text-to-speech

Generate speech audio from text using HeyGen's Starfish TTS model. Use when: (1) Generating standalone speech audio files from text, (2) Converting text to speech with voice selection, speed, and pitch control, (3) Creating audio for voiceovers, narration, or podcasts, (4) Working with HeyGen's /v1/audio endpoints, (5) Listing available TTS voices by language or gender.

Quality

88%

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

77%

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

The body is highly actionable with executable code and a clear workflow plus a sample-first feedback loop, but it is verbose from triple-language duplication and monolithic rather than split across reference files. Splitting the full API reference and per-language snippets into a references/ file would improve both conciseness and progressive disclosure.

Suggestions

Pick one primary language (e.g. curl) inline and move the TypeScript/Python snippets and full interface definitions into a references/ file, linked one level deep, to reduce duplication.

Move the verbatim response-format JSON blocks and the ElevenLabs settings table into a separate API reference file, keeping SKILL.md as a concise overview + workflow.

Trim the separate 'Usage Examples' section, which repeats calls already shown under each endpoint, to a single end-to-end example like 'Find a Voice and Generate Audio'.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material with no padding about concepts Claude already knows, but it duplicates each endpoint across curl, TypeScript, AND Python (six code blocks plus interface definitions and repeated 'Usage Examples'), which could be tightened to one or two languages.	2 / 3
Actionability	Fully executable curl/TypeScript/Python snippets, a concrete request-fields table with types and ranges, realistic examples (speed 1.1, locale pt-BR), and verbatim response JSON — copy-paste ready.	3 / 3
Workflow Clarity	The 'Default Workflow' is a clear 4-step sequence, and the 'Expressive Voice Direction' section adds an explicit feedback loop: generate a sample first and 'do not batch-generate the rest if the sample sounds flat, rushed, or ignores the intended breaks.'	3 / 3
Progressive Disclosure	Well-organized with headers and tables, but it is a single ~370-line monolithic file with no bundle files; full interface definitions, multi-language code, and response formats that could live in one-level-deep reference files are all inlined.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 states both capability and trigger conditions with an explicit 'Use when' clause. It carves out a distinct niche (standalone HeyGen Starfish TTS) with natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate speech audio from text', 'voice selection, speed, and pitch control', 'Listing available TTS voices by language or gender' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Generate speech audio from text using HeyGen's Starfish TTS model') and when via an enumerated 'Use when: (1)... (5)' clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'text to speech', 'voiceovers, narration, or podcasts', 'TTS voices' — alongside technical triggers like '/v1/audio endpoints'.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'HeyGen's Starfish TTS model' and '/v1/audio endpoints' for 'standalone speech audio', a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/text-to-speech/SKILL.md
Commit: 0af32ce

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.