Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
enterprise-patterns
Apply enterprise architecture patterns for integration and governance
pluginagentmarketplace/custom-plugin-software-architect 1
-
architecture-documentation
Create and maintain architecture documentation using standard formats
pluginagentmarketplace/custom-plugin-software-architect 1
-
technical-leadership
Provide technical leadership guidance for reviews, mentoring, and decisions
pluginagentmarketplace/custom-plugin-software-architect 1
-
cloud-architecture
Design cloud-native architectures with service selection and cost optimization
pluginagentmarketplace/custom-plugin-software-architect 1
-
data-architecture
Design data architectures with modeling, pipelines, and governance
pluginagentmarketplace/custom-plugin-software-architect 1
-
api-documentation
Production-grade skill for API documentation creation including OpenAPI/Swagger specifications, REST endpoint documentation, authentication flows, and error handling guides.
pluginagentmarketplace/custom-plugin-technical-writer 3
-
code-examples
Production-grade skill for generating clear, well-documented code examples, implementation patterns, configuration files, and integration samples with multi-language support.
pluginagentmarketplace/custom-plugin-technical-writer 3
-
user-guides
Production-grade skill for creating comprehensive user guides, tutorials, step-by-step instructions, troubleshooting guides, and FAQ sections with quality metrics and validation.
pluginagentmarketplace/custom-plugin-technical-writer 3
-
code-quality
Code quality standards for reviewing code changes. Activated when reviewing PRs, implementing features, or discussing code quality. Triggers on requests to "review code", "check quality", "improve code", or "refactor".
ken2403/claude-paralell-dev-plugin 2
-
security-review
Security review checklist for code changes. Automatically activates when reviewing security-sensitive code, authentication, authorization, or data handling. Use when user asks to "check security", "review for vulnerabilities", "audit code", or when changes touch auth, crypto, user input, or API endpoints.
ken2403/claude-paralell-dev-plugin 2
-
novel-creator
Interactive novel creation workflow combining RPG-style storytelling with professional EPUB ebook production.
Use when users want to: (1) Create interactive stories/RPG games with branching choices, (2) Write full novels from story concepts,
(3) Generate novels with time-travel/fantasy/romance elements, (4) Convert markdown stories to EPUB ebooks,
(5) Create Chinese web novels with ancient poetry paired with modern lyrics, (6) Write light novels or serialized fiction.
Triggers: "write a novel", "create a story", "interactive fiction", "RPG story", "make an ebook", "穿越小说", "写小说", "创作故事", "制作电子书"
mave99a/novel-skill 4
-
acceptance-criteria
检查Acceptance Criteria格式和完整性,验证是否符合Given-When-Then结构、覆盖正常流程/边界条件/异常场景。适合在为User Story编写AC后、准备测试用例前使用,当需要验收AC质量时。帮助不熟悉BDD的PM/BA确保AC明确、可测试、覆盖完整,避免遗漏关键场景。
tikazyq/agentic-spec-forge 5
-
nfr-to-user-impact
将技术性的NFR(非功能需求)约束转换为用户能感知的影响描述,用业务语言解释技术约束的价值。适合在NFR定义完成后、需要向客户或管理层解释时使用,当NFR过于技术化时。帮助不熟悉技术术语的PM/客户/BA理解NFR的业务意义,让技术约束变得亲切易懂。
tikazyq/agentic-spec-forge 5
-
document-quality
多维度审查 Markdown 文档质量,覆盖结构、内容、格式、引用、元数据五大维度。当需要评审文档质量、统一格式规范、验收交付文档时使用。提供分级检查清单、通过标准、常见问题修复指南,支持从快速检查到深度审计的多层次需求。
tikazyq/agentic-spec-forge 5
-
principle-invest
评估用户故事质量的六维度框架(独立性、可协商、有价值、可估算、小粒度、可测试),系统化审查需求质量。当需要编写用户故事、评审需求文档、拆分史诗故事时使用。提供分级检查清单和低质量故事的改进建议。
tikazyq/agentic-spec-forge 5
-
principle-dry
识别并消除知识重复,确保系统中每条知识有唯一权威表示。当需要重构代码、整理文档、优化配置、建立单一数据源时使用。覆盖代码重复、数据冗余、文档重复三大维度,提供具体消除策略和权衡建议。
tikazyq/agentic-spec-forge 5
-
principle-kiss
保持设计和实现的简单性,识别并消除不必要的复杂度。当需要架构设计评审、代码简化重构、接口设计优化时使用。覆盖代码、架构、接口、流程四大维度,提供简单性检查清单和过度复杂性的诊断修复方法。
tikazyq/agentic-spec-forge 5
-
code-review
执行代码审查流程(提交PR→自查→同行审查→反馈修改→合并),覆盖功能正确性、代码质量、测试完整性、安全合规四大维度。当提交Pull Request、进行结对编程、执行代码走查、需要知识共享时使用。支持L1/L2/L3三级审查深度。
tikazyq/agentic-spec-forge 5
-
code-quality
执行代码质量门禁检查(测试通过→覆盖率→Lint→GOAL追溯→可提交),验证单元测试覆盖率≥80%、集成测试通过率≥95%、代码规范零错误。当完成代码实现、准备提交代码、需要质量验证、进行提交前自检时使用。确保代码可合并。
tikazyq/agentic-spec-forge 5
-
tdd-cycle
执行 TDD 红绿重构循环(RED→GREEN→REFACTOR→REPEAT),通过先写失败测试、最小代码实现、保持绿色重构的节奏驱动开发。当启动功能开发、需要测试驱动节奏、进行迭代编码、追求高测试覆盖率时使用。提供检查清单和节奏控制。
tikazyq/agentic-spec-forge 5
-
refactoring
执行代码重构(识别坏味道→选择手法→小步修改→运行测试),在保持外部行为不变前提下改进内部结构。当TDD进入REFACTOR阶段、发现代码坏味道、需要消除重复代码、优化代码结构时使用。支持提取方法、类、参数对象等重构手法。
tikazyq/agentic-spec-forge 5
-
arch-options-compare
比较多个架构方案(单体/微服务等),从SOLID原则、成本、复杂度等维度评分,生成对比表和推荐方案。当需要向客户解释架构选择或ADR决策时使用。
tikazyq/agentic-spec-forge 5
-
dev-tech-view-supplement
根据设计补充Dev视角的技术细节(数据库/API/通信协议),帮助Dev快速进入实施。当L1/L2设计缺乏技术细节、或准备向Dev交付前使用。
tikazyq/agentic-spec-forge 5
-
design-consistency-check
检查VS↔SD/DM一致性(value_path是否与序列图/数据模型匹配),生成不一致项清单和修复建议。当Self-Reflection报告一致性问题或准备CONSTRAINT验收前使用。
tikazyq/agentic-spec-forge 5