用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Kilo-Org/kilo-marketplace --skill gcp-iam命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.
Expert guidance for Apache Arrow, the cross-language columnar memory format for analytics workloads. Helps developers use Arrow for high-performance data interchange between systems, zero-copy reads, and efficient columnar processing in Python (PyArrow) and JavaScript (Arrow JS).
Guides agents through Apache Hudi lakehouse design. Use when managing incremental upserts, record-level mutations, timeline behavior, compaction, and Hudi-based lakehouse tables.
正在显示 SKILL.md
基于 SOC 职业分类
| name | gcp-iam |
| description | Manages identity and access control for Google Cloud resources using IAM policies and roles. |
| metadata | {"upstream":{"cluster":"cloud-gcp","tags":["gcp","iam","access-control"],"authorization_required":false,"scope":"general","model_hint":"claude-sonnet","embedding_hint":"gcp iam access management policies roles permissions google cloud security"},"category":"development","source":{"repository":"https://github.com/alphaonedev/openclaw-graph","path":"skills/cloud-gcp/gcp-iam","license_path":"LICENSE","commit":"74b6037eb3320f51167ff1a72dd5f5e22f0f30e7"}} |
This skill delegates all GCP provisioning and operations to the official Google Cloud Python client libraries.
# Core GCP client library
pip install google-cloud-python
# Vertex AI + Agent Engine (AI/ML workloads)
pip install google-cloud-aiplatform
# Specific service clients (install only what you need)
pip install google-cloud-bigquery # BigQuery
pip install google-cloud-storage # Cloud Storage
pip install google-cloud-pubsub # Pub/Sub
pip install google-cloud-run # Cloud Run
SDK Docs: https://github.com/googleapis/google-cloud-python Vertex AI SDK: https://cloud.google.com/vertex-ai/docs/python-sdk/use-vertex-ai-python-sdk
Use the Google Cloud Python SDK for all GCP provisioning and operational actions. This skill provides architecture guidance, cost modeling, and pre-flight requirements — the SDK handles execution.
Consult this skill for:
| Capability | Tool |
|---|---|
| LLM agents | Vertex AI Agent Engine |
| Model serving | Vertex AI Model Garden |
| RAG | Vertex AI Search + Embeddings API |
| Multi-agent | Agent Development Kit (google/adk-python) |
| MCP | Vertex AI Extensions (MCP-compatible) |