oma-voice

Generate speech or transcribe audio locally with Voicebox. Use for narration, voice assets, dictation, and meeting transcription.

Quality

81%

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

81%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 highly actionable, well-sequenced skill body with concrete MCP/REST integration details and strong validation feedback loops. The main drag is conciseness — several guardrails are repeated across multiple sections — and progressive disclosure is slightly undercut by referenced resource files that are not bundled.

Suggestions

Consolidate the repeated rules (profile-required-for-TTS, 5000-char / 30-min limits, engine-download approval) into a single authoritative Guardrails section and reference it from the Transitions, Failure table, and Clarification protocol instead of restating each.

Ship the referenced resource files (resources/voice-matrix.md, prompt-tips.md, execution-protocol.md, checklist.md) in a bundle directory, or move the inlined guardrail/tool-mapping detail into them so the SKILL.md body stays a true overview.

Trim the Scheduling section's restatement of intent signatures and when-to-use clauses, which overlap with the description and the When NOT to use list.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense and avoids explaining concepts Claude already knows, but key rules (profile requirement, 5000-char / 30-minute limits, engine-download hint) are restated across When NOT to use, Transitions, the Failure table, Preconditions, Guardrails, and the Clarification protocol — more than minor redundancy, matching the 3 anchor; not 4 because the overlap is material rather than incidental.	3 / 5
Actionability	Concrete and executable throughout — exact MCP tool names, REST endpoints, parameter lists, output paths, and a canonical command path with copy-paste-ready blocks covering TTS, STT, and notification cases, matching the 5 anchor.	5 / 5
Workflow Clarity	A clear sequenced flow (Entry → PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE → Exit) with explicit validation in the VERIFY scene, a failure/recovery table with exit codes providing feedback loops, and a clarification-protocol checklist; the destructive/batch cap does not apply because validation is present, matching the 5 anchor.	5 / 5
Progressive Disclosure	Good section structure with a clearly signaled, one-level-deep References block (voice-matrix.md, prompt-tips.md, execution-protocol.md, checklist.md); falls short of 5 because the referenced resource files are not present in any bundle directory and a fair amount of detail (guardrails, tool-mapping tables, clarification protocol) is inlined rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

82%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 concise, well-formed description that clearly states what the skill does and when to use it with natural trigger terms and a distinct local-only niche. Its main weakness is specificity/trigger breadth — only two actions and no file-extension or synonym triggers.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions — "Generate speech" and "transcribe audio" — but stops at two actions without enumerating the fuller set (e.g., notification audio, profile comparison), matching the 1-2 concrete actions anchor; not the level above because coverage is not comprehensive.	3 / 5
Completeness	Explicitly answers both "what" ("Generate speech or transcribe audio locally with Voicebox") and "when" ("Use for narration, voice assets, dictation, and meeting transcription") with concrete trigger phrases, matching the 5 anchor; confirmed above 4 because the "when" clause is explicit and specific rather than weakly implied.	5 / 5
Trigger Term Quality	Natural terms users would say are present — "narration", "voice assets", "dictation", "meeting transcription" — giving good keyword coverage; falls short of 5 because common synonyms and file extensions ("text to speech", "audio to text", ".wav", ".mp3", "transcript") are missing.	4 / 5
Distinctiveness Conflict Risk	The local-only, Voicebox-specific framing carves a clear niche unlikely to trigger for cloud TTS or unrelated skills; minimal conflict risk, matching the 5 anchor.	5 / 5
	Total	17 / 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-voice/SKILL.md
Commit: 580da66

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.