LLM & AI

from "obra/superpowers"

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

from "affaan-m/everything-claude-code"

Claude Codeセッション向けの包括的な検証システム。

from "affaan-m/everything-claude-code"

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image Nano Banana , text/image-to-video Seedance, Kling, Veo 3 , text-to-speech CSM-1B , and video-to-audio...

from "affaan-m/everything-claude-code"

Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally...

from "affaan-m/everything-claude-code"

Everything Claude Code のインタラクティブなインストーラー — スキルとルールの選択とインストールをユーザーレベルまたはプロジェクトレベルのディレクトリへガイドし、パスを検証し、必要に応じてインストールされたファイルを最適化します。

from "affaan-m/everything-claude-code"

Claude Codeセッションの正式な評価フレームワークで、評価駆動開発（EDD）の原則を実装します

from "affaan-m/everything-claude-code"

Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files

from "affaan-m/everything-claude-code"

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.

from "affaan-m/everything-claude-code"

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.

from "affaan-m/everything-claude-code"

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

from "affaan-m/everything-claude-code"

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

from "affaan-m/everything-claude-code"

Pattern for progressively refining context retrieval to solve the subagent context problem

from "affaan-m/everything-claude-code"

PyTorch深度学习模式与最佳实践，用于构建稳健、高效且可复现的训练流程、模型架构和数据加载。

from "affaan-m/everything-claude-code"

苹果FoundationModels框架用于设备上的LLM——文本生成、使用@Generable进行引导生成、工具调用，以及在iOS 26+中的快照流。

from "affaan-m/everything-claude-code"

设计和优化AI代理的动作空间、工具定义和观察格式，以提高完成率。

from "affaan-m/everything-claude-code"

海关文件、关税分类、关税优化、受限方筛查以及多司法管辖区法规合规的编码化专业知识。由拥有15年以上经验的贸易合规专家提供。包括HS分类逻辑、Incoterms应用、自贸协定利用以及罚款减免。适用于处理海关清关、关税分类、贸易合规、进出口文件或关税优化时使用。license: Apache-2.0

from "affaan-m/everything-claude-code"

为离散和批量制造中的生产调度、作业排序、产线平衡、换模优化和瓶颈解决提供编码化专业知识。基于拥有15年以上经验的生产调度师的知识。包括约束理论/鼓-缓冲-绳、快速换模、设备综合效率分析、中断响应框架以及企业资源计划/制造执行系统交互模式。适用于调度生产、解决瓶颈、优化换模、应对中断或平衡制造产线时。license: Apache-2.0

from "affaan-m/everything-claude-code"

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

from "affaan-m/everything-claude-code"

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

from "affaan-m/everything-claude-code"

This skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule, or needs guidance on hookify rule syntax and patterns.

from "affaan-m/everything-claude-code"

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

from "affaan-m/everything-claude-code"

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

from "affaan-m/everything-claude-code"

Engineering operating model for teams where AI agents generate a large share of implementation output.

from "affaan-m/everything-claude-code"

通过 fal.ai MCP 实现统一的媒体生成——图像、视频和音频。涵盖文本到图像（Nano Banana）、文本/图像到视频（Seedance、Kling、Veo 3）、文本到语音（CSM-1B），以及视频到音频（ThinkSound）。当用户想要使用 AI 生成图像、视频或音频时使用。