writing-affordances
Use when refactoring fat Rails models with repetitive prefixes like entropy_*, notification_*, or multi-association coordination. Extracts PORO wrappers that group operations around nouns/concepts.
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。
Use when refactoring fat Rails models with repetitive prefixes like entropy_*, notification_*, or multi-association coordination. Extracts PORO wrappers that group operations around nouns/concepts.
Use after brainstorming to apply vanilla-rails patterns to a feature, producing structured handoff for implementation planning. Invoke with /shape.
Use when naming classes, methods, routes in vanilla Rails codebases - fixes concern verb/noun confusion, bang method misuse, custom action anti-patterns
Use when writing Hotwire (Turbo/Stimulus) code in Rails - enforces dom_id helpers, morph updates, focused Stimulus controllers, and JavaScript private methods
Guides users through creating a new TIA XMPP agent based on mistral-minimal. Use when the user wants to create, build, set up, or scaffold a new agent, bot, or when they ask how to get started with TIA.
Read project session context from .sessions/index.md to understand ongoing work, previous decisions, blockers, and history. Use when the user asks about project context, previous sessions, what was worked on be...
Suggest archiving completed work when PRs are merged or work is completed. Triggers when user asks to merge a PR ("merge it", "merge the PR"), after successful gh pr merge, or mentions completion ("shipped", "d...
Obsidian 플러그인 코드가 공식 가이드라인을 준수하는지 검토하고 개선점을 제안한다. Use when: - 사용자가 Obsidian 플러그인 가이드라인 준수 여부를 확인하고 싶을 때 - 플러그인을 커뮤니티 스토어에 제출하기 전 검토...
Build production AI agents using the Claude Agent SDK (TypeScript/Python). Use this skill when the user asks about: (1) Building AI agents with Claude, (2) Using the @anthropic-ai/claude-agent-sdk or claude-age...
启动 Telegram Webhook 服务器(主服务器或项目服务器)
Access and manage the local GitHub Wiki clone. Use this skill when you need to read wiki content (architecture, design docs, guides), update wiki documentation, check wiki status, or push wiki changes. The wiki...
Enforce Test-Driven Development when writing or modifying code. Use when implementing features, fixing bugs, or when the user asks to write code. Activates automatically for code changes unless user says "quick...
Review code for quality, style, and potential issues. Use when code has been written or modified, when user asks for code review, or when TDD autonomous mode needs quality assessment. Supports configurable stri...
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications. Use when implementing RAG (Retrieval Augmented Generation), creating AI agents with tools, or chain...
mypy - Static type checker for Python with gradual typing, strict mode, Protocol support, and framework integration
Comprehensive TDD patterns and practices for all programming languages, eliminating redundant testing guidance per agent.
Essential Git patterns for effective version control, eliminating redundant Git guidance per agent.
DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers. Use when optimizing prompts systematically, building production LLM systems, imple...
Use git worktrees for parallel development on multiple branches simultaneously
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
Create and manage stacked (dependent) pull requests for complex features
Safe patterns for evolving database schemas in production with decision trees and troubleshooting guidance.
CI security scanning: secrets, deps, SAST, triage, expiring exceptions
Systematic debugging methodology emphasizing root cause analysis over quick fixes. Use when debugging complex issues, investigating production failures, or avoiding symptom-based patches in favor of understandi...
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。