CtrlK
BlogDocsLog inGet started
Tessl Logo

fal-audio

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

42

Quality

43%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/fal-audio/SKILL.md

The canonical home for this skill is fal-audio in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

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-organized and lean but nearly content-free: it offers no executable guidance, no real workflow, and only defers to an external repository, which tanks actionability and workflow clarity.

Suggestions

Add a concrete quick-start example, e.g. a fal.ai API call or CLI snippet for TTS and speech-to-text, so the skill is actionable without leaving SKILL.md.

Replace the repeated capability sentence in Overview/Instructions with a concise step sequence (choose model, submit input, retrieve output) and a validation check on the returned audio.

Inline the most essential setup (authentication, endpoint, model ids) and keep the external link as a secondary reference rather than the sole source of instruction.

DimensionReasoningScore

Conciseness

The body is short and avoids explaining concepts Claude already knows, but the same capability phrase is repeated nearly verbatim across Overview, When to Use, and Instructions, which is unnecessary padding that could be tightened.

3 / 5

Actionability

The Instructions section only states it "provides guidance and patterns" and links to an external repo; there is no concrete code, command, or executable guidance, matching the "entirely vague or abstract; only describes rather than instructs" anchor.

1 / 5

Workflow Clarity

A rough direction is implied (use fal.ai for TTS/STT, see the source) but there are no defined steps and no validation; this fits the "rough sequence present but many gaps; steps poorly defined" anchor better than the incoherent 1.

2 / 5

Progressive Disclosure

The under-50-line body is cleanly sectioned (Overview, When to Use, Instructions) with one clearly signaled one-level reference to the source repo, but the reference points outside the bundle and the body carries no real split content, so it stops short of the well-populated 5 anchor.

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 is concise and names a specific platform niche, but it lacks an explicit "Use when..." trigger and natural-term synonyms, leaving it mid-tier across most dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete user phrases (e.g., 'Use when the user wants to generate speech from text or transcribe audio via fal.ai').

Include common synonyms and abbreviations users actually say, such as TTS, STT, transcription, and voice generation.

Broaden the capability list beyond the two directions (e.g., supported formats, voices, or streaming) to improve specificity and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain (audio) and two concrete capability directions ("text-to-speech and speech-to-text"), which matches the anchor naming 1-2 concrete actions, but coverage is not comprehensive (no transcription, voice cloning, format details).

3 / 5

Completeness

The description states a clear "what" but contains no "Use when..." trigger clause; per the judging guideline a missing explicit trigger caps completeness at 3, and it does not rise to 4 which requires both what and when.

3 / 5

Trigger Term Quality

Includes relevant natural keywords ("text-to-speech", "speech-to-text", "audio") but misses common variations and synonyms a user might say (TTS, STT, transcription, voice), matching the "some relevant keywords but missing common variations" anchor.

3 / 5

Distinctiveness Conflict Risk

Scoping to "fal.ai audio models" gives it a clear provider niche with only minor overlap risk against other audio/TTS skills, fitting "mostly distinct; minor overlap risk" rather than the broad 3 anchor.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.