speech

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Quality

92%

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

85%Weight 40%Scale 1-3

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

The body is actionable, well-sequenced with validation feedback loops, and cleanly split across real reference files. Its main weakness is conciseness: a duplicative reference map and dated version strings add tokens that could be trimmed.

Suggestions

Remove or consolidate the 'Reference map' section, which repeats links already listed under 'Guidance by use case' and 'CLI + environment notes', to cut redundancy.

Move the pinned model version 'gpt-4o-mini-tts-2025-12-15' (and any other dated strings) into a dedicated versions/deprecation note so the main flow stays evergreen and lean.

Tighten the 'Environment' section by combining the API-key setup bullets into a more compact checklist.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence, but the 'Reference map' section duplicates links already given under 'Guidance by use case' and 'CLI + environment notes', and dated version strings add maintainable noise. Mostly efficient but could be tightened, matching the score-2 anchor.	2 / 3
Actionability	Provides concrete executable guidance — CLI path, install commands, a JSONL batch example, a labeled instruction template, and specific defaults/limits — copy-paste ready and complete.	3 / 3
Workflow Clarity	A numbered 8-step workflow with an upfront decision tree, an explicit validation step ('For important clips, validate: intelligibility, pacing, pronunciation...'), and a single-change iterate/re-check feedback loop, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to one-level-deep references (all verified to exist) via a clear reference map and per-use-case modules; content is appropriately split with easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, well-triggered, complete, and clearly niche-scoped. It states concrete capabilities, an explicit 'Use when' trigger, and an out-of-scope boundary in third person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation' and 'run the bundled CLI (`scripts/text_to_speech.py`)'. Matches the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicit 'Use when the user asks for...' trigger clause plus a clear statement of what the skill does, satisfying both 'what' and 'when' as in the score-3 example.	3 / 3
Trigger Term Quality	Uses natural user phrasing ('narration', 'voiceover', 'accessibility reads', 'audio prompts', 'batch speech generation') that a user would plausibly say. Not quite exhaustive of every variation but strong natural coverage, closest to the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Scoped to OpenAI Audio API TTS with built-in voices and an explicit out-of-scope statement ('Custom voice creation is out of scope'), giving it a clear niche unlikely to trigger competing skills.	3 / 3
	Total	12 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: JetBrains/skills
Path: speech/SKILL.md
Commit: e0f258b

Reviewed: 1 month 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.