Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
building-with-llms
RefoundAI
Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI output quality.
nav-diagnose
alekspetrov
Detect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this".
nav-install-multi-claude
alekspetrov
Install Navigator multi-Claude workflow orchestration scripts. Auto-invokes when user says "install multi-Claude workflows", "set up multi-Claude", or "enable parallel execution".
frontend-component
alekspetrov
Create React/Vue component with TypeScript, tests, and styles. Auto-invoke when user says "create component", "add component", "new component", or "build component".
nav-init
alekspetrov
Initialize Navigator documentation structure in a project. Auto-invokes when user says "Initialize Navigator", "Set up Navigator", "Create Navigator structure", or "Bootstrap Navigator".
nav-upgrade
alekspetrov
Automates Navigator plugin updates. Detects current version, updates plugin, verifies installation, updates project CLAUDE.md, and validates new features. Auto-invoke when user mentions upgrading Navigator or getting new features.
crushable-wingman
yxp934
Dating wingman and texting coach. Use when the user asks for reply suggestions, message rewrites, DMs/openers, chat analysis, relationship health analysis, or date ideas, and when they provide chat screenshots to extract and structure before coaching. Prioritize context-first coaching, a concise case file, and 2-4 clarifying questions when information is missing. Reply in the user's language.
learning-sdk-integration
letta-ai
Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK
better
OpenAgentsInc
Push the current task, or a prompt the user gives, to a deeper version of itself. Use only when the user explicitly types /better or $better.
call-mcp-tool
openakita
Call MCP server tool for extended capabilities. Check 'MCP Servers' section in system prompt for available servers and tools. When you need to use external service or access specialized functionality.
doc-coauthoring
openakita
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
picocom
BrownFineSecurity
Use picocom to interact with IoT device UART consoles for pentesting operations including device enumeration, vulnerability discovery, bootloader manipulation, and gaining root shells. Use when the user needs to interact with embedded devices, IoT hardware, or serial consoles.
memory-management
aaron-he-zhu
'Use when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.'
hwpx
Canine89
"HWPX 문서(.hwpx 파일)를 생성, 읽기, 편집, 템플릿 치환하는 스킬. '한글 문서', 'hwpx', 'HWPX', '한글파일', '.hwpx 파일 만들어줘', 'HWP 문서 생성', '보고서', '공문', '기안문', '한글로 작성' 등의 키워드가 나오면 반드시 이 스킬을 사용할 것. 한글과컴퓨터(한컴)의 HWPX 포맷(KS X 6101/OWPML 기반, ZIP+XML 구조)을 python-hwpx 라이브러리로 다룬다. 보고서 양식이 필요하면 assets/ 폴더의 레퍼런스 템플릿을 활용한다. 일반 Word(.docx) 문서에는 docx 스킬을 사용할 것."
dify-dsl-generator
wwwzhouhui
专业的 Dify 工作流 DSL/YML 文件生成器，根据用户业务需求自动生成完整的 Dify 工作流配置文件，支持各种节点类型和复杂工作流逻辑
geo-fundamentals
vudovn
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
app-builder
vudovn
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
jimeng_mcp_skill
wwwzhouhui
使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力：文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。
code-review-checklist
vudovn
Code review guidelines covering code quality, security, and best practices.
jimeng_mcp_skill
wwwzhouhui
使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力：文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。
creating-agent-skills
bnadlerjr
Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
sentry-setup-ai-monitoring
getsentry
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.
local-llm-tool
xuiltul
ローカルLLM実行ツール。OllamaやvLLMでGPU上のモデルにテキスト生成・チャットを依頼する。 Use when: オンプレ推論、Ollamaエンドポイント呼び出し、ローカルモデルでの要約・生成が必要なとき。
video-generator
cdeistopened
Generate AI videos using Google VEO 3.1 or OpenAI Sora. Two providers for different strengths - VEO for native audio, Sora for visual quality and longer clips.