← 返回 Skills 市场
1098
总下载
3
收藏
1
当前安装
16
版本数
在 OpenClaw 中安装
/install tencent-mps
功能描述
腾讯云 MPS 媒体处理服务,支持以下功能:【视频转码】转码/压缩/格式转换/H.264/H.265/AV1/MP4/AVI/MKV/FLV/MOV/编码/码率/分辨率/帧率调整。【画质增强】画质增强/画质修复/老片修复/超分辨率/视频超分/画质提升/真人增强/漫剧增强/动漫超分/画面抖动/防抖/细节增强/人脸保...
安全使用建议
Key points before installing or using this skill:
- This skill's scripts require your Tencent Cloud SecretId and SecretKey (and often COS bucket/region). The registry metadata currently does NOT declare these required env vars — treat that as a red flag and require the publisher to correct it.
- Do NOT paste your SecretId/SecretKey into a chat/conversation. SKILL.md suggests the agent can help configure if you send values in the conversation — that would expose secrets to the agent and any logs. Use a secure secret injection mechanism instead (platform secret store, environment variables injected by an admin, or an IAM role with minimal privileges).
- Inspect mps_load_env.py and any code that auto-loads environment files before running: the scripts reference loading env from /etc/environment, ~/.profile, etc. Verify what files are read and whether any code writes to or parses arbitrary system files.
- Limit credentials: if you must provide keys, create least-privilege credentials scoped to MPS/COS actions only and avoid using owner/administrator keys. Prefer short-lived credentials or COS pre-signed URLs where possible.
- Be aware of billing: many operations call Tencent MPS and will incur costs. The SKILL.md reminds about costs — confirm expected costs and test with dry-run (--dry-run) first.
- Verify link and TaskId handling: SKILL.md requires Markdown links and explicit TaskId output. Make sure any automation that parses script stdout cannot be coerced to exfiltrate secrets via those outputs.
- If you are not comfortable supplying cloud credentials or allowing the skill to read environment files, do not install or run it. Consider running the scripts locally in an isolated environment (container or VM) after manually reviewing the code.
If you want, I can: (1) highlight the exact places in the code that read environment files or prompt for secrets, (2) summarize which scripts require which env vars, or (3) suggest minimal IAM policies to limit the provided credentials.
功能分析
Type: OpenClaw Skill
Name: tencent-mps
Version: 1.1.5
The skill bundle is a comprehensive and professional wrapper for Tencent Cloud Media Processing Services (MPS). It utilizes official Tencent Cloud Python SDKs to perform media transcoding, enhancement, AIGC generation, and content analysis. While `mps_load_env.py` performs high-privilege actions by scanning system configuration files (e.g., `/etc/environment`, `~/.bashrc`) for credentials, this behavior is explicitly documented and serves the legitimate purpose of simplifying environment configuration for the user. No evidence of data exfiltration, unauthorized remote execution, or malicious prompt injection was found; the scripts are well-commented and align strictly with their stated media processing objectives.
能力标签
能力评估
Purpose & Capability
Name, description, SKILL.md and included scripts all consistently implement Tencent Cloud MPS functionality (transcode, enhancement, AIGC, COS ops). However the registry metadata declares no required environment variables and no primary credential, while the scripts and SKILL.md clearly need TENCENTCLOUD_SECRET_ID / TENCENTCLOUD_SECRET_KEY and often TENCENTCLOUD_COS_BUCKET/TENCENTCLOUD_COS_REGION. That mismatch between declared requirements and actual code is an incoherence that should be resolved before trusting the skill.
Instruction Scope
SKILL.md enforces behavior (only emit python commands, require TaskId reporting, format links as Markdown) and instructs environment setup paths (/etc/environment, ~/.profile, etc.). Critically, SKILL.md suggests users may 'directly send variable values in the conversation, by AI help configure' and the scripts attempt to auto-load environment files. Those instructions encourage secret disclosure and allow the skill to read system environment files — beyond what a benign helper should ask a user to paste into chat.
Install Mechanism
There is no remote download or install spec; the package is delivered as local Python scripts. The scripts declare Python dependencies installed via pip (tencentcloud-sdk-python, cos-python-sdk-v5), which is a normal mechanism. No arbitrary external archives or URL-based installers were found in the provided manifest.
Credentials
The skill requires high-sensitivity credentials (Tencent Cloud SecretId/SecretKey) and COS configuration for many operations, plus optional region/bucket vars. Those secrets are essential for the skill's functionality, but they are not declared in the registry metadata and the SKILL.md gives instructions that could lead to insecure handling (auto-load env files, ask users to paste values into chat). Multiple environment variables are requested across scripts (and some scripts call get_cos_presigned_url using secrets), so the scope of secrets is broad and must be treated carefully.
Persistence & Privilege
The skill is not marked always:true and does not request elevated platform privileges. Nothing in the metadata indicates it modifies other skills or system-wide agent settings. That said, its runtime behavior (reading environment files, suggesting edits to ~/.profile or /etc/environment) means users may be prompted to persist credentials on the host — a user action, not an automatic privilege requested by the skill.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install tencent-mps - 安装完成后,直接呼叫该 Skill 的名称或使用
/tencent-mps触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.1.5
**增加视频去重及 dedupe 支持,所有处理类任务输出均统一展示 TaskId**
- 新增视频去重/防重相关脚本:加入 `mps_dedupe.py`、dedupe 参考文档,更新功能映射与说明
- 任务输出规范强化:所有处理类任务执行后,强制在回复中展示 TaskId(🆔 任务 ID:<TaskId>),便于后续查询
- 脚本调用规范增强:增加输入源参数选择强制规则,并优化异步任务类型说明
- 更新 description,补充支持 dedupe 视频去重功能
- 其它用语和映射表细节同步优化
v1.1.4
**新增效果对比功能,完善处理后前后对比体验。**
- 新增脚本 `mps_gen_compare.py`,用于生成处理前后效果对比页面(HTML 滑动对比),无 MPS 费用。
- 新增文档 `references/mps_gen_compare.md`,说明效果对比脚本用法。
- SKILL.md 增加「效果对比」描述、专属映射、触发规则及参数说明。
- 优化主 description,扩充各处理能力关键词(如“效果对比”、“AI生视频”等)。
- 统一任务默认自动轮询等待完成,“加 --no-wait 仅提交不等待”。
- 查询 VideoRemake 任务合并至 `mps_get_video_task.py`,补充功能映射表说明。
v1.1.3
**tencent-mps 1.1.3** adds new advanced image and video features, enhances scope clarification, and updates environment and mapping rules.
- 新增图片换装(AI 试衣/模特换装/服装替换)、图片背景融合(AI 换背景/商品图背景生成)等能力及相关脚本
- 显式增加脚本映射,严格区分图片换装、图背景融合、AIGC、生视频、增强等多种任务类型
- 所有查询和辅助类操作(如上传/下载/环境变量)明确纳入职责,必须用配套脚本,不得用通用命令替代
- 增强输入路径来源规则(本地、COS、URL 三种自动区分),明确参数映射与用户追问逻辑
- 文档重构,脚本功能与参考文档一一对应,环境变量细化
- 移除已废弃参考文件与冗余脚本(如 params.md,
v1.1.2
- 修正版本号和元数据:将 metadata.version 从 1.2.0 恢复为 1.1.2
- 明确要求所有生成的 Python 脚本命令必须加 scripts/ 路径前缀,禁止省略
- 其余功能和规则未更动,文档内容与前一版本基本保持一致
v1.1.1
Version 1.2.0 (2024-06)
- 支持 AI 生视频(mps_aigc_video.py)分镜功能,Kling 模型已支持分镜生成
- 技能说明文档同步加强:“AI生图/生视频(含分镜)”加入描述
- 其他内容和使用流程、参数要求保持不变
v1.1.0
腾讯云 MPS Skill 版本 1.1.0 变更摘要:
- 新增 AI解说(`scripts/mps_narrate.py`)和精彩集锦(`scripts/mps_highlight.py`)自动化处理脚本,支持短剧讲解和高光剪辑等新场景。
- 在 SKILL.md 明确所有核心操作都会产生腾讯云 MPS 服务相关费用,并增加醒目的计费提示。
- 详细补充了支持 COS 路径和 URL 两种输入方式的说明,并明确了推荐用法及注意事项。
- 扩展和细化命令生成及参数填写规则,`mps_narrate.py` 和 `mps_highlight.py` 的场景参数(`--scene`)现需严格在预设枚举中选择。
- 更新脚本功能映射表,含 narrate 与 highlight 全新能力的场景与使用边界。
v1.0.9
**新增大规模能力脚本,完善内容理解与质检等高级用法:**
- 新增音视频内容理解脚本:`mps_av_understand.py`
- 新增 COS 文件列表脚本:`mps_cos_list.py`
- 新增媒体质检脚本:`mps_qualitycontrol.py`
- 新增用量统计查询脚本:`mps_usage.py`
- 新增视频去重/变换脚本:`mps_vremake.py`
- 文档全面升级,覆盖场景更丰富,脚本分工更清晰
- 移除 LICENSE.txt 文件
v1.0.8
- 版本号升级至 1.0.8,并同步 metadata。
- 优化描述,大模型增强模板范围表述为“327001 至 327020”,“720P 至 4K”。
v1.0.7
tencent-mps 1.0.7
- 更新版本号至 1.0.7。
- 其余功能、说明、参数与上一个版本保持一致。更新默认路径。
v1.0.6
tencent-mps v1.0.6
v1.0.5
tencent-mps 1.0.5
- 新增本地文件上传与结果下载脚本:`scripts/mps_cos_upload.py` 和 `scripts/mps_cos_download.py`
- 支持标准化本地文件处理流程(本地文件需先上传 COS,处理结果支持从 COS 下载)
- 文档增加本地文件处理流程说明与用法示例
- 依赖补充:建议同时安装 `cos-python-sdk-v5`
v1.0.4
No code or interface changes detected in this version.
- No files were changed in version 1.0.4.
- There are no visible updates, bugfixes, or feature additions in this release.
v1.0.3
tencent-mps 1.0.3
- 增加了 5 个新文件,包括 desc.txt、参数说明和脚本辅助工具(如环境变量加载、任务轮询)。
- 文档全面升级:着重强调如音视频增强、去水印、AIGC 智能生图/生视频、伴奏提取等场景下都必须使用本 Skill,不建议自行实现。
- 新增详细环境变量说明、配置检测及自动加载方法,提升易用性和可用性。
- 脚本行为优化:绝大多数异步任务支持自动轮询,默认无需手动调用查询脚本,指南更加清晰易懂。
- 图片与视频处理场景补充人脸和车牌模糊、音频分离等能力描述。
- 新增了脚本参数和任务状态查询的详细参考文档,便于快速查阅使用方法。
v1.0.2
- 修正环境变量命名,将 `TENCENT_COS_BUCKET` 和 `TENCENT_COS_REGION` 改为 `TENCENTCLOUD_COS_BUCKET` 和 `TENCENTCLOUD_COS_REGION`,统一配置。
- 更新文档中所有环境变量、参数示例与相关说明,确保与最新脚本接口一致。
- 保持所有现有功能与脚本用法不变,注重一致性和可用性改进。
- 无新增功能或脚本,变更仅涉及配置细节和文档。
v1.0.1
No file changes detected in this version; internal metadata version updated only. No functional or documentation changes for users.
v1.0.0
腾讯云媒体处理服务 MPS。当用户需要对音视频或图片进行处理时触发,包括:视频转码/压缩/格式转换、视频画质增强/老片修复、提取或翻译视频字幕、去除视频字幕或水印、图片超分/美颜/水印处理、AI生成图片(文生图/图生图)、AI生成视频(文生视频/图生视频)。支持极速高清转码、视频增强(大模型/综合/去毛刺)、智能字幕(ASR/OCR/翻译)、智能去字幕与擦除、图片处理(增强/超分/降噪/美颜/擦除/盲水印/缩放)、AIGC 智能生图(Hunyuan/GEM/Qwen)、AIGC 智能生视频(Hunyuan/Hailuo/Kling/Vidu/OS/GV)。使用关键词:转码、视频增强、字幕、去字幕、擦除、图片处理、超分、美颜、AIGC、AI生图、AI生视频、文生图、图生图、文生视频、图生视频。
元数据
常见问题
Tencent MPS 是什么?
腾讯云 MPS 媒体处理服务,支持以下功能:【视频转码】转码/压缩/格式转换/H.264/H.265/AV1/MP4/AVI/MKV/FLV/MOV/编码/码率/分辨率/帧率调整。【画质增强】画质增强/画质修复/老片修复/超分辨率/视频超分/画质提升/真人增强/漫剧增强/动漫超分/画面抖动/防抖/细节增强/人脸保... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1098 次。
如何安装 Tencent MPS?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tencent-mps」即可一键安装,无需额外配置。
Tencent MPS 是免费的吗?
是的,Tencent MPS 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Tencent MPS 支持哪些平台?
Tencent MPS 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Tencent MPS?
由 ollielin(@ollielin)开发并维护,当前版本 v1.1.5。
推荐 Skills