BF tencent-mps-video-dubbing
Tencent Cloud MPS 一站式端到端视频译制专用 Skill，在单次任务中**不可拆分**地完成「提取原视频语音/字幕 → 翻译为目标语言 → 压制目标语言字幕 → AI 克隆原声配音」整条跨语言本地化流水线。**触发的硬条件（必须同时满足）：(1) 用户的输入是一段视频；(2) 明确要求变更音视频的语言（翻译 + 配音 / 翻译 + 换语言 / 做成另一语言版本）；(3) 是端到端产出一个全新语言版本的视频，而不是只做流水线中的某一步子任务**。满足硬条件的典型表达：把这段视频翻译成英文并配音、中文视频做成韩语版、韩剧中配、短剧出海译制、做一个日语配音版、 跨语言视频制作 / 视频本地化一站式处理。**额外触发场景（查询类豁免）**：用户明确要求查询一个"视频译制任务"的状态/结果/进展，也应触发本 Skill。**仅询问工具推荐或咨询而不进行实际处理时不触发**。
As a process F 33/100 · Will not run — References files that are not bundled: URL
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenreferences/mps_video_dubbing.md:136High-entropy token-like string (may be an id, hash or a credential) (placeholder value)python3 scripts/mps_video_dubbing.py --query-task 2600…xxx
placeholder
Files scanned: 12. 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: URL
Process rating: all ten parameters 33/100
- 0Tools and files. 1 referenced file(s) missing: URL
- 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
- 30Running it twice. 2 mutating operations with no state check
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1886 tokens
- low The response is described with custom markup (10 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 395: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
- +3All 6 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.