BD PureVocals-UVR-Automator
当用户想要**一键批量从音频文件中提取超干净纯人声（干声 / Vocals Only）**、去除伴奏/背景音乐时，自动调用此技能。 一键音频人声分离工具。专门从音频文件（.mp3/.wav/.flac等）中提取超干净干声（Acapella）或去除背景音制作伴奏。 核心用途：支持单个音频文件或整个文件夹批量处理（.mp3/.wav/.flac 等格式），输出高质量无杂音干声，自动在输入同级创建 [输入文件夹]_vocals 文件夹，完美保留原目录结构。 高频触发场景包括： - 翻唱练习、翻唱视频制作、B站/抖音/小红书演唱素材清洗 - 卡拉OK 伴奏制作（只保留人声） - 音乐制作中的人声分离（vocal isolation / stem separation） - 音频素材清洗、原音轨提取、去背景音处理 - 翻唱素材制作、卡拉OK伴奏生成、音频后期清洗。 用户常用自然语言表述： “帮我提取干声”“把这首歌的伴奏去掉，只留清唱”“批量分离文件夹里的所有人声”“做翻唱要纯人声”“卡拉OK 干声提取”“vocal remover”“UVR 人声分离”“去除伴奏”“音频人声隔离”“stem 分离 vocals”等。 支持顶级 UVR 模型，默认推荐速度最快且干净度最高的 shibing624-chinese-kenlm-klm，也支持卡拉OK 专用模型。自动检测 GPU（CUDA 加速）或 CPU，自动创建并管理虚拟环境，无需用户手动配置。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 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
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 195 tokens
- 100Running it twice. No mutating operations
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -34 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 630: enough signal without eating the budget
- +4Structure: 3 headings
- +3Step-by-step instructions: 6 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.