Menu
一站式 GitHub 仓库配置初始化工具。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | gh-bootstrap |
| description | 一站式 GitHub 仓库配置初始化工具。 |
| allowed-tools | Task, AskUserQuestion, Read, Bash, Glob, Grep, Write |
基准路径:
.claude/skills/devops-specialist/references/domains/github-platform/bootstrap/
bootstrap/
├── phases/
│ ├── 01-detection.md
│ ├── 02-collection.md
│ ├── 02.1-quick-mode.md
│ ├── 02.2-custom-mode.md
│ ├── 02.3-full-mode.md
│ ├── 02.9-finalize-config.md
│ ├── 03-conflict.md
│ ├── 04-execution.md
│ └── 05-report.md
├── specs/
│ ├── detection-rules.md
│ ├── execution-rules.md
│ ├── manual-actions.md
│ ├── presets.md
│ └── template-catalog.md
├── templates/
│ └── README.md
└── SKILL.md
一站式 GitHub 仓库配置初始化工具，将项目配置时间从数小时缩短到几分钟。
┌─────────────────────────────────────────────────────────────────┐
│ gh-bootstrap Skill Architecture │
├─────────────────────────────────────────────────────────────────┤
│ │
│ SKILL.md (入口) │
│ ↓ │
│ Phase 1: Detection → 扫描项目，识别语言/框架/现有配置 │
│ ↓ │
│ Phase 2: Collection → 交互式收集配置 (AskUserQuestion) │
│ ↓ │
│ Phase 3: Conflict → 检测冲突，制定处理策略 │
│ ↓ │
│ Phase 4: Execution → 下载模板 + 直接复制（仅替换变量） │
│ ↓ │
│ Phase 5: Report → 生成执行报告和后续建议 │
│ │
└─────────────────────────────────────────────────────────────────┘
phases/(逻辑) + specs/(配置) + templates/(视图)⚠️ 禁止自行编写配置文件！必须遵循以下规则：
在开头调用问答式表单，询问用户的沟通语言（决定了与你沟通），询问用户编写后续模板使用的语言（Issue模板之类） 若用户确认了使用中文 or Chinese 你必须在后续的所有模板的编写都尽量以中文友好
Read specs/template-catalog.md → git clone 模板仓库 → Read 模板文件 → 直接复制 + 变量替换 → Write 输出
specs/template-catalog.md 获取精确的文件路径映射template-catalog.md 中下载对应的推荐仓库{{projectName}}、{{description}}、{{author}} 等）{{owner}}、{{repo}}、badges URL 等）node-version、python-version 等）为检测到的版本${{ secrets.* }}、${{ github.* }} 表达式（这些是 GitHub Actions 语法）@v4模板中的变量占位符必须全部替换，不能留空！ 这些变量在 Phase 2 收集阶段必须全部确定。
违反以上规则将导致工作流失效！详见 04-execution.md
用户触发 gh-bootstrap
│
▼
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Phase 1 │ ──▶ │ Phase 2 │ ──▶ │ Phase 3 │
│ Detection │ │ Collection │ │ Conflict │
│ 项目检测 │ │ 配置收集 │ │ 冲突检测 │
└─────────────┘ └─────────────┘ └─────────────┘
│
┌────────────────────────────────────────┘
▼
┌─────────────┐ ┌─────────────┐
│ Phase 4 │ ──▶ │ Phase 5 │
│ Execution │ │ Report │
│ 执行生成 │ │ 报告总结 │
└─────────────┘ └─────────────┘
{project-root}/
├── .github/
│ ├── workflows/
│ │ └── ci.yml
│ ├── ISSUE_TEMPLATE/
│ │ ├── bug_report.md
│ │ └── feature_request.md
│ ├── PULL_REQUEST_TEMPLATE.md
│ ├── dependabot.yml
│ ├── labels.yml
│ └── CODEOWNERS
├── README.md
├── LICENSE
├── .gitignore
└── CONTRIBUTING.md
| Document | Purpose |
|---|---|
| phases/01-detection.md | 智能项目检测 |
| phases/02-collection.md | 交互式配置收集 |
| phases/03-conflict.md | 冲突检测与处理 |
| phases/04-execution.md | 模板下载与直接复制 |
| phases/05-report.md | 执行报告 |
| specs/detection-rules.md | 检测规则定义 |
| specs/presets.md | 预设配置定义 |
| specs/template-catalog.md | 推荐模板仓库目录 |
Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
Specialist in self-healing data pipelines — uses air-gapped local SLMs and semantic clustering to automatically detect, classify, and fix data anomalies at scale. Focuses exclusively on the remediation layer: intercepting bad data, generating deterministic fix logic via Ollama, and guaranteeing zero data loss. Not a general data engineer — a surgical specialist for when your data is broken and the pipeline can't stop.
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.
Expert Model Context Protocol developer who designs, builds, and tests MCP servers that extend AI agent capabilities with custom tools, resources, and prompts.
创建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。
Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.