SKILLEMALL.ai
GitHub ↗ RU Sign in

CD nemotron-voice-agent-builder

Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) customization and cloud or local deployment. Not for offline/batch speech-to-text, text-only chat or RAG, or generic Docker or CUDA work unrelated to a voice agent.

ClawHub Agent Skills author: NVIDIA 1 file body ≈ 684 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit.

As a process D 42/100 · Unfinished process — References files that are not bundled: references/operations/iterate.md, references/operations/troubleshoot.md, references/intake.md

GeneratorDockerAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
73
Run on models
none yet
Process rating
D
42/100
Unfinished process
References files that are not bundled: references/operations/iterate.md, references/operations/troubleshoot.md, references/intake.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/operations/iterate.md
  • warning missing-ref reference to a missing file: references/operations/troubleshoot.md
  • warning missing-ref reference to a missing file: references/intake.md
  • warning missing-ref reference to a missing file: references/platforms/readiness.md
  • warning missing-ref reference to a missing file: references/output-contract.md
  • warning missing-ref reference to a missing file: references/operations/observability.md
  • warning missing-ref reference to a missing file: references/operations/run.md
  • warning missing-ref reference to a missing file: scripts/smoke.sh
  • warning missing-ref reference to a missing file: references/preflight.md
  • warning missing-ref reference to a missing file: references/networking/remote-webrtc.md

Process rating: all ten parameters 42/100

Will not run. References files that are not bundled: references/operations/iterate.md, references/operations/troubleshoot.md, references/intake.md
  • 0Tools and files. 10 referenced file(s) missing: references/operations/iterate.md, references/operations/troubleshoot.md, references/intake.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 5 mutating operations with no state check
  • 100Steps. 8 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 684 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 360: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 8 items
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.