SKILLEMALL.ai

BF video-translate

将用户明确选择的本地视频转为中英双语 ASS/SRT。经用户确认后,读取本机 OkFile 与阿里凭据,把视频音频上传到 OkFile,将临时公开链接交给阿里 Fun-ASR 获取词级时间戳,并按用户选择把字幕文本交给 qwen-mt-plus 或当前 Agent 模型翻译、全文审校和质检;不接受用户直接提供的音频。Converts a selected local video to bilingual ASS/SRT only after explicit consent for OkFile audio upload, Alibaba Fun-ASR transcription, and qwen-mt-plus or current-Agent text processing; rejects direct audio input.

ClawHub Agent Skills author: AI落地第四声 v1.7.0 MIT-0 31 files · 1 script body ≈ 3 403 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 46/100 · Will not run — References files that are not bundled: ../../docs/video-translate/视频翻译工作流说明书.md

GeneratorAI and agentsMedia and videoWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
98
Quality 40%
62
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: ../../docs/video-translate/视频翻译工作流说明书.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Concealment en-hide-from-user references/execution-contract.md:85
    Instruction to hide actions from the user (negated — the text forbids it)
    If the check fails, fix the environment before running transcription. For missing tools such as `ffmpeg`, give the platform-specific install command or request user approval before installing. Do not 
    negated
  • low Obfuscation obf-hex-escape-chain scripts/preflight.py:5
    Escaped/char-code string obfuscation (quoted — discussed, not commanded)
    QUESTIONNAIRE = """必读:翻译流程会自动提取音频并上传到 OkFile,生成供 Fun-ASR 调用的临时公开链接,以获得词级时间戳,并支持后续 AI 语义划分、修正和质检。ASR 固定使用阿里百炼 Fun-ASR;翻译可选择通过 API 调用阿里百炼旗舰翻译模型 `qwen-mt-plus`,或直接使用当前 Agent 的模型额度。若当前环境支持,推荐在 Codex 中使用 G
    quoted

Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: ../../docs/video-translate/视频翻译工作流说明书.md
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: ../../docs/video-translate/视频翻译工作流说明书.md
  • 0Tools and files. 1 referenced file(s) missing: ../../docs/video-translate/视频翻译工作流说明书.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 10 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 39 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3403 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • -318 of 23 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 374: enough signal without eating the budget
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (2 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: clean
This skill is a disclosed video-subtitle workflow that uses local files, provider credentials, and network services in ways that match its stated purpose.
LLM: benign (high) · VirusTotal: · 29 Jul 2026