BF local-voice-reply
Local OPUS/Ogg voice-reply pipeline for Feishu/Discord with structured voice customization. Default voice is Juno (`voice/juno_ref.wav`), with support for registered custom voices via API. Includes FastAPI server + scripts for stable generation/sending. Requires ffmpeg on PATH and Python deps (torch/torchaudio/chatterbox-tts/fastapi/uvicorn). Activate for /voice_mode_on or any user request for voice/audio reply.
As a process F 41/100 · Will not run — References files that are not bundled: scripts/send_voice_reply.ps1, scripts/generate_cuda_voice.ps1
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: scripts/send_voice_reply.ps1 - warning
missing-refreference to a missing file: scripts/generate_cuda_voice.ps1
Process rating: all ten parameters 41/100
- 0Tools and files. 2 referenced file(s) missing: scripts/send_voice_reply.ps1, scripts/generate_cuda_voice.ps1
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 61 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1084 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)
- +4No input/output examples
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 415: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 61 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.