fish-audio-tts

Generate expressive, multilingual narration with fish.audio (S1 / S2-generation models) and reuse cloned voices via reference_id. Use when the user prefers fish.audio/Fish Audio TTS, wants a specific playground voice model, or needs high-emotion voice-clone narration.

Quality

85%

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

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.

A well-structured, highly actionable TTS skill body with executable examples and an approval-gated workflow. Time-sensitive pricing/date detail inline and a missing in-workflow error-recovery loop are the main refinement opportunities.

Suggestions

Move the time-sensitive promo-window date and pricing caveats into a clearly labeled 'Deprecated / promotional' or 'Pricing & promo' subsection so the core guidance stays evergreen and lean.

Add a brief validate-then-retry feedback step inside the Recommended Workflow (e.g. on 401/404, fix the key/reference_id and re-run the sample) rather than only covering errors in a separate Troubleshooting section.

Consider extracting the full backend-model and pricing tables into a references file, keeping SKILL.md as a concise overview that links one level deep.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no boilerplate explaining TTS — but the time-sensitive promo-window detail (the August 31, 2026 date and pricing caveats) sits inline rather than in a deprecated/old-patterns section, adding tokens that could be trimmed.	4 / 5
Actionability	Two complete, executable Python examples with imports and exact parameters, plus a concrete HTTP call spec and specific error-code troubleshooting, make the guidance copy-paste ready for the common cases.	5 / 5
Workflow Clarity	The 'Recommended Workflow' gives a clear numbered sequence with an explicit approval checkpoint before full paid narration, but it lacks an error-recovery feedback loop (validation failures route to the separate Troubleshooting section).	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and no nested references; self-contained with no external bundle files needed, though contract/pricing detail could arguably be split out for a leaner overview.	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.

A strong, third-person description that clearly states capabilities and provides explicit trigger guidance with natural synonyms. Minor gains possible from broader synonym coverage and enumerating more concrete actions.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'Generate expressive, multilingual narration' and 'reuse cloned voices via reference_id' — plus the model generations (S1/S2), but coverage is two core actions rather than a comprehensive list.	4 / 5
Completeness	Explicitly answers both 'what' (generate multilingual narration, reuse cloned voices via reference_id) and 'when' ('Use when the user prefers fish.audio/Fish Audio TTS, wants a specific playground voice model, or needs high-emotion voice-clone narration') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms users would say appear with synonyms — 'fish.audio'/'Fish Audio TTS', 'playground voice model', 'high-emotion voice-clone narration' — but a few common phrasings (e.g. 'text-to-speech', 'voice cloning') are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche — fish.audio TTS with reference_id voice cloning and emotion tags — with provider-specific triggers that minimize overlap with other TTS skills.	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: calesthio/OpenMontage
Path: .agents/skills/fish-audio-tts/SKILL.md
Commit: 08e2151

Reviewed: 2 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.