BB local-qwen3-asr-aipc
Local offline ASR on Windows — no cloud, no API cost, full privacy. Qwen3-ASR 0.6B + Intel OpenVINO, GPU-accelerated inference. NETWORK: required for first-time setup (install deps + download 2 GB model); NOT required for inference. Auto-extracts audio from video files (mp4, mkv, webm, mov, avi) — just pass the video path. Also supports audio: mp3, wav, flac, m4a, ogg, aac, wma, opus. Single file, batch folder, or watch-mode continuous transcription with automatic txt/json archive. 30 languages + 22 Chinese dialects, auto language detection. One-line LLM API: from acoustic_pipeline import AcousticPipeline Local speech to text, transcribe audio, voice recognition, transcribe video, transcribe recording, convert speech to text, audio transcription, local ASR, offline speech recognition, dictation on Windows. 本地离线语音识别，零云端，支持视频音轨自动提取，支持批量转录和文件夹监听，自动保存转写文档。 网络说明：仅首次安装环境和下载模型时需要网络，推理转录完全离线。
As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "os" - note
frontmatter-keyunknown frontmatter key "requires" - note
frontmatter-keyunknown frontmatter key "network"
Process rating: all ten parameters 77/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4686 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 50 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 tags): a typed call is more reliable
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)
- +3Description length 897: 120–800 characters recommended
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (24 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.