Context & AI engineering
25,831 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
Microck/ordinary-claude-skills/skills_categorized/mobile/hook-development Skill
no license324★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
The same file is in 3 other repositories
Microck/ordinary-claude-skills/skills_categorized/monitoring/github-release-management Skill
no license324★ repoComprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/nosql-databases/chroma Skill
no license324★ repoOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
The same file is in 5 other repositories
Microck/ordinary-claude-skills/skills_categorized/nosql-databases/pinecone Skill
no license324★ repoManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
The same file is in 5 other repositories
Microck/ordinary-claude-skills/skills_categorized/package-distribution/codex-skill Skill
no license324★ repoUse when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
Microck/ordinary-claude-skills/skills_categorized/philosophy-ethics/ai-llm-engineering Skill
no license324★ repoOperational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
Microck/ordinary-claude-skills/skills_categorized/philosophy-ethics/ts-agent-sdk Skill
no license324★ repoGenerate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts verbose JSON-RPC curl commands to clean function calls (docs.createDocument() vs curl). Auto-detects MCP tools from server modules, generates TypeScript types and client methods, creates runnable example scripts. Use when: building MCP-enabled applications, need typed programmatic access to MCP tools, want Claude Code to manage apps via scripts, eliminating manual JSON-RPC curl commands, validating MCP inputs/outputs, or creating reusable agent automation.
Microck/ordinary-claude-skills/skills_categorized/productivity-tools/claude-opus-4-5-migration Skill
no license324★ repoMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
The same file is in 5 other repositories
Microck/ordinary-claude-skills/skills_categorized/productivity-tools/hook-development Skill
no license324★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
The same file is in 3 other repositories
Microck/ordinary-claude-skills/skills_categorized/productivity-tools/mcp-integration Skill
no license324★ repoThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/productivity-tools/skill-writer Skill
no license324★ repoGuide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/project-management/github-release-management Skill
no license324★ repoComprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/project-management/sparc-methodology Skill
no license324★ repoSPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
The same file is in 3 other repositories
Workflow orchestration patterns
Microck/ordinary-claude-skills/skills_categorized/project-management/workflow-orchestration-patterns Skill
no license324★ repoDesign durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
The same file is in 3 other repositories
Microck/ordinary-claude-skills/skills_categorized/real-estate-legal/biomni Skill
no license324★ repoAutonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
The same file is in 7 other repositories
Microck/ordinary-claude-skills/skills_categorized/real-estate-legal/mcp-management Skill
no license324★ repoManage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
The same file is in 1 other repository
Microck/ordinary-claude-skills/skills_categorized/sales-marketing/github-release-management Skill
no license324★ repoComprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/sales-marketing/sparc-methodology Skill
no license324★ repoSPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
The same file is in 3 other repositories
Workflow orchestration patterns
Microck/ordinary-claude-skills/skills_categorized/sales-marketing/workflow-orchestration-patterns Skill
no license324★ repoDesign durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
The same file is in 3 other repositories
Microck/ordinary-claude-skills/skills_categorized/scientific-computing/agentdb-vector-search Skill
no license324★ repoImplement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
The same file is in 1 other repository
Microck/ordinary-claude-skills/skills_categorized/scientific-computing/biomni Skill
no license324★ repoAutonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
The same file is in 7 other repositories
Microck/ordinary-claude-skills/skills_categorized/scientific-computing/claude-scientific-skills Skill
no license324★ repoComprehensive collection of 128+ ready-to-use scientific skills for Claude enabling research across biology, chemistry, medicine, genomics, and advanced analysis domains.
Microck/ordinary-claude-skills/skills_categorized/scientific-computing/claude-scientific-skills/scientific-skills/biomni Skill
no license324★ repoAutonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
The same file is in 7 other repositories
Microck/ordinary-claude-skills/skills_categorized/scripting/hook-development Skill
no license324★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
The same file is in 3 other repositories
Workflow orchestration patterns
Microck/ordinary-claude-skills/skills_categorized/scripting/workflow-orchestration-patterns Skill
no license324★ repoDesign durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
The same file is in 3 other repositories
Microck/ordinary-claude-skills/skills_categorized/sql-databases/pinecone Skill
no license324★ repoManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
The same file is in 5 other repositories
Relational database mcp cloudbase
Microck/ordinary-claude-skills/skills_categorized/sql-databases/relational-database-mcp-cloudbase Skill
no license324★ repoThis is the required documentation for agents operating on the CloudBase Relational Database. It lists the only four supported tools for running SQL and managing security rules. Read the full content to understand why you must NOT use standard Application SDKs and how to safely execute INSERT, UPDATE, or DELETE operations without corrupting production data.
Microck/ordinary-claude-skills/skills_categorized/system-admin/claude-opus-4-5-migration Skill
no license324★ repoMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
The same file is in 5 other repositories
Microck/ordinary-claude-skills/skills_categorized/system-admin/hook-development Skill
no license324★ repoThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
The same file is in 3 other repositories
Microck/ordinary-claude-skills/skills_categorized/system-admin/mcp-integration Skill
no license324★ repoThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/system-admin/skill-writer Skill
no license324★ repoGuide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/technical-docs/skill-builder Skill
no license324★ repoCreate new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
The same file is in 2 other repositories
Microck/ordinary-claude-skills/skills_categorized/technical-docs/skill-creator Skill
no license324★ repoGuide 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.
The same file is in 16 other repositories
Microck/ordinary-claude-skills/skills_categorized/technical-docs/skill-writer Skill
no license324★ repoGuide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
The same file is in 4 other repositories
Microck/ordinary-claude-skills/skills_categorized/wellness-health/ai-llm-engineering Skill
no license324★ repoOperational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
Microck/ordinary-claude-skills/skills_categorized/wellness-health/ts-agent-sdk Skill
no license324★ repoGenerate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts verbose JSON-RPC curl commands to clean function calls (docs.createDocument() vs curl). Auto-detects MCP tools from server modules, generates TypeScript types and client methods, creates runnable example scripts. Use when: building MCP-enabled applications, need typed programmatic access to MCP tools, want Claude Code to manage apps via scripts, eliminating manual JSON-RPC curl commands, validating MCP inputs/outputs, or creating reusable agent automation.
w95/awesome-claude-corporate-skills/02-finance-accounting/spglobal-tear-sheet Skill
324★ repoGenerate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M&A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.
The same file is in 1 other repository
w95/awesome-claude-corporate-skills/07-operations/memory-management Skill
324★ repoTwo-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
w95/awesome-claude-corporate-skills/08-it-engineering/mcp-builder Skill
324★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 42 other repositories
syahiidkamil/Software-Engineer-AI-Agent-Atlas/.claude/skills/anthropic-product-knowledge Skill
no license319★ repoStop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.
syahiidkamil/Software-Engineer-AI-Agent-Atlas/.claude/skills/mcp-builder Skill
no license319★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 42 other repositories
syahiidkamil/Software-Engineer-AI-Agent-Atlas/.claude/skills/skill-creator Skill
no license319★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
modu-ai/cowork-plugins/moai-content/skills/humanize-korean Skill
316★ repoAI(ChatGPT·Claude·Gemini 등)가 쓴 한국어 텍스트의 "AI 티"를 정밀하게 제거해 사람이 쓴 글처럼 윤문하는 한국어 특화 스킬입니다. 번역투(~를 통해/~에 있어서/이중 피동), 영어 인용 과다, 기계적 병렬(첫째·둘째·셋째), AI 특유 관용구(결론적으로/시사하는 바가 크다/혁신적인), 피동태 남용, 문두 접속사 남발, 형식명사 과다, 이모지·불릿·볼드 남용 등 10대 카테고리 × 40+ 패턴을 S1/S2/S3 심각도로 탐지·윤문하고, 의미는 한 글자도 건드리지 않습니다(고유명사·수치·날짜·인용 100% 보존, 변경률 30% 초과 시 경고·50% 초과 시 강제 중단). 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "AI 티 없애줘", "GPT 문체 제거해줘", "ChatGPT 티 제거" - "사람이 쓴 것처럼 윤문해줘", "AI 같은 글 자연스럽게" - "한글 AI 윤문", "AI 글 사람처럼", "AI 글 티 안 나게" - "번역투 제거", "영어 인용 많은 글 윤문" - "휴머나이저", "humanize Korean", "AI detector bypass 한글" - 후속 작업: "특정 카테고리만 다시", "이 문단만", "2차 윤문", "강도 조정", "장르 바꿔서" 적용 대상 — 모든 한국어 텍스트 산출물(블로그·뉴스레터·카피·사업계획서·제안서·보고서·이메일·랜딩 카피·칼럼·리포트). ai-slop-reviewer가 1차 일반 후처리를 마친 뒤 2차 한국어 정밀 윤문으로 호출하는 것을 권장합니다. 적용 제외 — 단순 맞춤법·오탈자 교정(직접 처리), 번역(번역 스킬), 내용 추가·삭제 동반 재작성(별도 집필 스킬), 코드·JSON·CSV·차트·표. 한국 번역학계 8유형 번역투 계보를 통합한 10대 카테고리 분류 + 신규 패턴 A-16/A-18/A-19/E-7 + post-editese 14메트릭 기반 한국어 정밀 윤문 스킬입니다.
modu-ai/cowork-plugins/moai-core/skills/mcp-connector-setup Skill
316★ repo[책임 경계] Drive·Notion·Higgsfield 3커넥터 인증·환경변수·트러블슈팅 가이드 전담. 페어 moai-commerce:commerce-morning-brief(MCP 매장 데이터 호출)와 명확히 구분 — 본 스킬은 커넥터 설치·인증 단계, 페어는 인증 이후 실제 MCP 호출 결과물. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: "MCP 커넥터 연결", "Drive 인증 방법", "Notion Integration Token 어디서", "Higgsfield 키 발급", "Windows MAX_PATH 오류", "한글 파일명 30자 오류", "computer:// 링크 안 열려요", "커넥터 3개 연결 방법", "MCP 3커넥터 인증", "커넥터 오류 해결".
modu-ai/cowork-plugins/moai-core/skills/skill-builder Skill
316★ repo6-Phase 스킬 생성 워크플로우. revfactory/harness 방법론을 기반으로 체계적으로 새 스킬을 생성합니다. 요구사항 분석부터 최종 검증까지 전체 생명주기를 관리합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "새 스킬 만들어줘", "스킬 생성", "skill-builder" - "이 기능 스킬로 만들고 싶어", "스킬 제작" - "Vibe 스킬 추가", "새 플러그인 스킬" - skill-template으로 시작한 스킬의 체계적 생성이 필요할 때 - /harness 커맨드의 new 단계로 진입할 때
modu-ai/cowork-plugins/moai-core/skills/skill-template Skill
316★ repoSKILL.md 표준 템플릿. 새 스킬 생성 시 이 템플릿을 기반으로 작성합니다. 스킬 작성 가이드라인과 필수 섹션 구조를 정의합니다. 다음과 같은 요청 시 이 스킬을 참조하세요: - "새 스킬 만들고 싶어", "스킬 템플릿", "SKILL.md 템플릿" - "스킬 작성 방법", "스킬 구조", "스킬 포맷"
modu-ai/cowork-plugins/moai-design/skills/claude-design-brief Skill
316★ repoClaude Design용 6요소 브리프(Project·Audience·Pages·Tone·Reference·Constraints)를 자동으로 작성해 주는 스킬. 자연어 한 줄 요청에서 시작해 누락된 요소를 차례로 채우고, AI 슬롭 회피 블록을 포함한 복붙용 프롬프트를 출력합니다. 완성된 프롬프트는 claude.ai/design 채팅에 그대로 붙여 넣어 사용합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "Claude Design 브리프 만들어 줘" - "클로드 디자인 프롬프트 작성" - "디자인 브리프 6요소" - "claude.ai/design에 넣을 프롬프트" - "디자인 요청 정리"
modu-ai/cowork-plugins/moai-design/skills/claude-design-handoff-reader Skill
316★ repoClaude Code 핸드오프 번들(README + design-tokens.json + components.json + layout-hierarchy.json + chat-history.md)을 분석해 요약 보고서와 Claude Code에 넘길 짧은 지시 1줄을 자동 생성합니다. 핸드오프 번들 구조를 한눈에 파악하고, 컴포넌트 트리·토큰·디자인 결정 맥락을 정리합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "Claude Design 핸드오프 번들 분석" - "handoff 번들 요약" - "핸드오프 번들 읽어 줘" - "디자인 토큰 추출" - "Claude Code 핸드오프 준비"
modu-ai/cowork-plugins/moai-design/skills/claude-design-prompt-builder Skill
316★ repoClaude Design용 시니어 UX 프롬프트를 10가지 전문 패턴(정보 구조·디자인 시스템·카피·온보딩·접근성·대시보드·폼·테스트·휴리스틱·리서치) 중 적합한 것을 골라 완성해 줍니다. 각 패턴은 구체적 역할(예: IDEO 시니어 UX 아키텍트 12년차)을 부여해 결과 분산을 30-40% 감소시킵니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "Claude Design 시니어 프롬프트" - "UX 패턴 프롬프트" - "정보 구조 프롬프트 만들어 줘" - "접근성 디자인 프롬프트" - "디자인 시스템 프롬프트" - "프롬프트 빌더"
modu-ai/cowork-plugins/moai-design/skills/claude-design-slop-check Skill
316★ repoClaude Design에서 생성된 결과 카피(헤드라인·서브헤드·CTA·feature·푸터)를 AI 슬롭 패턴으로 검수합니다. 영문(Reimagine your·Unleash your potential 등)과 한국어(혁신적인·차세대·재정의하는 등) 진부 표현을 검출하고 수정안을 제안합니다. 후속으로 moai-content:humanize-korean 체이닝을 권장합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "Claude Design 카피 검수" - "AI 슬롭 점검" - "AI 티 나는 카피 확인" - "디자인 카피 후처리" - "humanize 직전 검수"
modu-ai/cowork-plugins/moai-design/skills/claude-design-system-prep Skill
316★ repo브랜드 자산(로고·색·타이포·기존 사이트·PPTX 등)을 분석해 Claude Design 업로드용 DESIGN.md를 자동으로 합성합니다. Claude Design 디자인 시스템 셋업의 가장 흔한 실패(자산이 흩어져 있고 정리가 안 된 채 업로드)를 해결합니다. 결과는 그대로 claude.ai/design 온보딩에 업로드하면 됩니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "Claude Design용 디자인 시스템 자료 정리" - "브랜드 자산을 DESIGN.md로 합성" - "디자인 시스템 자산 업로드 준비" - "claude.ai/design 디자인 시스템 셋업 준비" - "DESIGN.md 만들어 줘"
modu-ai/cowork-plugins/moai-media/skills/gemini-3-image-prompt Skill
316★ repoGoogle Gemini 3 Pro Image (a.k.a. Nano Banana Pro) 전용 이미지 프롬프트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정으로 컨텍스트를 수집해 Google AI Developers 공식 가이드의 5-component 구조([Subject+Adj] doing [Action] in [Location]. [Composition]. [Lighting]. [Style]. [Constraint/Text])로 변환합니다. Google AI Studio · Vertex AI · Gemini 앱에 그대로 복붙 가능. 보너스로 GPT-image-2(6-Block) · Midjourney v8.1(키워드+파라미터) 프롬프트도 동시 출력해 모델 간 비교·이식이 가능합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "Gemini 이미지 프롬프트 만들어줘", "나노바나나 프롬프트" - "Nano Banana Pro 프롬프트", "Gemini 3 Pro Image 프롬프트" - "Google AI Studio 이미지 프롬프트", "Vertex AI 이미지 프롬프트" - "/gemini-3-image-prompt" (직접 호출) 이미지 자동 생성은 페어 스킬 higgsfield-image(Higgsfield MCP, Nano Banana Pro 포함)를 사용하세요. 본 스킬은 프롬프트 텍스트 산출 전용입니다.
modu-ai/cowork-plugins/moai-media/skills/gpt-image-2-prompt Skill
316★ repoOpenAI GPT-image-2 모델 전용 이미지 프롬프트 텍스트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정 라운드로 컨텍스트를 수집하고, OpenAI Cookbook 공식 6-Block 구조(Subject·Action·Scene·Composition·Lighting·Style&Text)에 매핑해 ChatGPT·OpenAI API에 복붙 가능한 프롬프트를 출력합니다. 보너스로 같은 입력에 대한 Gemini 3 Pro Image · Midjourney v8.1 프롬프트도 함께 생성해 모델 간 비교·이식이 즉시 가능합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "GPT 이미지 프롬프트 만들어줘", "ChatGPT 이미지 프롬프트" - "GPT-image-2 프롬프트", "gpt image 2 프롬프트 작성" - "OpenAI 이미지 프롬프트", "GPT용 이미지 프롬프트 빌더" - "/gpt-image-2-prompt" (직접 호출) 이미지 자동 생성은 페어 스킬 higgsfield-image(Higgsfield MCP)를 사용하세요. 본 스킬은 프롬프트 텍스트 산출 전용입니다.
modu-ai/cowork-plugins/moai-media/skills/midjourney-v8-prompt Skill
316★ repoMidjourney v8.1 (2026.03 Alpha) 전용 이미지 프롬프트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정으로 컨텍스트를 수집해 Midjourney 공식 Parameter List 기반 키워드+`--파라미터` 형식으로 변환합니다. Discord `/imagine` 또는 alpha.midjourney.com에 그대로 복붙 가능. `--sref`/`--oref`/`--cw`/`--p`/`--hd`/`--q 4`/`--style raw`/`--no`/`--c`/`--s` 모두 지원. 보너스로 GPT-image-2(6-Block) · Gemini 3 Pro Image(5-component) 프롬프트도 동시 출력합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "미드저니 프롬프트 만들어줘", "MJ 프롬프트" - "Midjourney 프롬프트", "/imagine 프롬프트 작성" - "Midjourney v8 프롬프트", "미드저니 8.1 프롬프트" - "--sref 프롬프트", "--oref 프롬프트", "스타일 코드 프롬프트" - "/midjourney-v8-prompt" (직접 호출) Midjourney는 공식 API 자동화가 제한적이므로 본 스킬은 프롬프트 텍스트만 산출하고, 실제 생성은 사용자가 Discord 또는 web alpha에서 직접 실행합니다.
modu-ai/cowork-plugins/moai-office/skills/notebooklm-slide-prompt Skill
316★ repo강연·강의·세미나 본문 마크다운을 입력받아 (1) NotebookLM Studio에 그대로 붙여 넣을 슬라이드 데크 생성 프롬프트와 (2) 슬라이드별 나노바나나(Gemini 3 Pro Image, a.k.a. Nano Banana Pro) 5-Component 이미지 프롬프트를 동시 산출하는 prompt-builder 스킬. NotebookLM Studio의 공식 4축(Format/Length/Output language/Prompt)을 정확히 매핑하고, 슬라이드별 시각 자료는 Google DeepMind 공식 가이드의 5-Component 구조(Style·Subject·Setting·Action·Composition)에 따라 작성한다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "NotebookLM 슬라이드 프롬프트", "NotebookLM 프롬프트", "NotebookLM 데크" - "강의 슬라이드 프롬프트", "강연 슬라이드 자료", "세션 슬라이드 프롬프트" - "Detailed Deck", "Presenter Slides", "프레젠터 슬라이드", "디테일드 데크" - "슬라이드 이미지 프롬프트", "나노바나나 슬라이드", "Nano Banana 슬라이드" - "본문 MD를 NotebookLM 프롬프트로 변환", "강연용 슬라이드 자료 만들어줘" - "PPT 발표 자료 프롬프트", "발표 슬라이드 통째로 생성"
InterfaceX-co-jp/genshijin/skills/genshijin-crew Skill
312★ repo原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore` の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。 Trigger: 「subagent 委譲」「genshijin-crew 使用」「investigator/builder/reviewer 起動」「コンテキスト節約」「圧縮 agent 出力」。
The same file is in 5 other repositories
HeyClaude — Claude & AI workflow directory
JSONbored/awesome-claude/io.github.JSONbored/heyclaude MCP server
310★ repoSearch the HeyClaude directory of Claude Code agents, MCP servers, skills, and tools.
sveltejs/ai-tools/dev.svelte/mcp MCP server
306★ repoThe official Svelte MCP server providing docs and autofixing tools for Svelte development
Agentsop agent topology selection
agentsope/SkillAlchemy/skills/agentsop-agent-topology-selection Skill
303★ repoCross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is single-agent + tools enough? do agents need to know about each other? does the output need one voice? — maps the answer to single-agent / supervisor / swarm / sequential / hierarchical. Activates when a coder agent is tempted to "split the work into roles" or reaches for a multi-agent framework. Encodes the *selection rubric* that the per-framework skills assume but never surface. Search keywords: when to use multi-agent, single vs multi agent, do I need multiple agents, supervisor vs swarm, multi-agent vs single agent, agent team design.
agentsope/SkillAlchemy/skills/agentsop-bounded-loop Skill
303★ repoUniversal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recursion_limit + state counter + interrupt), CrewAI (max_iter + max_rpm + human_input), Claude / OpenAI SDKs (max_iterations + tool_use_budget), DSPy (declared evaluation budget), Aider (REPL + explicit retry cap), and AutoGen (max_consecutive_auto_reply). Search keywords: infinite loop, recursion limit, recursion_limit, GraphRecursionError, max iterations, max_iter, agent stuck, agent won't stop, runaway agent, ReAct loop not terminating, agent repeating itself.