chatbot-designer
Skill0 starsChanged 6 months agoNo licenceView on GitHub
LLM Agent Architect — LLM 에이전트, 챗봇, AI 시스템 설계 종합 스킬. 사용자가 에이전트/챗봇/LLM 시스템을 기획하거나 구축할 때, 심리학 논문·최신 연구·사례 기반으로 최적의 아키텍처, 프롬프트 엔지니어링, 대화 설계, UX를 도메인에 맞춰 적용한다. Use this skill when designing, planning, or building any LLM-powered system — chatbots, AI agents, conversational AI, RAG systems, multi-agent systems, system prompts, or prompt pipelines. Triggers: "에이전트 만들어", "챗봇 기획", "시스템 프롬프트", "프롬프트 설계", "AI 어시스턴트", "LLM 앱 기획", "agent architecture", "chatbot", "system prompt", "prompt engineering", "conversational AI".
In this repository37 other files it gives its agents.
- rules/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-evaluatorSkill
- agentic-workflowsSkill
- ai-developer-practiceSkill
- ai-research-integrationSkill
- api-designSkill
- api-spec-generatorSkill
- architecture-designSkill
- backend-apiSkill
- clean-codeSkill
- code-reviewSkill
- context-compressorSkill
- database-schemaSkill
- debuggingSkill
- dev-blog-writerSkill
- developer-growthSkill
- dev-journalSkill
- documentation-genSkill
- frontend-codemapSkill
- git-workflowSkill
- industry-persona-qaSkill
- learning-journalSkill
- llm-app-plannerSkill
- mcp-integrationSkill
- ml-trainingSkill
- mobile-tablet-redesignSkill
- performance-optimizationSkill
- portfolio-generatorSkill
- product-plannerSkill
- prompt-optimizerSkill
- rag-2.0Skill
- react-componentSkill
- refactoringSkill
- research-agent-techSkill
- security-auditSkill
- tdd-workflowSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
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.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.