Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Real Time Voice Reasoner — measured AI agent skill | DecimalAI

stijnman/real-time-voice-reasoner

SkillScore92Maintained

Handles real-time voice input with low-latency reasoning. Use for voice sess ions or user says voice mode, speak and reason. Use when the user needs this capability. Triggers: voice mode, speak and reason, voice assistant, listen .

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

decimalai skills pull stijnman-real-time-voice-reasoner

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-real-time-voice-reasoner/SKILL.md

Raw file: /s/stijnman-real-time-voice-reasoner/SKILL.md ↗ · machine-readable summary at /s/stijnman-real-time-voice-reasoner.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +50% lift-52% tokens0% turns92% of whole cases pass with skill (22/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-18	✗→✓	▲ Improved	-66%	0%
case-01	✗→✓	▲ Improved	222%	0%
case-02	✗→✓	▲ Improved	17%	0%
case-07	✗→✓	▲ Improved	-75%	0%
case-08	✗→✓	▲ Improved	-69%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/real-time-voice-reasoner/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Real Time Voice Reasoner

When to Use

User says voice mode or task matches this capability
User says speak and reason or task matches this capability
User says voice assistant or task matches this capability
User says listen or task matches this capability

Workflow

Transcribe or receive voice input stream.
Apply voice-think-fast-handler for quick ack.
Reason on full utterance; respond concisely for TTS.
Confirm ambiguous commands verbally.

Integrations

voice-think-fast-handler
voice-synthesis-handler

Error Handling

| Failure | Response | |---------|----------| | Poor transcription | Ask user to repeat once. |

Gotchas

Voice confirmations for destructive actions.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/real-time-voice-reasoner would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.