Search Skills
Find the perfect capability for your agent.
documentation-writer
Activates when creating or improving technical documentation, READMEs, and API docs
codebase-librarian
Create a comprehensive inventory of a codebase. Map structure, entry points, services, infrastructure, domain models, and data flows. Pure documentation—no opinions or recommendations.
writing-plans
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
project-specification-writer
Generate a complete software specification document for the current project/repo, including architecture, data model, key processes, pseudocode, and Mermaid diagrams (context, container/deployment, module relations, sequence, ER, class, flowchart, state).
openapi-spec-generation
Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns.
global-commenting
Write self-documenting code with minimal, helpful comments that explain complex logic without documenting temporary changes or fixes. Use this skill when adding comments to code, documenting functions or classes, or explaining complex algorithms. When writing or editing any code file that may benefit from explanatory comments. When reviewing existing comments to ensure they remain evergreen and relevant. When deciding whether code needs comments or if better naming and structure would be clearer. This skill applies to all code files in any programming language including `.js`, `.ts`, `.py`, `.rb`, `.java`, `.go`, `.php`, and others.
fetching-npm-source
Fetches source code for npm packages and GitHub repositories to provide AI agents with implementation details beyond types. Use when you need to understand how a package works internally or reference its actual implementation.
spec-drafting
Creates detailed specification documents using standardized templates. Focuses on clarity, rigor, and implementability, utilizing `spec-refactoring` for final polish.
documentation-system
Standards for documenting codebases. Use when writing documentation, deciding where docs should go, reviewing doc quality, or updating docs after code changes. Covers folder structure, content guidelines, and maintenance workflows.
system-designer
为单个系统设计详细的技术文档。负责架构图、接口设计、数据模型、Trade-offs讨论等。
ai-guidance
Apply when creating or editing AI guidance documents ('**/AGENTS.md', '.cursor/**/*.md')
document-hub-initialize
Bootstrap a new project's documentation hub by creating the four core documentation files (systemArchitecture.md, keyPairResponsibility.md, glossary.md, techStack.md) with initial content based on codebase analysis.
writing-plans
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
api-doc-writer
요구사항을 대화로 받아 도메인별 API 목록 문서(md)를 예시 포맷으로 생성/보강한다. 테스트 코드는 만들지 않고, 문서의 테스트 시나리오 체크리스트만 작성한다.
code-documentation-standards
Comprehensive code documentation standards and guidelines for maintaining up-to-date documentation across Python, HTML, CSS, and JavaScript codebases. Use when creating or modifying code to ensure proper documentation practices and maintainable code.
