llm-ai
2
multi-agent-orchestration
Workflow patterns for multi-agent systems across frameworks. Directs to RAG for implementation.
MattMagg
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
2
claude-mobile-cost-tracking
Use when implementing Claude API cost tracking, monitoring token usage, displaying cost metrics in Settings, or user asks about costs - calculates exact costs using $0.003/1k input and $0.015/1k output pricing with per-session aggregation
krzemienski
data-ai
llm-ai
2
mcp-builder
Guide 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). | 適切に設計されたツールを通じてLLMが外部サービスと対話できるようにする高品質MCP（Model Context Protocol）サーバーを作成するためのガイド。Python（FastMCP）またはNode/TypeScript（MCP SDK）で外部APIやサービスを統合するMCPサーバーを構築する際に使用
lv416e
data-ai
llm-ai
2
moai-project-batch-questions
Standardize AskUserQuestion patterns and provide reusable question templates for batch optimization
AJBcoding
data-ai
llm-ai
2
agent-file-coordination
File-based context sharing for multi-agent workflows. Provides directory organization, agent output templates, progress tracking, and inter-agent context. Use when setting up multi-agent workflows, reading/writing agent context files, or maintaining workflow transparency with file-based coordination.
laurigates
data-ai
llm-ai
2
godel-machine
Schmidhuber''s Gödel Machine: Self-improving systems that prove their
plurigrid
data-ai
llm-ai
2
implicit-coordination
Stigmergic agent coordination through environment modification, not messages. Vehicle semantics where carrier encodes meaning.
plurigrid
data-ai
llm-ai
2
claude-skills
Guide for creating Agent Skills with progressive disclosure, SKILL.md structure, and best practices
vinnie357
data-ai
llm-ai
2
voice-transcription
Record and transcribe voice input when user wants to speak instead of type, describe complex issues verbally, provide audio input, or dictate text. Use this when user says "record my voice", "let me speak", "voice input", "transcribe audio", or when verbal description would be clearer than typing.
aldervall
data-ai
llm-ai
2
embedding-generator
Generate and manage text embeddings for semantic search, clustering, and similarity tasks
eddiebe147
data-ai
llm-ai
2
mlx-apple-silicon
Run LLMs on Apple Silicon with MLX/mlx_lm - unified memory, 4-bit quantization, streaming generation, prompt caching. Optimal for M-series chips.
plurigrid
data-ai
llm-ai
2
stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
bjpl
data-ai
llm-ai
2
embedding-service
文本向量化（Embedding）基础服务。将自然语言转换为高维稠密向量，为语义搜索、聚类分析、推荐系统等下游任务提供核心数据支持。
Lin-A1
data-ai
llm-ai
2
accept-no-substitutes
This skill should be used when agents generate placeholder tokens like "pseudo-", "mock-", "temporary", "TODO", "demo-", or similar incompleteness markers. Detects substitution patterns in agent OUTPUT and triggers mandatory user interview instead of accepting incomplete work. Activates automatically on any output containing forbidden tokens.
plurigrid
data-ai
llm-ai
2
moai-security-encryption
Enterprise Encryption Security with AI-powered cryptographic architecture, Context7 integration, and intelligent encryption orchestration for data protection
AJBcoding
data-ai
llm-ai
2
meeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns,
plurigrid
data-ai
llm-ai
2
skill-ollama-deepseek-ocr-tool
Batch OCR processing with DeepSeek-OCR via Ollama
dnvriend
data-ai
llm-ai
2
power-agent-creator
This skill should be used when users want to create powerful AI agents comparable to Claude Code or sonph-code. It provides battle-tested system prompts, masterfully-crafted tool implementations, and the simple but powerful agent loop pattern. Use this skill when users ask to build coding agents, AI assistants with tools, or any autonomous agent that needs file operations, code execution, search, and task management capabilities. The key insight is that customization requires only ONE HumanMessage after the SystemPrompt.
hongbietcode
data-ai
llm-ai
2
anthropic-streaming-patterns
Use when integrating Claude API with streaming responses, implementing tool execution in streams, tracking API costs, or encountering streaming errors - provides Anthropic SDK 0.30.1+ patterns with mandatory cost monitoring
krzemienski
data-ai
llm-ai
2
ha-translations-and-ids
Home Assistant translation_key and identifier practices—entity/device naming via translations, stable unique IDs, and migration tips.
plebann
data-ai
llm-ai
2
ai-news-crawler
Trigger phrase \"watching news!\"; Create a JSON file named with the current timestamp only in the current directory, crawl 10 AI-related news in descending order of time and output Chinese summaries
feed-mob
data-ai