explore-concept
Broad ideation and problem definition using Socratic questioning. Use for early-stage exploration when the problem isn't well-defined.
发现 测试与安全 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。
Broad ideation and problem definition using Socratic questioning. Use for early-stage exploration when the problem isn't well-defined.
Review layout consistency (spacing, alignment, grid usage). Use to ensure visual consistency across components.
Performance analysis and optimization opportunities. Use when application feels slow or before optimization work.
Tree-of-thoughts reasoning for elusive, intermittent bugs. Use when standard debugging fails or the bug is hard to reproduce.
Identify code smells and refactoring opportunities without fixing. Use for tech debt assessment.
Create technical architecture specification with data models, component hierarchy, and risk analysis. Use after PRD approval for large features.
Evaluate technical options (libraries, architecture patterns, performance tradeoffs). Use when exploring "how should we build this?" or "what library/approach should we use?"
Review typography consistency and usability. Use to ensure readable, consistent text styling.
Génère des **cours complets, structurés et utilisables pour un élève de lycée**. Le contenu doit suivre une progression pédagogique claire, avec objectifs, notions, exemples, exercices, activités et mini-évalua...
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx file...
Git workflow assistant for common tasks. Use this skill when the user asks to: - Create a commit with proper conventional commit formatting (feat, fix, docs, style, refactor, test, chore) - Create a new feature...
Ralph Loop autonomous iteration plugin - enables self-referential development loops with multi-ralph support. Forked from ralph-loop@claude-plugins-official for persistence.
Manages the dynamic skill learning system. Use when you want to list skills, scan transcripts for patterns, learn preferences, approve/reject candidates, rollback versions, view skill history, or check usage st...
Show agent-mobile system health when user asks "health", "system health", "check health", or runs /health
Use the Anthropic Claude SDK for programmatic API access. Enables spawning sub-agents, parallel processing, batch operations, and custom Claude interactions via Python. Use when tasks need multiple Claude insta...
Allows Claude to directly start Ralph-Wiggum autonomous loops without user commands. Use when user asks to "start a ralph loop", "run ralph", wants autonomous iteration, says "keep working until done", or when...
Use when implementing end-to-end tests, using Playwright or Cypress, testing user journeys, debugging flaky tests, or asking about "E2E testing", "Playwright", "Cypress", "browser testing", "visual regression",...
Use when "organizing files", "cleaning up folders", "finding duplicates", "structuring directories", or asking about "Downloads cleanup", "folder structure", "file management"
Use when "nanobanana", "generate image", "create image", "edit image", "AI drawing", "Gemini image", "image generation"
Use when "data pipelines", "ETL", "data warehousing", "data lakes", or asking about "Airflow", "Spark", "dbt", "Snowflake", "BigQuery", "data modeling"
Use when testing "web application", "Playwright", "browser automation", "UI testing", "frontend testing", "E2E testing", "end-to-end tests", or asking about "test local webapp", "browser screenshots", "DOM insp...
Use when "vector database", "embedding storage", "similarity search", "semantic search", "Chroma", "ChromaDB", "FAISS", "Qdrant", "RAG retrieval", "k-NN search", "vector index", "HNSW", "IVF"
Use when designing microservices architectures, decomposing monoliths, implementing service boundaries, inter-service communication, or asking about "microservices", "service decomposition", "API gateway", "cir...
Use when you have a written implementation plan to execute in a separate session with review checkpoints
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。