add-voice

Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice to an app, including replacing an STT-LLM-TTS cascade or OpenAI Realtime. Wire speech-to-speech, safe auth, and app mic. Composer: waveform button, mic icon reserved for dictation. For mic-to-text only use /add-dictation; to speak text replies use /add-read-aloud. To add debug logging and fix from logs use /debug-voice.

Quality

94%

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

96%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 tight, highly actionable skill body with executable code, explicit validation checkpoints, and a clear feedback loop. Its only weakness is that all content lives inline with no bundle files, leaving minor organization room for the larger skeletons and composer spec.

Suggestions

Move the TS and Python skeletons into scripts/ files referenced from SKILL.md to reduce body length and let progressive_disclosure reach 5.

Consider extracting the detailed composer UI spec (icon weights, bar dimensions, phase animations) into a references/ file, keeping SKILL.md to the core convention summary.

Add a short 'Verify' checklist at the end of step 9 so the smoke-test checkpoints read as an explicit checklist rather than prose.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — specific API events, exact pixel specs, and gotchas ('never the fill weight, which renders as a blob at 16 px', 'that is echo, not a bug') with no padding or explanation of basics Claude already knows, matching the 5 anchor.	5 / 5
Actionability	Fully executable copy-paste-ready TS and Python skeletons with the real WebSocket URL and session.update payload, plus concrete smoke-test commands ('grep the built client bundle for the env name and client_secrets'), matching the 5 anchor.	5 / 5
Workflow Clarity	A 9-step sequenced workflow (Map, Auth, Connect, Audio I/O, Composer, Skeletons, Instrument, Smoke) with explicit validation checkpoints ('Instrument before the first human test', confirm-no-key grep, /debug-voice feedback loop), matching the 5 anchor with feedback loops.	5 / 5
Progressive Disclosure	Well-organized single file with clear headers and external docs links placed appropriately, but at ~115 lines with inlined TS+Python skeletons and a dense composer spec it slightly exceeds the <50-line simple-skill exception that would allow a 5, leaving minor organization gaps per the 4 anchor.	4 / 5
	Total	19 / 20 Passed

Description

92%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 highly specific, well-triggered description that clearly states what the skill does and when to use it, with concrete actions and explicit routing away from sibling skills. The only minor gap is synonym/extension breadth in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Wire speech-to-speech, safe auth, and app mic', 'Composer: waveform button, mic icon reserved for dictation', replacing 'an STT-LLM-TTS cascade or OpenAI Realtime'), matching the comprehensive-coverage anchor rather than the 4 anchor with minor gaps.	5 / 5
Completeness	Explicitly answers both what ('Wire speech-to-speech, safe auth, and app mic') and when ('Use when the user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice') with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	Strong natural trigger phrasing ('user runs /add-voice, types Voice Mode, or asks to add Grok realtime voice') plus related terms ('STT-LLM-TTS cascade or OpenAI Realtime', 'mic-to-text'), but stops short of the full synonym/extension spread of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche with explicit disambiguation against siblings ('mic icon reserved for dictation', 'For mic-to-text only use /add-dictation… use /add-read-aloud… use /debug-voice'), giving minimal conflict risk per the 5 anchor.	5 / 5
	Total	19 / 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: cursor/plugins
Path: grok-voice/skills/add-voice/SKILL.md
Commit: 5bf2b15

Reviewed: 15 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.