MCP HubMCP Hub
返回技能列表

when-configuring-sandbox-security-use-sandbox-configurator

DNYoussef
更新于 2 days ago
23 次查看
9
2
9
在 GitHub 上查看
其他general

关于

This skill routes sandbox security configuration requests to the dedicated `sandbox-configurator` SOP. It enforces structured constraint analysis and safety controls like isolation and deny-by-default networking. Use it when designing sandbox policies for filesystem, network, secrets, or observability.

快速安装

Claude Code

推荐
插件命令推荐
/plugin add https://github.com/DNYoussef/context-cascade
Git 克隆备选方式
git clone https://github.com/DNYoussef/context-cascade.git ~/.claude/skills/when-configuring-sandbox-security-use-sandbox-configurator

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Purpose

Activate the sandbox-configurator workflow for sandbox policy design (filesystem, network, secrets, observability) using skill-forge structure-first and prompt-architect constraint/confidence rules.

SOP (Routing)

  1. Scope: Capture HARD/SOFT/INFERRED constraints (runtime, mounts, network needs, secrets, observability).
  2. Safety: Require isolation, deny-by-default network, secure secret handling, and rollback plan.
  3. Execute: Invoke sandbox-configurator SOP; record MCP tags (WHO=sandbox-configurator-{session}, WHY=skill-execution).
  4. Validate: Ensure allowed workflows pass and blocked paths fail; attach evidence with confidence ceilings.
  5. Deliver: Policy pack + validation log archived under skills/security/specialized-tools/when-configuring-sandbox-security-use-sandbox-configurator/{project}/{timestamp}.

Output Format

  • Scope/constraints table, routed actions, validation summary, and confidence line.

Confidence: 0.70 (ceiling: inference 0.70) - Routing skill synced with updated sandbox-configurator SOP.

GitHub 仓库

DNYoussef/context-cascade
路径: skills/security/specialized-tools/when-configuring-sandbox-security-use-sandbox-configurator

相关推荐技能

algorithmic-art

该Skill使用p5.js创建包含种子随机性和交互参数探索的算法艺术,适用于生成艺术、流场或粒子系统等需求。它能自动生成算法哲学文档(.md)和对应的交互式艺术代码(.html/.js),确保作品原创性避免侵权。开发者可通过定义计算美学理念快速获得可交互的艺术实现方案。

查看技能

subagent-driven-development

开发

该Skill用于在当前会话中执行包含独立任务的实施计划,它会为每个任务分派一个全新的子代理并在任务间进行代码审查。这种"全新子代理+任务间审查"的模式既能保障代码质量,又能实现快速迭代。适合需要在当前会话中连续执行独立任务,并希望在每个任务后都有质量把关的开发场景。

查看技能

executing-plans

设计

该Skill用于当开发者提供完整实施计划时,以受控批次方式执行代码实现。它会先审阅计划并提出疑问,然后分批次执行任务(默认每批3个任务),并在批次间暂停等待审查。关键特性包括分批次执行、内置检查点和架构师审查机制,确保复杂系统实现的可控性。

查看技能

cost-optimization

其他

这个Claude Skill帮助开发者优化云成本,通过资源调整、标记策略和预留实例来降低AWS、Azure和GCP的开支。它适用于减少云支出、分析基础设施成本或实施成本治理策略的场景。关键功能包括提供成本可视化、资源规模调整指导和定价模型优化建议。

查看技能