Core Alibaba Cloud plugin for OpenAPI SDK code generation through a constrained MCP server.
Guide for Alibaba Cloud CLI (aliyun) command syntax, plugin system, parameter naming, and best practices. Use this skill to generate correct CLI commands, understand plugin vs built-in command differences, structured parameter syntax, output filtering, pagination, and error troubleshooting. This skill is a CLI knowledge reference — when MCP tools (AlibabaCloud___CallCLI, etc.) are available, always prefer MCP tools for execution rather than running aliyun commands locally in the shell.
Use this skill when users want to search, discover, browse, or find Alibaba Cloud (阿里云) agent skills. Triggers include: "find a skill for X", "search alicloud skills", "阿里云有什么 skill","阿里云", "搜索阿里云技能", "有没有管理 ECS/RDS/OSS 的 skill", "阿里云 skills 有哪些类目", "帮我找一个 skill", "browse alicloud skills", "list alicloud skill categories", "is there an alicloud skill that can...", "what alicloud skills are available", "XX Skill 的内容是什么", "我想了解阿里云 XX Skill 具体做什么","帮我安装阿里云 Skill","使用阿里云相关的skill", "阿里云 agent skill 市场", "搜一下阿里云的 skill".
Generate or modify code that calls Alibaba Cloud OpenAPIs. Use when the user asks for Alibaba Cloud SDK code, API parameters, endpoints, SDK dependencies, typed product SDK calls, or generic OpenAPI calls.
Generate and modify Alibaba Cloud Terraform HCL code. Use when the user asks for Terraform configurations, alicloud provider resources, HCL code generation, infrastructure as code for Alibaba Cloud, or modifications to existing Terraform files. Triggers on: write Terraform for Alibaba Cloud, create alicloud Terraform config, generate HCL for ECS, Terraform code for VPC, alicloud infrastructure as code, Terraform resource for RDS, modify Terraform configuration, alicloud provider Terraform, terraform best practices.
Shared reference for using Alibaba Cloud OpenAPI MCP Server Core effectively. Covers tool usage patterns, API exploration workflow, CLI command generation, cross-account access, and safety policy configuration. Referenced by other alibabacloud-core skills as the canonical guide for MCP Core interactions.
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Help AI coding agents build, deploy, and operate applications on Alibaba Cloud.
This repository provides Alibaba Cloud agent plugins, skills, MCP configuration, and validation tooling.
The repository currently provides:
alibabacloud-core and alibabacloud-spec-ops.alibabacloud-core includes an SDK usage skill that generates Alibaba Cloud OpenAPI interaction code through a constrained MCP server. alibabacloud-spec-ops delivers a planning-to-execution workflow for Alibaba Cloud infrastructure operations driven by Terraform and IaC Service.
.
├── plugins/
│ ├── alibabacloud-core/
│ ├── alibabacloud-spec-ops/
│ ├── alibabacloud-agent/
│ └── alibabacloud-data-analytics/
├── rules/
├── skills/
└── tools/
alibabacloud-core is the canonical source of truth for the hook
implementation. Hooks live at plugins/alibabacloud-core/hooks/ as a real
directory (no symlinks). When a new plugin (e.g. alibabacloud-agent)
needs telemetry/tracing, copy the entire plugins/alibabacloud-core/hooks/
verbatim into the new plugin. Do not maintain parallel implementations.
CI (tools/dev-hooks/verify-hooks.sh) fails on any divergence or on the
re-introduction of a hooks/ symlink.
| Plugin | Status | Description |
|---|---|---|
| alibabacloud-core | Active | Alibaba Cloud OpenAPI SDK code generation using the local alibabacloud-core MCP server. |
| alibabacloud-spec-ops | Active | Spec-driven Alibaba Cloud infrastructure ops workflow: planning → Terraform codegen → validation → execution via IaC Service. |
alibabacloud-agent | Placeholder | Reserved for future agent-focused capabilities. |
alibabacloud-data-analytics | Placeholder | Reserved for future analytics and data workflow capabilities. |
Python 3.10+ — hook handlers (pre-installed on most systems).
uv (provides uvx) — telemetry tracing view & mcp server:
# macOS
brew install uv
# Linux / WSL
curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env
Alibaba Cloud CLI (aliyun) — cloud operations:
# Linux amd64
curl -fsSL https://aliyuncli.alicdn.com/aliyun-cli-linux-latest-amd64.tgz | tar xz
# macOS
brew install aliyun-cli
npx openplugin acloudlabs-unofficial/alibabacloud-agent-toolkit
Automatically detects installed clients (Claude Code, Codex, QoderWork), lets you pick which plugins to install, and configures everything.
codex plugin marketplace add acloudlabs-unofficial/alibabacloud-agent-toolkit
Then open Codex /plugins and install alibabacloud-core and/or alibabacloud-spec-ops.
/plugin marketplace add acloudlabs-unofficial/alibabacloud-agent-toolkit
/plugin install alibabacloud-core@alibabacloud-agent-toolkit
/plugin install alibabacloud-spec-ops@alibabacloud-agent-toolkit
/reload-plugins
Use the one-command install above (npx openplugin), which handles QoderWork hook registration automatically.
The installer patches ~/.qoderwork/settings.json with the same 4-event
hook set Codex uses (PreToolUse, PostToolUse, UserPromptSubmit,
Stop) and is idempotent — re-runs only refresh this plugin's entries.
Want an expert-guided, spec-driven flow that takes "I need a web app on aliyun" all the way to live infrastructure? One command:
/alibabacloud-spec-ops:alibabacloud-planning I need a web app on aliyun
4 stages, auto-chained, one user gate (right before deploy):
npx claudepluginhub acloudlabs-unofficial/alibabacloud-agent-toolkit --plugin alibabacloud-coreAlibaba Cloud AI Ops Plugin - Infrastructure operations workflow with intelligent planning, validation, and execution powered by MCP tooling.
Memory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.