One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
tygwanReads credentialsSkilltygwan/skills/n8n-code-javascript/SKILL.md
Expert guidance for writing JavaScript in n8n Code nodes. Covers execution modes, data access patterns, return formats, and common pitfalls. Essential for n8n workflow automation with custom code.
tygwanSkilltygwan/skills/n8n-code-python/SKILL.md
Expert guidance for writing Python in n8n Code nodes. Covers when to use Python vs JavaScript, standard library usage, data patterns, and common pitfalls. JavaScript is recommended for 95% of cases.
tygwanReads credentialsSkilltygwan/skills/n8n-expression-syntax/SKILL.md
Comprehensive guide for writing correct n8n expressions in workflows. Covers expression format, core variables, webhook data structure, common patterns, and validation rules.
tygwanSkilltygwan/skills/n8n-mcp-tools-expert/SKILL.md
Master guide for using n8n-mcp MCP server tools to build workflows. Covers 40+ tools, node type formats, tool selection priority, validation workflows, and iterative building strategies.
tygwanSkilltygwan/skills/n8n-node-configuration/SKILL.md
Expert guide for operation-aware n8n node configuration. Covers progressive disclosure, property dependencies, configuration workflows, and common node patterns with 91.7% success rate methodology.
Often used withn8n-agentsn8n-error-handlingn8n-subworkflows
tygwanSkilltygwan/skills/n8n-validation-expert/SKILL.md
Expert guide for interpreting and fixing n8n validation errors. Covers error severity levels, validation profiles, common error types, auto-sanitization, false positives, and recovery strategies.
tygwanSkilltygwan/skills/n8n-workflow-patterns/SKILL.md
Proven architectural patterns for building n8n workflows. Covers 5 essential patterns - Webhook Processing, HTTP API Integration, Database Operations, AI Agent Workflows, and Scheduled Tasks.
tygwanSkilltygwan/skills/nextjs15-init/SKILL.md
Use when user wants to create a new Next.js 15 project (Todo/Blog/Dashboard/E-commerce/Custom domain) with App Router, ShadCN, Zustand, Tanstack Query, and modern Next.js stack
tygwanSkilltygwan/skills/prompt-enhancer/SKILL.md
Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development requests that would benefit from project-specific context to generate more accurate, contextually-aware prompts.
tygwanPipes a download into a shellSkilltygwan/skills/railway/SKILL.md
Railway MCP 설치 및 클라우드 배포 자동화 스킬 - Claude Code 전용
tygwanSkilltygwan/skills/resilience-patterns/SKILL.md
Implement battle-tested resilience patterns (Circuit Breaker, Retry Logic, Dead Letter Queue, Rate Limiting) for systems with external dependencies. Use when building fault-tolerant microservices, API integrations, message queues, or any system requiring graceful degradation under failure conditions. Essential for production systems with APIs, databases, third-party services, or distributed architectures.
tygwanReads credentialsSkilltygwan/skills/senior-architect/SKILL.md
Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.
tygwanReads credentialsSkilltygwan/skills/senior-backend/SKILL.md
Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.
Often used withsenior-frontendcode-reviewerui-ux-pro-max
tygwanReads credentialsSkilltygwan/skills/senior-secops/SKILL.md
Comprehensive SecOps skill for application security, vulnerability management, compliance, and secure development practices. Includes security scanning, vulnerability assessment, compliance checking, and security automation. Use when implementing security controls, conducting security audits, responding to vulnerabilities, or ensuring compliance requirements.
tygwanSkilltygwan/skills/skill-creator/SKILL.md
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
188 projects use a version of this
Often used withtaskflow-inbox-triagemermaid-diagram-generatorecosystem-reference
tygwanSkilltygwan/skills/skill-manager/SKILL.md
Efficient management and deployment of Claude Code skills and marketplace. Automates marketplace initialization, skill updates, Git workflows, version management, and release notes with proper Git conventions.
Often used withSkill Evolution Managerskill-creatorgithub-to-skills
tygwanSkilltygwan/skills/slash-command-creator/SKILL.md
Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, update an existing slash command, or asks about slash command syntax, frontmatter options, or best practices.
tygwanSkilltygwan/skills/subagent-creator/SKILL.md
Create specialized Claude Code sub-agents with custom system prompts and tool configurations. Use when users ask to create a new sub-agent, custom agent, specialized assistant, or want to configure task-specific AI workflows for Claude Code.
tygwanSkilltygwan/skills/systematic-debugging/SKILL.md
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
Often used withchinese-code-reviewdiagnosing-superpowerschinese-commit-conventions
tygwanSkilltygwan/skills/tdd-mvp-planner/SKILL.md
Transform architecture documents into comprehensive development documentation (PLAN.md, TODO.md, CLAUDE.md, DEVELOPMENT.md) following TDD methodology. All documents are saved in the project's `dev-docs/` folder. Provides a systematic 10-phase workflow with Codex validation, applicable to any project type.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
