Prompts
Prompt engineering and templates
agent-development
by ma1orek
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation, troubleshooting agent memory issues, or building agent pipelines.
long-document-llm-pipeline
by shimo4228
"Use when processing documents over 50K characters through LLM APIs with section splitting and batch cost reduction."
marp-slide
by cachemoney
Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.
Agentforce Planner Bundle Builder
by dylandersen
Comprehensive guide for building, configuring, and deploying Legacy Agentforce GenAiPlannerBundles. Use when creating Agentforce agents, working with GenAiPlannerBundles, GenAiPlugins, or GenAiFunctions, understanding Agentforce architecture, configuring topics/actions/schemas, deploying planner bundles, creating Service or Employee agents, or troubleshooting bundle deployment issues.
skill-creator
by Jackiexiao
"Guide for creating effective skills. Use when the user wants to create a new skill or update an existing one to extend capabilities via expertise, workflows, or tool integration."
building-cloudflare-mcp
by WebSmartTeam
Create MCP servers on Cloudflare Workers using the MCP Connector pattern. Use when user mentions "cloudflare mcp", "worker mcp", "mcp connector", or wants to deploy MCP tools on Cloudflare.
ui-designer
by dereknex
Use when the user provides UI screenshots/mockups and wants a design system extracted or an implementation prompt that matches those references.
vault-structure-sync
by teslasoft-de
PARA-specific IDEA synchronization for Obsidian vault projects. Scans PARA folders (00-90), registers as modules, creates category-based scopes.
data-ai-guide
by pluginagentmarketplace
Comprehensive data science, machine learning, and AI guide covering Python, deep learning, NLP, LLMs, prompt engineering, and MLOps. Use when building AI models, data pipelines, or machine learning systems.
claude-code-self-generation-over-api
by shimo4228
"Use when Claude Code needs to generate or transform text data in bulk. Try self-generation before API calls on Max plan."
chief-of-ai
by mmcmedia
Chief of AI who researches new AI/tech developments, recommends tools, automation opportunities, and strategies to stay on the cutting edge. Monitors AI news, evaluates new tools, and identifies leverage points.
agent-builder
by 101mare
Knowledge for designing Claude Code agents with research-backed identity design (Soul Formula). Teaches experiential identities, anti-patterns, multi-file structure, and consolidation patterns. Use when building new agents or improving existing ones. Recognizes: "create an agent", "new agent for X", "agent that does Y", "how do I make an agent?", "agent configuration", "add a subagent", "agent frontmatter", "agent tools", "agent soul", "agent identity", "agent design"
claude-agent-ruby
by ya-luotao
Implement or modify Ruby code that uses the claude-agent-sdk gem, including query() one-shot calls, Client-based interactive sessions, streaming input, option configuration, tools/permissions, hooks, SDK MCP servers, structured output, budgets, sandboxing, session resumption, Rails integration, and error handling.
complete-prompt
by choru-k
Generate context prompts for AI-to-AI handoffs. Use when sharing conversation context, continuing work in a fresh session, or handing off to another LLM. Supports full, brief, debug, architect, diff, general, research, career, and learning modes. Use for "cp", "complete prompt", "context prompt", "handoff prompt", "share context", or "hand off to another AI".
text-processor
by evansking
iMessage processing pipeline — auto-classifies texts, saves memories, handles reminders/calendar events, monitors chat responses, detects tapback reactions, and handles group chat join requests.
skills-ref
by khw1031
스킬 디렉토리를 스캔하여 CLAUDE.md에 Available Skills 섹션을 XML 구조로 생성합니다. 스킬 등록, 스킬 목록 생성, CLAUDE.md 스킬 섹션, skills ref, 스킬 인덱스, available skills 작성 요청 시 활성화.
zenn-context-driven-writing
by shimo4228
"Use when preparing context and drafts for experience-based Zenn articles. Parallel research + context file pattern."
slurm-info-summary
by kdkyum
Gather and cache SLURM cluster information (partitions, GPUs, memory, QOS limits). Generates a readable summary doc on first run; returns the cached doc on subsequent runs.
project-memory-autopilot
by L61
Build and maintain a project-scoped external memory system for AI collaboration. Use when users ask to make the assistant "smarter", persistent across sessions, less forgetful, or to codify team preferences, workflow rules, and decision history in repository files.
planning-setup
by rohanpatriot
Sets up planning-with-files infrastructure for complex projects. Creates task_plan.md, findings.md, progress.md, updates CLAUDE.md with methodology guidance, and adds .claude/rules enforcement. Use when starting a project that will require >5 tool calls or complex multi-step work.
regex-vs-llm-structured-text
by shimo4228
"Use when parsing structured text (quizzes, forms, documents). Start with regex, add LLM only for low-confidence edge cases."
code-review-team
by khw1031
프로젝트 컨텍스트를 파악한 뒤 전문가 관점으로 코드 리뷰하고, 사용자 승인 후 Agent Team SPAWN으로 병렬 개선 작업을 수행합니다. 트리거: 코드리뷰, 코드 리뷰, code review, 리뷰해줘, 리팩토링, 코드검토, PR 리뷰, 변경사항 검토.
spanora-setup
by spanora
Setup Spanora AI observability in any project (JavaScript/TypeScript or Python). Use when user asks to "add spanora", "setup spanora", "integrate spanora", "add AI observability", "monitor LLM calls with spanora", "track AI costs", or mentions spanora in the context of adding observability to their project. Detects the language and installed AI SDKs (Vercel AI, Anthropic, OpenAI, LangChain) and configures the optimal integration pattern.
create-plan
by dereknex
Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.