speech

Generate spoken audio from text using OpenAI's API with built-in voices. Useful for narrated explainers, lecture audio, and quick voiceover tracks.

Quality

50%

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/speech/SKILL.md

Quality

Content

47%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.

This is a thin catalogue stub: concise and cleanly organized, but it contains no executable guidance for the skill's task — everything is deferred to an external GitHub URL. Actionability and workflow clarity are the weak points, as an agent cannot perform speech generation from this body alone.

Suggestions

Include a minimal executable example of the core task (e.g. an OpenAI TTS API call or CLI command with voice and output-file arguments) instead of deferring entirely to the upstream URL.

Replace "open https://github.com/openai/skills" with concrete, portable install/inspection commands and exact paths in the upstream repo.

Add a verification step (e.g. confirm the installed skill appears in the agent's skills directory or invoke it with a test phrase) so the workflow has a checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is short and sectioned with no padding or explanation of concepts Claude already knows. Minor trim possible: the "What it does" section repeats the frontmatter description verbatim. Fits anchor 4 (efficient, minor instances that could be trimmed), not anchor 5's every-token-earns-its-place.	4 / 5
Actionability	The only command is "open https://github.com/openai/skills", which is non-portable and does not instruct on the skill's actual task; there is no code or API usage for speech generation. Matches anchor 2 (minimal concrete guidance; high-level hints missing the specific steps), not anchor 3 which requires at least some concrete, if incomplete, guidance.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream README, install bundle, invoke by name or trigger) but the steps are poorly defined — no install commands, no paths, no verification the skill is available. Matches anchor 2 (rough sequence with many gaps); better than anchor 1 because a sequence is at least present.	2 / 5
Progressive Disclosure	No bundle files exist, and the short body is well organized into clearly signaled sections with a single one-level-deep pointer (the upstream repo). Fits anchor 4 (good structure, minor organization gaps) rather than 5, since navigation defers to an external URL instead of local references and the actual skill content is entirely absent.	4 / 5
	Total	12 / 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 gives a clear, concise statement of what the skill does with some natural use-case phrases, but it lacks an explicit "Use when..." trigger clause and misses the most common synonyms (TTS, text-to-speech). It is distinct enough within the audio/music category.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants text-to-speech, narration, or a voiceover for text content."

Include the most common synonyms and phrasings users would say: "TTS", "text-to-speech", "read this aloud", "narration".

Mention one or two more concrete capabilities (e.g. built-in voice options or audio output format) to broaden specificity beyond the single generate action.

Dimension	Reasoning	Score
Specificity	"Generate spoken audio from text using OpenAI's API with built-in voices" names the domain and one concrete action, plus output use cases, but lists no further specific actions (voice selection, formats, parameters). Matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive), not anchor 4 which requires several specific listed actions.	3 / 5
Completeness	The 'what' is clear (generate spoken audio from text via OpenAI's API), but 'when' guidance appears only as an application list ("Useful for narrated explainers, lecture audio, and quick voiceover tracks") rather than an explicit "Use when..." trigger clause. Per the guideline capping completeness at 3 without an explicit trigger clause, this is 3 rather than 4.	3 / 5
Trigger Term Quality	Natural phrases like "narrated explainers", "lecture audio", and "voiceover tracks" are present, but the most common user terms — "TTS", "text-to-speech", "read aloud" — are missing. Fits anchor 3 (relevant keywords but missing common variations or synonyms), not anchor 4's good coverage with only a few gaps.	3 / 5
Distinctiveness Conflict Risk	OpenAI-API text-to-speech is a clear niche with distinct triggers; only minor overlap risk with other audio/music skills. Matches anchor 4 (mostly distinct, minor overlap with closely related skills), not anchor 5 since triggers like "narrated audio"/"voice over" could also match generic audio-generation skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/speech/SKILL.md
Commit: 1b47e60

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.