faion-net
Universal orchestrator for software projects: SDD workflow, research, product planning, development, marketing, project/business analysis, UX, HR/recruiting. 60+ agents, 18 skills, 605 methodologies.
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Universal orchestrator for software projects: SDD workflow, research, product planning, development, marketing, project/business analysis, UX, HR/recruiting. 60+ agents, 18 skills, 605 methodologies.
ML Engineer role: LLM APIs (OpenAI, Claude, Gemini), embeddings, RAG pipelines, fine-tuning, LangChain, LlamaIndex, vector databases (Pinecone, Chroma, Weaviate), prompt engineering, model evaluation, cost opti...
从当前会话中提取经验,自动生成可复用的 Claude Code Skill。Use when user wants to 提取skill, 总结成skill, 固化经验, 生成skill, extract skill, create skill from context, save as skill, 把经验变成skill.
使用 AI 理解和分析多媒体内容(图片、视频、音频)。Use when user wants to 理解图片, 分析视频, 音频转文字, 视频问答, understand media, analyze video, transcribe audio, describe image, what is in this video/image/...
Apply Focus.AI brand guidelines to documents, presentations, websites, and other materials. Supports two sub-brands - Focus.AI Client (services, proposals, client work) and Focus.AI Labs (research, experiments,...
Meaning engine that translates intention into safe, effective symbolic experience
Listener agency preservation and non-coercive suggestion framework
Generate production-ready SSML scripts for Google Cloud TTS
Generate voice audio using Google Cloud TTS with enhancement
Use for any TiDB-related projects, tasks, or code. Context engineering and context management for AI agents: keep prompt prefixes stable for KV-cache, use append-only context, prefer tool masking over tool remo...
A high-precision implementation mode for the Claude-type AI to execute the plan with zero errors.
The unified AI agent for Polyprophet - combines deep analysis, precise execution, and atomic-level investigation. One agent, one skill, one mission.
A deep analysis mode for the Google AI (Gemini) to fully deconstruct the codebase and market conditions without editing code.
Capture session context before ending for seamless resume by next agent. Use when ending a session, switching contexts, or when user runs /handoff.
结束当前对话
Ralph Wiggum 自主循环模式。AI 持续执行任务直到全部完成,按用户确认的节奏汇报(默认整单完成后)。触发词:ralph、ralph-loop、/ralph-loop、自主循环、autonomous、直到完成、循环执行。
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers to integrate APIs, whether in Python (FastMCP) or Node/Typ...
Two-phase reasoning paradigm that reduces hallucinations and constraint violations in complex planning tasks. Use when tasks involve multi-step planning, constraint satisfaction, resource allocatio...
Use when starting a Ralph loop and you want guided prompt creation. Asks questions to gather specs, requirements, tech stack, testing needs, and completion criteria before auto-starting the loop.
Apply RLM (Recursive Language Model) reasoning pattern for large context processing. Use when analyzing large files, codebases, or documents. Triggers on "RLM pattern", "large file analysis", "selective reading...
Claude Code CLI の仕様と使い方に関する知識を提供。プラグイン開発、スキル、スラッシュコマンド、サブエージェント、フック、LSP、MCP、権限設定、セッション管理について回答。Use when user asks about Claude Code, plug...
Gemini CLI の仕様と使い方に関する知識を提供。モデル選択、スラッシュコマンド、組み込みツール、拡張機能について回答。Use when user asks about Gemini CLI, gemini command, model selection, /model, /settings, google...
Claude Code プラグインの command 仕様知識。スラッシュコマンドの正しい形式、フロントマター、変数、model 指定を提供。Use when creating, updating, or maintaining commands, understanding command structure, or imple...
OpenAI Codex CLI の仕様と使い方に関する知識を提供。モデル選択、推論レベル、承認モード、サンドボックス、組み込みツール、スラッシュコマンド、設定方法について回答。Use when user asks about Codex CLI, codex command...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.