AB voiceclaw
Local voice I/O for OpenClaw agents. Transcribe inbound audio/voice messages using local Whisper (whisper.cpp) and generate voice replies using local Piper TTS. Requires whisper, piper, and ffmpeg pre-installed on the system. All inference runs on-device — no network calls, no cloud APIs, no API keys. Use when an agent receives a voice/audio message and should respond in both voice and text, or when any text response should be synthesized and sent as audio. Triggers on: voice messages, audio attachments, respond in voice, send as audio, speak this, voiceclaw.
As a process B 73/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 9 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 1056 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 565: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (6 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.