oma-voice

Local-first text-to-speech and speech-to-text via the Voicebox MCP server. Generates speech from cloned or preset voice profiles for agent notifications, content voiceovers, and audio asset creation, and transcribes audio files for meeting notes or memos. Runs entirely on-device with no cloud, no API keys, no per-call cost. Use for voice generation, TTS, STT, transcription, voiceover, narration, dictation, audio asset work.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

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

A highly actionable, well-sequenced skill body with concrete MCP commands and validation checkpoints, held back by repetitive guardrails and referenced bundle files that are not actually present.

Suggestions

Deduplicate guardrails 1-4 against the Transitions and Failure-and-recovery table so each constraint appears once.

Create the referenced files (resources/voice-matrix.md, resources/execution-protocol.md, resources/checklist.md, config/voice-config.yaml) or remove the dangling references.

Move the inline MCP tool-mapping table and clarification checklist into the referenced resources to keep SKILL.md an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific, but guardrails 1-4 restate the Transitions and Failure-and-recovery table nearly verbatim (length limits, profile required, tool-name discovery), a clear tightening opportunity.	2 / 3
Actionability	Provides concrete, executable commands — exact MCP tool signatures, REST endpoints, output paths, and a verified tool-mapping table — that are copy-paste ready.	3 / 3
Workflow Clarity	Clear sequenced Entry and PREPARE->ACQUIRE->ACT->VERIFY->FINALIZE flow with an explicit VERIFY checkpoint and a recovery table providing feedback loops for error cases.	3 / 3
Progressive Disclosure	References are one-level-deep and clearly signaled, but the referenced bundle files (resources/, config/) are absent from disk and substantial detail (tool mapping, guardrails, clarification checklist) is inline rather than split out.	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.

A strong, third-person description that names concrete capabilities, lists natural trigger terms, and provides an explicit 'Use for' trigger clause with a clear local-only niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — speech generation, transcription, notifications, voiceovers, and audio asset creation — rather than vague language.	3 / 3
Completeness	Explicitly states what it does and includes a 'Use for ...' clause with explicit triggers, answering both what and when.	3 / 3
Trigger Term Quality	Covers natural user terms broadly — TTS, STT, transcription, voiceover, narration, dictation, audio asset — matching how a user would phrase the request.	3 / 3
Distinctiveness Conflict Risk	The local-first, on-device, no-cloud/no-API-key framing carves a distinct niche unlikely to conflict with cloud-based voice skills.	3 / 3
	Total	12 / 12 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-voice/SKILL.md
Commit: 3021301

Reviewed: about 21 hours 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.