai's API, including the specific model endpoints (e.g., fal-ai/wizper for STT, fal-ai/metavoice-v1 for TTS) and executable Python snippets.

Provide a clear workflow with steps: install fal client, set API key, submit request, handle response/output file.

Remove the redundant 'When to Use' and 'Instructions' sections that just restate the overview, and replace them with actual technical content.

If detailed content belongs in separate files, create bundle files and reference them; otherwise inline the essential patterns directly in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The content is padded with repetitive statements that add no value — the overview, 'when to use' section, and instructions all say essentially the same thing. However, it's short enough that it's not severely verbose, just noticeably redundant.	2 / 5
Actionability	There is zero concrete guidance — no code, no commands, no API endpoints, no model names, no examples. It merely describes the topic without providing any executable or actionable instructions.	1 / 5
Workflow Clarity	No steps, no sequence, no workflow of any kind is provided. There is nothing to follow for either TTS or STT tasks.	1 / 5
Progressive Disclosure	There is a link to an external source repository, but no bundle files exist and the SKILL.md itself contains no substantive content to organize. The external link is essentially a redirect with no local content to support it.	2 / 5
	Total	6 / 20 Passed

Description

39%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 too terse and lacks actionable detail. While it identifies the domain (TTS/STT) and the specific platform (fal.ai), it fails to list concrete actions and entirely omits a 'Use when...' clause, making it difficult for Claude to reliably select this skill from a large pool. The distinctiveness from mentioning fal.ai is a strength, but the description needs significantly more detail.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks to transcribe audio, generate speech, convert text to voice, or mentions TTS, STT, or fal.ai audio.'

List specific concrete actions such as 'Generates speech audio from text input, transcribes audio files to text, supports multiple voices and languages.'

Include common synonyms and natural terms users would say: 'TTS', 'STT', 'transcribe', 'voice generation', 'audio transcription', 'dictation', and relevant file extensions like '.mp3', '.wav'.

Dimension	Reasoning	Score
Specificity	Names the domain (text-to-speech and speech-to-text) and the platform (fal.ai), but does not list any concrete actions beyond the two high-level capabilities. No mention of specific operations like 'transcribe audio files', 'generate speech from text', 'convert audio formats', etc.	2 / 5
Completeness	Provides a vague 'what' (text-to-speech and speech-to-text using fal.ai) but has no 'when' clause at all. There is no 'Use when...' guidance or trigger phrases to help Claude know when to select this skill.	2 / 5
Trigger Term Quality	Includes relevant keywords like 'text-to-speech', 'speech-to-text', and 'fal.ai audio models', but misses common natural language variations users would say such as 'TTS', 'STT', 'transcribe', 'transcription', 'voice synthesis', 'audio generation', 'convert speech', or file extensions like '.mp3', '.wav'.	3 / 5
Distinctiveness Conflict Risk	The mention of 'fal.ai audio models' provides a fairly distinct niche, and the combination of TTS/STT with a specific platform reduces overlap risk. However, it could still conflict with other audio processing or transcription skills if they exist.	4 / 5
	Total	11 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/fal-audio/SKILL.md
Commit: 57c135b

Reviewed: 3 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.