发现 文档写作 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Automatically activated when user mentions multi-project coordination, cross-project dependencies, portfolio management, roadmap planning, resource allocation across projects, or asks to coordinate/manage multi...
Deep, gap-filling interview that enhances an existing doc/spec (preferred) or explores a topic. Use when deepening PRDs, ADRs, tickets, notes, or draft specs; if given a doc path, update it in-place with Delta/...
Interactive release readiness checklist with semantic versioning guidance. Use when preparing a software release, cutting a version, deploying to production, or when user asks about release preparation. Trigger...
Self-improving skill system for Makepad development. Features self-evolution (accumulate knowledge), self-correction (fix errors automatically), self-validation (verify accuracy), usage feedback (track pattern...
Guide for creating effective skills that extend Claude's capabilities. This skill provides the framework for creating new skills with specialized knowledge, workflows, or tool integrations. Use when building a...
Generate and winnow project improvement ideas to a top 5. Use when asked for roadmap/improvement ideas.
Core interview engine enforcing strict discovery/decision gating with externalized state, decisions, assumptions, and an approval gate. Use when building interview wrapper skills.
Use dtctl CLI tool for querying observability data in Dynatrace via DQL (logs, metrics, traces, ...) and to manage Dynatrace platform resources (workflows, dashboards, notebooks, SLOs, settings, buckets, lookup...
Build or adapt Oak Curriculum API driven learning experiences, especially for child-facing, interactive ChatGPT Apps SDK workflows. Use when working with Oak API endpoints, curriculum data (subjects, units, les...
Turn a user prompt into a **single, actionable plan** delivered in the final assistant message.. Use when When a user explicitly asks for a plan or roadmap..
Library of 18+ ready-to-use prompt templates and executable agents
Structure a multidisciplinary design review for LLM-powered products, producing actionable risks, fixes, and evidence gaps across UX, architecture, AI safety, and operations.. Use when Use this skill when the t...
Analyze files/directories for token optimization. Reports waste patterns and improvements. Use when: context limits, high costs, large codebases. Enforcement via .cursorrules.
Deep architectural audit focused on finding dead code, duplicated functionality, architectural anti-patterns, type confusion, and code smells. Use when user asks for architectural analysis, find dead code, iden...
Use this skill when working with ast-grep, an AST-based code search, lint, and rewrite tool. Activate when the user asks to search code patterns, refactor code structurally, create linting rules, or perform AST...
Automatically activated when user works with Jest tests, mentions Jest configuration, asks about Jest matchers/mocks, or has files matching *.test.js, *.test.ts, jest.config.*. Provides Jest-specific expertise...
Detect common security vulnerabilities in code. Covers OWASP patterns, SQL injection, bare excepts, shell injection. Framework-agnostic.
Technical spike and research investigation specialist. Use when exploring options for a technical decision, conducting timeboxed investigations, or evaluating technology choices.
Automatically activated when user asks about test quality, code coverage, test reliability, test maintainability, or wants to analyze their test suite. Provides framework-agnostic test quality analysis and impr...
Comprehensive testing specialization covering test strategy, automation, TDD methodology, test writing, and web app testing. Use when setting up test infrastructure, writing tests, implementing TDD workflows, a...
Comprehensive performance specialist covering analysis, optimization, load testing, and framework-specific performance. Use when identifying bottlenecks, optimizing code, conducting load tests, analyzing Core W...
Automatically find relevant context from knowledge graph and code relationships while coding. Detects when context would be helpful (new files, unfamiliar code, architectural decisions) and surfaces related ent...
Expert at analyzing documentation quality, coverage, and completeness. Auto-invokes when evaluating documentation health, checking documentation coverage, auditing existing docs, assessing documentation quality...
Patterns and techniques for analyzing brownfield codebases. Use when onboarding to unfamiliar code, preparing for refactoring, conducting architecture reviews, or identifying technical debt.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。