Engineering Skills
技能 警告 活跃23 engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365. 30+ Python tools (stdlib-only).
To provide AI coding agents with a comprehensive set of specialized skills and tools for a wide range of engineering, development, and business tasks.
功能
- Extensive skill library across multiple domains
- Bundled stdlib-only Python CLI tools
- Cross-platform compatibility with 12 AI coding agents
- Dedicated security auditing skill
- Comprehensive documentation and installation guides
使用场景
- Reviewing code and architecture with specialized skills
- Automating development workflows from scaffolding to deployment
- Performing security audits and compliance checks
- Generating content, analyzing data, and managing projects
非目标
- Providing a single, narrowly focused tool
- Requiring users to install external Python packages
- Limiting functionality to a single AI coding agent
Scope
- warning:Single responsibility principleThe extension bundles a very large number of skills across many diverse domains (engineering, marketing, finance, legal, etc.), which violates the single responsibility principle and may lead to poor trigger precision.
- info:Minimal I/O surfaceWhile the intent is for minimal I/O, the sheer number of skills and tools implies varying degrees of I/O surface across the collection. Specific examples are not detailed enough to confirm minimization for all.
- critical:Tool surface sizeThe repository contains 268 skills and 300+ Python tools, vastly exceeding the recommended limit and indicating a 'kitchen sink' approach that will overwhelm agents and users.
- info:Dry-run previewWhile the extension focuses on development and analysis, specific dry-run capabilities for state-changing operations are not explicitly detailed across the vast skill set.
Invocation
- info:Scoped toolsWhile many skills are listed, the core invocation mechanism seems to rely on selecting individual skills rather than a single generalist tool, but the exact tool breakdown per skill is not fully visible here.
- warning:Overlapping near-synonym toolsWith hundreds of skills and tools across many domains, it is highly probable that overlapping near-synonym tools exist, forcing agents to disambiguate complex choices.
- warning:Precise PurposeWhile individual skills likely have precise purposes, the overall collection is too broad and lacks explicit non-goals for the entire umbrella project, leading to potential confusion and trigger issues.
- warning:Concise FrontmatterThe `description` field in the SKILL.md frontmatter is quite long (255 characters) and keyword-stuffed, which could hinder precise routing.
Documentation
- info:Configuration & parameter referenceThe SKILL.md frontmatter and README mention Python tools and specific agent commands, but detailed parameter references for all these are not fully exposed in this context.
- critical:Concise BodyThe SKILL.md and README files are extremely long and contain an overwhelming amount of information, far exceeding the recommended limits and failing to delegate material to separate files effectively.
Execution
- info:ValidationThe project emphasizes Python tools and security auditing, suggesting validation practices, but detailed schema library usage across all tools is not explicitly stated.
Code Execution
- info:LoggingWhile not explicitly detailed, the 'production-ready' nature and security focus suggest logging practices are likely implemented for auditability, though not explicitly detailed here.
Compliance
- info:GDPRThe inclusion of GDPR and compliance-related skills indicates an awareness of data privacy, but specific data handling for all skills is not detailed.
Protocol
- info:Idempotent retry & timeoutsGiven the 'production-ready' claims, some level of retry and timeout handling is expected, but specifics are not detailed for the numerous skills.
Context
- critical:Progressive DisclosureThe SKILL.md and README files embed vast amounts of material inline, including extensive lists of skills and detailed explanations, rather than using progressive disclosure via separate reference files.
Practical Utility
- info:Edge casesThe 'skill-security-auditor' likely handles edge cases, and the 'production-ready' framing suggests some attention to failure modes, but specific documentation for all edge cases across hundreds of skills is not evident.
Portability
- info:Tool FallbackThe README mentions installation for multiple tools, implying some level of adaptability, but explicit fallbacks for missing tools or skill dependencies are not detailed.
- warning:Cross-skill couplingThe sheer number of skills and domains covered makes it highly likely that implicit coupling exists between skills, and the README does not explicitly cross-link or manage these potential dependencies.
Safety
- info:Halt on unexpected stateThe 'skill-security-auditor' and 'production-ready' claims suggest a cautious approach, but explicit machine-readable checklists for pre-conditions and halting on unexpected states are not detailed for all skills.
安装
请先添加 Marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install engineering-team@claude-code-skills质量评分
警告类似扩展
OpenClaw Release Maintainer
100Prepare or verify OpenClaw stable/beta releases, changelogs, release notes, publish commands, and artifacts.
Master Claude for Legal
100Master skill for legal teams using Claude. Loads the right reference for the user's question (privilege configuration, MCP hardening, verification, long documents, practice-area patterns, skill authoring) and routes to specialized starter skills (NDA triage, version diff, meeting brief, citation verification, status synthesis). Auto-invokes when the user mentions legal work, contracts, redlines, NDAs, privilege, attorney-client, court filings, depositions, regulatory compliance, or asks how to set up Claude for a law firm or in-house legal team.
Context Mode Ops
100使用并行子代理军队管理 context-mode GitHub 问题、PR、发布和营销。为每个任务编排 10-20 个动态代理。在分类问题、审查 PR、发布版本、撰写 LinkedIn 帖子、宣布发布、修复错误、合并贡献、验证 ENV 变量、测试适配器或同步分支时使用。
Azure Container Registry SDK for Python
100Azure Container Registry SDK for Python. Use for managing container images, artifacts, and repositories. Triggers: "azure-containerregistry", "ContainerRegistryClient", "container images", "docker registry", "ACR".
Azure App Configuration SDK for Python
100Azure App Configuration SDK for Python. Use for centralized configuration management, feature flags, and dynamic settings. Triggers: "azure-appconfiguration", "AzureAppConfigurationClient", "feature flags", "configuration", "key-value settings".
Ship Gate
100Pre-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for "run ship gate", "am I ready to ship", "pre-launch audit", "can I deploy", "push to production", "go live checklist", "preflight check". Not for CI/CD setup or infra provisioning.