Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
免费在 GitHub 公开
gcloud-cli
Google Cloud CLI operations and resource management
中文简介正在准备中。当前显示原文说明。
集成工具Google Cloud
查看安装方法包含的文件（10）
- SKILL.md3.9 KB
- commands/gcloud-cli.md110 B
- hooks/post-execute.cjs850 B
- hooks/pre-execute.cjs856 B
- references/research-requirements.md322 B
- rules/gcloud-cli.md282 B
- schemas/input.schema.json257 B
- schemas/output.schema.json618 B
- scripts/main.cjs1.6 KB
- templates/implementation-template.md184 B
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Google Cloud CLI Skill
Installation
The skill invokes the gcloud CLI. Install and initialize:
- Linux/macOS:
curl https://sdk.cloud.google.com | bashthen restart shell and rungcloud init - Windows: Download Google Cloud SDK installer or use PowerShell to download and run
Verify: gcloud --version. Configure: gcloud init
Cheat Sheet & Best Practices
Config: gcloud config set project <id>; gcloud config list; gcloud config configurations create/activate <name> — switch projects.
Auth: gcloud auth login; use --impersonate-service-account for SA; --access-token-file for CI.
Hacks: Use --format="table(name,zone,status)" or --format=json + jq to cut output. Use --flags-file=file.yaml for long or repeated flags. Use named configurations for dev/staging/prod. Run gcloud components update periodically.
Certifications & Training
Free: Google Cloud Learn and Google Skills — Innovators Program (35 credits/month). Certs: Cloud Digital Leader, Cloud Engineer (associate), Cloud Architect/DevOps (professional). Skill data: Config, auth, compute/storage/IAM; no exposed service-account keys.
Hooks & Workflows
Suggested hooks: Pre-deploy: gcloud config get-value project. Use when devops is routed for GCP tasks (contextual: gcp_project).
Workflows: Use with devops (contextual: gcp_project). Flow: detect GCP → load gcloud-cli → run CLI via skill script.
Overview
Google Cloud Platform CLI operations. 90%+ context savings.
Requirements
- gcloud CLI installed
- GOOGLE_PROJECT_ID environment variable
- Authenticated via gcloud auth
Tools (Progressive Disclosure)
Compute
| Tool | Description | Confirmation |
|---|---|---|
| instances-list | List VM instances | No |
| instances-create | Create VM | Yes |
| instances-delete | Delete VM | REQUIRED |
Storage
| Tool | Description | Confirmation |
|---|---|---|
| storage-ls | List buckets/objects | No |
| storage-cp | Copy objects | Yes |
| storage-rm | Delete objects | Yes |
IAM
| Tool | Description |
|---|---|
| iam-list | List IAM policies |
| service-accounts | List service accounts |
Logging
| Tool | Description |
|---|---|
| logs-read | Read logs |
| logs-tail | Tail logs in real-time |
BLOCKED
| Tool | Status |
|---|---|
| projects delete | BLOCKED |
| iam-policy delete | BLOCKED |
Agent Integration
- devops (primary): Cloud operations
- gcp-cloud-agent (primary): GCP specific
- cloud-integrator (secondary): Multi-cloud
Security
⚠️ Never expose service account keys ⚠️ Resource deletion requires confirmation
Memory Protocol (MANDATORY)
Before starting:
Read .claude/context/memory/learnings.md
After completing:
- New pattern ->
.claude/context/memory/learnings.md - Issue found ->
.claude/context/memory/issues.md - Decision made ->
.claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新