SKILLEMALL.ai
GitHub ↗ RU Sign in

CF tencent-mps

腾讯云 MPS 音视频与图片处理、AI 生成、内容理解。涉及以下场景必须触发：【转码】转码/压缩/格式转换/转封装/H.264/H.265/AV1/码率/分辨率。【画质增强】画质增强/画质修复/老片修复/超分/真人增强/漫剧增强/防抖/人脸保真/1080P/2K/4K。【音频】音频分离/人声提取/伴奏提取/去人声/降噪/音量均衡。【字幕】字幕提取/字幕翻译/语音识别/语音转文字/ASR/OCR字幕/SRT/视频翻译。【擦除】去字幕/去水印/人脸模糊/车牌模糊/马赛克。【配音】语音合成/TTS/文字转语音/AI配音/配音/声音克隆/音色复刻。【图增强】图片超分/美颜/降噪/色彩增强/低光照增强。【抠扩图】AI抠图/去背景/透明PNG/AI扩图/outpaint/图片修复。【图片编辑】局部重绘/inpainting/目标检测/分镜拆图/多视角生图/换角度/水印擦除。【图片理解】图片理解/图片OCR/图片问答/AI看图。【电商图】AI试衣/图片换装/服装替换/模特换装/换模特/换体型/换背景/背景融合/商品套图。【AIGC】AI生图/文生图/图生图/AI绘画/全景图/AI生视频/文生视频/图生视频/参考视频/分镜生成/Kling/可灵/Vidu/Mingmou/PixVerse/Hunyuan。【AI生音频】AI生音频/文生音效/视频生音效/文生音乐/AI音乐/BGM生成/歌曲翻唱。【横竖转换】转横屏/转竖屏/9:16转换/16:9转换/ROI智能裁剪/AIGC补全画面/短视频比例转换。【文档生视频】文档生成视频/PDF转视频/PPT转视频/Word转视频。【内容理解】音视频理解/视频摘要/场景识别/内容分析/对比分析两段视频/音频理解。【二创】换脸/换人/视频交错。【去重】视频去重/画中画/视频扩展。【集锦】精彩集锦/高光提取/自动剪辑/足球集锦/篮球集锦/短剧高光/VLOG集锦。【AI解说】AI解说/短剧解说/短剧混剪。【质检】媒体质检/画质检测/模糊检测/花屏检测/卡顿检测/音频质检。【COS】上传COS/下载COS/列出COS/列出Bucket文件/查看COS目录/查看存储桶（须用本 Skill 的 COS 脚本，禁用 coscli、tccli、aws s3）。【任务】查询MPS任务/查询TaskId/环境变量检查。【用量】MPS用量查询。【对比】生成对比页面。仅咨询能力不需处理时不触发。

ClawHub Agent Skills author: tencent-mpaas-skills v1.3.2 MIT-0 75 files body ≈ 4 857 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

腾讯云 MPS 音视频与图片处理、AI…

As a process F 31/100 · Will not run — References files that are not bundled: URL, references/<script>.md

IntegrationAWSInfrastructureSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
66/100
safety, quality, tests
Safety 60%
69
Quality 40%
62
Run on models
none yet
Process rating
F
31/100
Will not run
References files that are not bundled: URL, references/<script>.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 · 31

✓ No critical or high findings

Medium and low: 31
  • low Secrets in code secret-high-entropy-token references/best_practices.md:478
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    1. 查询视频处理任务状态，任务ID：`2600…123`。
    quoted
  • low Secrets in code secret-high-entropy-token references/best_practices.md:479
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    → `python3 scripts/mps_get_video_task.py --task-id 2600…123`
    quoted
  • low Secrets in code secret-high-entropy-token references/best_practices.md:485
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    → `python3 scripts/mps_get_image_task.py --task-id 2600…001`
    quoted
  • low Secrets in code secret-high-entropy-token references/best_practices.md:487
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    → `python3 scripts/mps_get_image_task.py --task-id 2600…123`
    quoted
  • low Secrets in code secret-high-entropy-token references/best_practices.md:491
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    → `python3 scripts/mps_get_video_task.py --task-id 2600…001`
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_aigc_audio.md:103
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_aigc_audio.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_dubbing.md:250
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx --verbose
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_dubbing.md:253
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_erase.md:109
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx --verbose
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_erase.md:112
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_highlight.md:88
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_image_changemodel.md:139
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…345",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_comprehend.md:136
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…890",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_cutout.md:112
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…678",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_detect.md:141
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…012",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_multiview.md:123
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…901",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_padding.md:123
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…789",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_poster_suite.md:254
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    "TaskId": "2600…xxx",
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_image_repaint.md:134
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…123",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_image_split.md:124
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "TaskId": "2600…234",
    quoted
  • low Secrets in code secret-high-entropy-token references/mps_narrate.md:82
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_qualitycontrol.md:63
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_query_task.md:5
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    适用于 `ProcessMedia` 提交的任务（TaskId 格式：`1234…xxx`）
    placeholder
  • low Secrets in code secret-high-entropy-token references/mps_vremake.md:98
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/mps_aigc_audio.py:56
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 mps_aigc_audio.py --task-id 2600…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/mps_av_understand.py:49
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_av_understand.py --task-id 1234…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/mps_get_video_task.py:1393
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    python3 mps_get_video_task.py --task-id 2353…48a
    quoted
  • low Secrets in code secret-high-entropy-token scripts/mps_get_video_task.py:1396
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    python3 mps_get_video_task.py --task-id 2353…48a --verbose
    quoted
  • low Secrets in code secret-high-entropy-token scripts/mps_get_video_task.py:1399
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    python3 mps_get_video_task.py --task-id 2353…48a --json
    quoted
  • low Secrets in code secret-high-entropy-token scripts/mps_qualitycontrol.py:48
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 1234…xxx
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/mps_vremake.py:48
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    python3 scripts/mps_get_video_task.py --task-id 1234…xxx
    placeholder

Files scanned: 75. 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: URL
  • warning missing-ref reference to a missing file: references/<script>.md

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: URL, references/<script>.md
  • 0Tools and files. 2 referenced file(s) missing: URL, references/<script>.md
  • 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. 5 mutating operations with no state check
  • 70Execution cost. Instruction body is 4857 tokens
  • 100Steps. 43 steps
  • 100Consistency. Name and required fields are in place
  • low The response is described with custom markup (13 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 1013: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -31 of 38 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 43 items
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (32 of 33)
  • +1License stated

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

External checks

ClawHub: suspicious
This is mostly a disclosed Tencent Cloud media-processing skill, but it needs Review because it combines cloud credential use, automatic media upload/link generation, runtime package upgrades, and an explicit duplicate-detection evasion workflow.
LLM: suspicious (high) · 9 Aug 2026