BD video-subtitle
日语视频自动翻译烧录技能。将日语视频转换为中文硬字幕，完整流程：ffmpeg 提取音频 → Whisper 日语转录 → LLM 翻译日→中 → SRT 转 ASS → ffmpeg NVENC 烧录硬字幕 → 验证。触发条件：用户提到视频字幕、硬字幕、字幕烧录、日语视频翻译、whisper 字幕、ass 字幕、或要求处理 .mp4 视频加字幕。
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
ProcedureMedia and videoInfrastructuretype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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: 4. 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")
Process rating: all ten parameters 41/100
- 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
- 40Consistency. Frontmatter name (video-subtitle) differs from the folder (video-japanese-subtitle)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 8 steps
- 100Execution cost. Instruction body is 726 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
- +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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 174: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.
External checks
ClawHub: suspicious
This subtitle tool appears to do what it says, but it ships an embedded gateway token and can send video transcript text to translation services without clear user control.
LLM: suspicious (high) · VirusTotal: · 29 May 2026