Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
agent-delegation
yeisonrestrepo
"Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries only — raw output never enters main context"
ai4pkm-helper
jykim
AI4PKM helper for orchestrator configuration, worker management, and CLI workflow integration.
deep-research
feiskyer
'深度调研的多实例（多 Agent）编排工作流：把一个调研目标拆成可并行子目标，用 Codex CLI（codex exec）在默认 workspace-write 沙箱内运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付“成品报告文件路径 + 关键结论/建议摘要”。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及“深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研”等场景。'
nanobanana-skill
feiskyer
'Generate or edit images using Google Gemini API via nanobanana. Use when the user asks to create, generate, edit images with nanobanana, or mentions image generation/editing tasks.'
claude-skill
feiskyer
'Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc). Provides non-interactive automation mode for hands-off task execution without approval prompts.'
frappe-ui-patterns
lubusIN
UI/UX patterns and guidelines derived from official Frappe apps (CRM, Helpdesk, HRMS). Use when designing interfaces for custom Frappe applications to ensure consistency with the ecosystem.
li-er
JWCodeWrote
A persona-based skill for simulating an "Ideological Inquisitor" - an extremist agent who prioritizes ideology over facts. Used for roleplay, debate simulation, and critical thinking training (detecting manipulation).
skill-creator
kjgarza
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.
wallstreet-tieling
Dear-Ded
?????????? ? 13-role concurrent AI crew ? due diligence/financial analysis/risk assessment/OSINT ? 10-30 data sources ? platform-agnostic v0.5.0 engine
agent-swarm-dev
pmaojo
Sistema de desarrollo para agent swarms con Synapse memory. Usa Anthropic Swarm pattern + Synapse (pmaojo/synapse-engine) para memoria persistente. Flujo: SPEC.md → agentes especializados → código → Vercel.
conversation-mining
FairladyZ625
统一检索和使用 Claude Code / Codex / AntiGravity 的历史对话。支持按日期、关键词、会话 ID、Conversation Reference、Conversation Prompt 找回原文，也支持在用户明确要求时，对指定会话或某天会话做提炼、总结、笔记整理。
ai-patterns
lexler
Reference patterns for augmented coding with AI. Use when discussing AI coding patterns, anti-patterns, obstacles, context management, steering AI, or looking up Lexler's patterns collection.
teams-anthropic-integration
youdotcom-oss
Add Anthropic Claude models (Opus, Sonnet, Haiku) to Microsoft Teams.ai applications using @youdotcom-oss/teams-anthropic. Optionally integrate You.com MCP server for web search and content extraction. - MANDATORY TRIGGERS: teams-anthropic, @youdotcom-oss/teams-anthropic, Microsoft Teams.ai, Teams AI, Anthropic Claude, Teams MCP, Teams bot - Use when: building Microsoft Teams bots with Claude, integrating Anthropic with Teams.ai, adding MCP tools to Teams applications
xiaohongshu-images
iamzifei
Transform markdown/HTML into styled 3:4 ratio images for Xiaohongshu
voice-extractor
BrianRWagner
Extract and document someone's authentic writing voice from samples. Use when someone needs a "voice guide," wants to capture their writing DNA, or needs to train AI to write in their style. Also useful for ghostwriting, brand voice documentation, or onboarding writers.
x-filter
kangarooking
Score and filter topics for X content creation using weighted criteria. Use when user wants to evaluate collected materials, filter topics by score, or mentions "filter topics", "score materials", "x-filter", "选题筛选". Applies 10-point scoring system with customizable weights.
md-to-docx
Xueheng-Li
Convert Markdown files to Word documents (.docx) with proper formatting, Chinese font support (FangSong for all text including headings), black font color, 1.5x line spacing, precise first-line indent (24pt), heading spacing after (1 line), no italic headings, and automatic superscript conversion for citation numbers. Use when converting .md files to .docx, creating Word documents from markdown, or when user mentions Word, DOCX, or document conversion. Requires pandoc.
chat-history-summarizer
Xueheng-Li
Extract and summarize Claude Code chat history into structured documentation. Use when the user asks to export, summarize, or document a conversation session, extract prompts and actions from chat logs, or create a record of what was accomplished in a session.
context-engineering
itsmostafa
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
notion-meeting-intelligence
makenotion
Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an internal pre-read and external agenda saved to Notion. Helps you arrive prepared with comprehensive background and structured meeting docs.
prompt-engineering
itsmostafa
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
mlx
itsmostafa
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
agents
itsmostafa
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
cost-status
DeevsDeevs
"Configure the Claude Code cost/status line plugin that shows session, monthly, total cost, and context usage. Use when a user wants cost tracking, status line setup, or context usage display. Triggers: cost status, status line, show cost, context usage, Claude cost tracking."