Sap Extension Creator
heshengtao/super-agent-party
Create Super Agent Party (SAP) extensions. An agent skill from heshengtao/super-agent-party.
腾讯云对象存储(COS)和数据万象(CI)集成技能。当用户需要上传、下载、管理云存储文件, 或需要进行图片处理(质量评估、超分辨率、抠图、二维码识别、水印)、智能图片搜索、 文档转PDF、视频智能封面生成等操作时使用此技能。
$ npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills tencent-cloud-cos --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tencentcloud-cos-skill .claude/skills/tencent-cloud-cos && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tencent-cloud-cos" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skill into .claude/skills/tencent-cloud-cos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tencent-cloud-cos", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills tencent-cloud-cos --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tencentcloud-cos-skill .agents/skills/tencent-cloud-cos && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tencent-cloud-cos" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skill into .agents/skills/tencent-cloud-cos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tencent-cloud-cos", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills tencent-cloud-cos --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tencentcloud-cos-skill .cursor/skills/tencent-cloud-cos && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tencent-cloud-cos" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skill into .cursor/skills/tencent-cloud-cos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tencent-cloud-cos", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/tencentcloud-cos-skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills tencent-cloud-cos --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tencentcloud-cos-skill .gemini/skills/tencent-cloud-cos && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tencent-cloud-cos" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skill into .gemini/skills/tencent-cloud-cos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tencent-cloud-cos", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills tencent-cloud-cosInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tencentcloud-cos-skill .github/skills/tencent-cloud-cos && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tencent-cloud-cos" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skill into .github/skills/tencent-cloud-cos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tencent-cloud-cos", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills tencent-cloud-cos --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tencentcloud-cos-skill .opencode/skills/tencent-cloud-cos && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tencent-cloud-cos" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/tencentcloud-cos-skill into .opencode/skills/tencent-cloud-cos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tencent-cloud-cos", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
tencent-cloud-cos腾讯云对象存储(COS)和数据万象(CI)集成技能。当用户需要上传、下载、管理云存储文件, 或需要进行图片处理(质量评估、超分辨率、抠图、二维码识别、水印)、智能图片搜索、 文档转PDF、视频智能封面生成等操作时使用此技能。
Tencent Cloud Cos is an agent skill from LeoYeAI/openclaw-master-skills. 腾讯云对象存储(COS)和数据万象(CI)集成技能。当用户需要上传、下载、管理云存储文件, 或需要进行图片处理(质量评估、超分辨率、抠图、二维码识别、水印)、智能图片搜索、 文档转PDF、视频智能封面生成等操作时使用此技能。
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 22 other files, including scripts and reference files (for example `QUICK_START.md`, `README.md` and `_meta.json`).
It sits in Documents & Office. It works with Tencent Cloud, Model Context Protocol, npm and Node.js. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 3 files in scripts/ (Shell, Python and JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
npxnpmnodepipFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
console.cloud.tencent.comtencentcloud.comgithub.comcloud.tencent.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
TENCENT_COS_SECRET_KEYTENCENT_COS_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Tencent Cloud Cos loads about 3.2k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 659 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 659 words, ~3,212 tokens.
.claude/skills/tencent-cloud-cos/SKILL.md (or your agent's skills folder). This skill also uses 17 other files; get the full folder from GitHub.通过 cos-mcp MCP 工具 + Node.js SDK 脚本 + COSCMD 管理腾讯云对象存储和数据万象。
当用户首次要求操作 COS 时,按以下流程操作:
{baseDir}/scripts/setup.sh --check-only如果输出显示一切 OK(cos-mcp 已安装、凭证已配置),跳到「执行策略」。
告诉用户:
我需要你的腾讯云凭证来连接 COS 存储服务。请提供:
- SecretId — 腾讯云 API 密钥 ID
- SecretKey — 腾讯云 API 密钥 Key
- Region — 存储桶区域(如 ap-guangzhou)
- Bucket — 存储桶名称(格式 name-appid,如 mybucket-1250000000)
- DatasetName(可选) — 数据万象数据集名称(仅智能搜索需要)
- Domain(可选) — 自定义域名,用于替换默认的 COS 访问域名(如 cdn.example.com)
- ServiceDomain(可选) — 自定义服务域名,用于自定义 COS API 请求域名
- Protocol(可选) — 协议,如 https 或 http
你可以在 腾讯云控制台 > 访问管理 > API密钥管理 获取密钥, 在 COS 控制台 查看存储桶信息。
⚠️ 安全要求:必须使用子账号密钥,仅授予 COS 相关权限(如
QcloudCOSDataFullControl),严禁使用主账号密钥。详见下方「最小权限与子账号密钥」章节。
推荐方式(凭证不会出现在 shell 历史中):
export TENCENT_COS_SECRET_ID="<SecretId>"
export TENCENT_COS_SECRET_KEY="<SecretKey>"
export TENCENT_COS_REGION="<Region>"
export TENCENT_COS_BUCKET="<Bucket>"
# 可选:
# export TENCENT_COS_DATASET_NAME="<DatasetName>"
# export TENCENT_COS_DOMAIN="<Domain>"
# export TENCENT_COS_SERVICE_DOMAIN="<ServiceDomain>"
# export TENCENT_COS_PROTOCOL="<Protocol>"
{baseDir}/scripts/setup.sh --from-env备选方式(凭证会出现在 shell 历史中,不推荐):
{baseDir}/scripts/setup.sh --secret-id "<SecretId>" --secret-key "<SecretKey>" --region "<Region>" --bucket "<Bucket>"脚本会自动:
node_modules(npm install,非全局)node_modules(npm install,非全局;通过 npx mcporter 调用)~/.zshrc / ~/.bashrc)~/.mcporter/mcporter.json,写入 cos-mcp 服务器配置(凭证通过 env 字段传递,权限 600)~/.cos.conf(权限 600);不会自动安装 coscmd用户安装前应了解 setup.sh 会产生的所有变更:
| 变更类型 | 具体内容 | 持久性 |
|---|---|---|
| npm 本地安装 | cos-mcp、cos-nodejs-sdk-v5、mcporter 安装到项目 node_modules/ | 持久(仅限项目目录) |
| 项目文件 | 如无 package.json 则创建 | 持久(仅限项目目录) |
| 配置文件 | ~/.mcporter/mcporter.json(含凭证) | 持久(用户主目录) |
| 配置文件 | ~/.cos.conf(仅当 coscmd 已安装时) | 持久(用户主目录) |
| 环境变量 | TENCENT_COS_* export 到当前 session | 临时(关闭终端失效) |
⚠️ 脚本不会:
- 写入
~/.zshrc/~/.bashrc或任何 shell 启动文件- 执行
npm install -g(全局安装)- 执行
pip install(不自动安装 Python 包)- 修改用户 shell 配置文件的权限
凭证写入的文件(⚠️ 持久化存储凭证会增加暴露风险,详见「安全注意事项」):
| 文件 | 内容 | 权限 |
|---|---|---|
~/.mcporter/mcporter.json | MCP 服务器配置中的 env 字段含凭证 | 600 |
~/.cos.conf | coscmd 配置(仅当 coscmd 已安装时) | 600 |
如需完全清理凭证:
rm -f ~/.mcporter/mcporter.json ~/.cos.conf如需持久化环境变量,用户可自行在 shell 配置中添加 export 语句。 强烈建议使用子账号最小权限密钥,详见「最小权限与子账号密钥」章节。
设置完成后即可开始使用。
三种方式按优先级降级,确保操作始终可完成:
scripts/cos_node.mjs 执行存储操作mcporter + cos-mcp 可用?(npx mcporter --version && 配置存在)
├─ 是 → 使用方式一 mcporter 调用(全部功能)
└─ 否 → cos-mcp MCP 工具可直接调用?(getCosConfig 返回结果)
├─ 是 → 使用方式一直接调用(全部功能)
└─ 否 → Node.js + cos-nodejs-sdk-v5 可用?
├─ 是 → 使用方式二(存储操作)
└─ 否 → coscmd 可用?(which coscmd)
├─ 是 → 使用方式三(存储操作)
└─ 否 → 运行 setup.sh 安装判断方式一(mcporter):npx mcporter --version 成功 且 cat ~/.mcporter/mcporter.json | grep cos-mcp 有输出。
判断方式一(直接):尝试调用 getCosConfig MCP 工具,若返回结果则可用。
判断方式二:node -e "require('cos-nodejs-sdk-v5')" 成功则可用。
判断方式三:which coscmd 有输出则可用。
MCP 配置模板见 references/config_template.json。
通过 mcporter 命令行调用 cos-mcp MCP 工具:
npx mcporter call cos-mcp.<tool_name> --config ~/.mcporter/mcporter.json --output json [--args '<JSON>']列出所有可用工具:
npx mcporter list cos-mcp --config ~/.mcporter/mcporter.json --schema判断 mcporter 是否可用:npx mcporter --version 成功 且 ~/.mcporter/mcporter.json 包含 cos-mcp 配置。
如果 mcporter 不可用,可回退到客户端直接调用 MCP 工具(getCosConfig 等)。
| 类别 | 说明 |
|---|---|
| 存储操作 | 上传、下载、列出、获取签名URL |
| 图片处理 | 质量评估、超分辨率、抠图、二维码识别、水印 |
| 智能搜索 | 以图搜图、文本搜图(需预建数据集) |
| 文档媒体 | 文档转PDF、视频智能封面(异步任务) |
以下示例同时展示两种调用格式。mcporter 格式省略公共前缀
npx mcporter call cos-mcp.和--config ~/.mcporter/mcporter.json --output json。 完整 mcporter 命令:npx mcporter call cos-mcp.<tool> --config ~/.mcporter/mcporter.json --output json --args '<JSON>'
# 上传本地文件(mcporter 格式)
npx mcporter call cos-mcp.putObject --config ~/.mcporter/mcporter.json --output json --args '{"filePath":"/path/to/file.jpg","targetDir":"images"}'
# 上传本地文件(客户端直接调用格式)
putObject filePath="/path/to/file.jpg" targetDir="images"
# 上传字符串内容
putString content="hello world" fileName="test.txt" targetDir="docs"
# 通过 URL 上传
putObjectSourceUrl sourceUrl="https://example.com/image.png" targetDir="images"
# 列出文件
getBucket Prefix="images/"
# 下载文件
getObject objectKey="images/photo.jpg"
# 获取签名下载链接
getObjectUrl objectKey="images/photo.jpg"# 图片质量评估
assessQuality objectKey="images/photo.jpg"
# AI 超分辨率
aiSuperResolution objectKey="images/photo.jpg"
# AI 智能抠图
aiPicMatting objectKey="images/photo.jpg"
# 二维码识别
aiQrcode objectKey="images/qrcode.jpg"
# 添加文字水印
waterMarkFont objectKey="images/photo.jpg" text="版权所有"
# 获取图片元信息
imageInfo objectKey="images/photo.jpg"# 以图搜图
imageSearchPic uri="https://example.com/query.jpg"
# 文本搜图
imageSearchText text="蓝天白云"# 文档转 PDF
createDocToPdfJob objectKey="docs/report.docx"
# 查询任务结果
describeDocProcessJob jobId="<jobId>"
# 视频智能封面
createMediaSmartCoverJob objectKey="videos/demo.mp4"
# 查询任务结果
describeMediaJob jobId="<jobId>"工具详细参数定义见 references/api_reference.md。
官方文档: https://www.tencentcloud.com/zh/document/product/436/8629
当 cos-mcp 不可用时,通过 scripts/cos_node.mjs 执行存储操作。凭证从环境变量读取。
支持的环境变量:
TENCENT_COS_SECRET_ID / TENCENT_COS_SECRET_KEY / TENCENT_COS_REGION / TENCENT_COS_BUCKET(必需)TENCENT_COS_DOMAIN / TENCENT_COS_SERVICE_DOMAIN / TENCENT_COS_PROTOCOL(可选,自定义域名)以下省略
node {baseDir}/scripts/cos_node.mjs前缀。完整格式:node {baseDir}/scripts/cos_node.mjs <action> [options]
# 上传文件
upload --file /path/to/file.jpg --key remote/path/file.jpg
# 上传字符串
put-string --content "文本内容" --key remote/file.txt --content-type "text/plain"
# 下载文件
download --key remote/path/file.jpg --output /path/to/save/file.jpg
# 列出文件
list --prefix "images/"
# 获取签名 URL
sign-url --key remote/path/file.jpg --expires 3600
# 查看文件信息
head --key remote/path/file.jpg
# 删除文件
delete --key remote/path/file.jpg所有命令输出 JSON 格式,success: true 表示成功,退出码 0。
仅支持存储操作,不支持图片处理、智能搜索、文档转换。
官方文档: https://www.tencentcloud.com/zh/document/product/436/10976
当方式一和方式二均不可用时使用。配置持久化在 ~/.cos.conf。
自定义域名支持(有限):
-e ENDPOINT 参数,设置后 Region 失效http,对应 coscmd 的 --do-not-use-ssl 参数# 上传
coscmd upload /path/to/file.jpg remote/path/file.jpg
coscmd upload -r /path/to/folder/ remote/folder/
# 下载
coscmd download remote/path/file.jpg /path/to/save/file.jpg
coscmd download -r remote/folder/ /path/to/save/
# 列出文件
coscmd list images/
# 删除
coscmd delete remote/path/file.jpg
coscmd delete -r remote/folder/ -f
# 签名 URL
coscmd signurl remote/path/file.jpg -t 3600
# 文件信息
coscmd info remote/path/file.jpg
# 复制/移动
coscmd copy <BucketName-APPID>.cos.<Region>.myqcloud.com/source.jpg dest.jpg
coscmd move <BucketName-APPID>.cos.<Region>.myqcloud.com/source.jpg dest.jpg仅支持存储操作,不支持图片处理、智能搜索、文档转换。
| 功能 | 方式一 cos-mcp | 方式二 Node SDK | 方式三 COSCMD |
|---|---|---|---|
| 上传文件 | ✅ | ✅ | ✅ |
| 上传字符串/Base64 | ✅ | ✅ | ❌ |
| 通过 URL 上传 | ✅ | ❌ | ❌ |
| 下载文件 | ✅ | ✅ | ✅ |
| 列出文件 | ✅ | ✅ | ✅ |
| 获取签名 URL | ✅ | ✅ | ✅ |
| 删除文件 | ❌ | ✅ | ✅ |
| 查看文件信息 | ❌ | ✅ | ✅ |
| 递归上传/下载目录 | ❌ | ❌ | ✅ |
| 图片处理(CI) | ✅ | ❌ | ❌ |
| 智能搜索 | ✅ | ❌ | ❌ |
| 文档转 PDF | ✅ | ❌ | ❌ |
| 视频智能封面 | ✅ | ❌ | ❌ |
setup.sh 在处理凭证时遵循以下原则:
~/.zshrc、~/.bashrc 或其他 shell RC 文件node_modules/,不使用 npm install -gpip install 或其他系统级包安装⚠️ 重要安全提示:setup.sh 会将 SecretId/SecretKey 持久化写入磁盘文件。虽然文件权限设为 600(仅当前用户可读写),但持久存储仍增加了凭证暴露风险(如磁盘被窃取、备份泄露、恶意软件读取等)。用户应充分了解此风险。
setup.sh 运行后,凭证会存储在以下文件中:
| 文件 | 写入场景 | 存储内容 | 权限 | 风险 |
|---|---|---|---|---|
~/.mcporter/mcporter.json | 始终写入 | cos-mcp 服务器配置的 env 字段含 SecretId/SecretKey | 600 | 凭证明文存储在用户主目录 |
~/.cos.conf | 仅当 coscmd 已预装时 | coscmd 配置含 SecretId/SecretKey | 600 | 凭证明文存储在用户主目录 |
降低风险的措施:
rm -f ~/.mcporter/mcporter.json ~/.cos.conf本技能通过 npm 安装以下 registry 包(标准 npm 安装,无任意 URL 下载):
cos-mcp — 腾讯云 COS MCP 服务器cos-nodejs-sdk-v5 — 腾讯云 COS Node.js SDKmcporter — MCP 命令行工具这些包来自 npm 公共 registry,与所有 npm 包一样存在供应链风险。建议在安装前通过 npm info <package> 核实包的发布者和版本。
⚠️ 永远不要使用主账号密钥。主账号密钥拥有账户下所有资源的完全控制权,一旦泄露后果严重。
推荐创建专用子账号并授予仅限 COS 操作的最小权限策略:
QcloudCOSDataReadOnlyAccess — 仅读取(如果只需下载/列出)QcloudCOSDataFullControl — COS 数据读写(推荐,如需上传+下载)QcloudCIFullAccess{
"statement": [{
"effect": "allow",
"action": ["cos:*"],
"resource": ["qcs::cos:<Region>::uid/<APPID>:<BucketName>/*"]
}]
}对于更高安全要求的场景,建议使用腾讯云 STS 临时凭证:
TENCENT_COS_TOKEN 环境变量)--from-env 模式设置凭证,避免凭证出现在 shell 历史记录中ps aux 进程列表中rm -f ~/.mcporter/mcporter.json ~/.cos.conf 清除持久化凭证{baseDir}/scripts/setup.sh --check-only 检查环境--config ~/.mcporter/mcporter.json 和 --output json(使用 npx mcporter 调用)objectKey/cospath/--key)为存储桶内的相对路径,如 images/photo.jpgjobId 轮询结果getObjectUrl 或 sign-url 返回访问链接setup.sh --check-only 诊断环境问题scripts/cos_node.mjsreferences/api_reference.mdreferences/config_template.json© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 17 other files (scripts, references) in skills/tencentcloud-cos-skill of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Tencent Cloud Cos next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tencent Cloud Cos this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.2k | Automated safety check: Pass | MIT | |
| Sap Extension Creatorheshengtao/super-agent-party | 2.7k | — | ~6k | Automated safety check: Pass | AGPL-3.0 | |
| Jpagecode2rich/jpage | 175 | — | ~3.2k | Automated safety check: Notes | MIT | |
| Spreadsheet Managementfreema/mcp-gsheets | 100 | — | ~486 | Automated safety check: Pass | MIT | |
| Slidev CLI Skilldskilld-dev/vue-ecosystem-skills | 181 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Tencentcloud Cosinfometa/workbuddyskills | 348 | — | ~4.4k | Automated safety check: Notes | None |
heshengtao/super-agent-party
Create Super Agent Party (SAP) extensions. An agent skill from heshengtao/super-agent-party.
code2rich/jpage
即页(jpage)统一技能:生成 HTML/Markdown 内容、制作 reveal.js 幻灯片、使用内容模板市场风格、上传到即页并管理文件。所有内容生产与文件管理操作都通过本技能完成。
freema/mcp-gsheets
This skill should be used when the user asks about Google Sheets, spreadsheets, cells, rows, columns, charts, or data tables.
skilld-dev/vue-ecosystem-skills
Build, present, and ship Slidev decks with @slidev/cli. An agent skill from skilld-dev/vue-ecosystem-skills.
infometa/workbuddyskills
腾讯云对象存储(COS)和数据万象(CI)集成技能。覆盖文件存储管理、AI处理和知识库三大核心场景. An agent skill from infometa/workbuddyskills.
agent-skills-hub/agent-skills-hub
Formula WorkPaper runtime and MCP server for AI agents and Node.js services.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
腾讯云对象存储(COS)和数据万象(CI)集成技能。当用户需要上传、下载、管理云存储文件, 或需要进行图片处理(质量评估、超分辨率、抠图、二维码识别、水印)、智能图片搜索、 文档转PDF、视频智能封面生成等操作时使用此技能。. Tencent Cloud Cos is an agent skill from LeoYeAI/openclaw-master-skills.
Tencent Cloud Cos fits situations like: documents & Office work in your project.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a claude-code`. Or copy the skill folder (skills/tencentcloud-cos-skill in LeoYeAI/openclaw-master-skills) into .claude/skills/tencent-cloud-cos in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a codex`. Or copy the skill folder (skills/tencentcloud-cos-skill in LeoYeAI/openclaw-master-skills) into .agents/skills/tencent-cloud-cos in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill tencent-cloud-cos -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tencent-cloud-cos, .gemini/skills/tencent-cloud-cos, .github/skills/tencent-cloud-cos and .opencode/skills/tencent-cloud-cos in your project.
Going by SKILL.md and its folder, Tencent Cloud Cos needs a shell, Python and JavaScript for the scripts in its folder, the command-line tools its instructions call (npx, npm, node and pip) and credentials named TENCENT_COS_SECRET_KEY and TENCENT_COS_TOKEN. Our summary lists: Python 3; Node.js; A Bash shell; A credential in TENCENT_COS_SECRET_KEY.
SKILL.md names 4 domains. As links in the text: console.cloud.tencent.com, tencentcloud.com, github.com and cloud.tencent.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Tencent Cloud Cos is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Tencent Cloud Cos: Sap Extension Creator (heshengtao/super-agent-party, 2.7k stars), Jpage (code2rich/jpage, 175 stars), Spreadsheet Management (freema/mcp-gsheets, 100 stars) and Slidev CLI Skilld (skilld-dev/vue-ecosystem-skills, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.