Agent 工作流
可复用的 Agent 工作流和编排模式
Skills 列表
ralphinho-rfc-pipeline
基于RFC的多智能体DAG执行模式，包含质量门禁、合并队列和工作单元编排。
affaan-mnanoclaw-repl
操作和扩展 NanoClaw v2，ECC 基于 claude -p 构建的零依赖、会话感知的 REPL。
affaan-mcontext-budget
全面盘点 Claude Code 会话中 Agent、Skill、MCP 服务和 Rule 对上下文窗口（context window）的占用。精准识别体积过大与冗余的组件，并按优先级输出 Token 瘦身建议。
affaan-miterative-retrieval
逐步优化上下文检索以解决子代理上下文问题的模式
affaan-magentic-engineering
以评估优先执行、任务分解和成本感知模型路由的方式，作为智能体工程师运作。
affaan-mautonomous-loops
自主 Claude Code 循环的模式与架构——从简单的顺序流水线到基于 RFC 的多智能体 DAG 系统。
affaan-minvestor-materials
创建和更新融资演示文稿、一页纸、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文档、预测、资金用途表、里程碑计划或需要在多个融资资产之间保持内部一致性的材料时使用。
affaan-mvideo-editing
AI辅助视频编辑工作流，用于剪辑、组织和增强真实素材。涵盖从原始拍摄到FFmpeg、Remotion、ElevenLabs、fal.ai，再到Descript或CapCut最终润色的完整流程。当用户想要编辑视频、剪辑素材、制作vlog或构建视频内容时使用。
affaan-mcontinuous-learning-v2
基于本能的持续学习系统，通过钩子观察会话，创建带有置信度评分的原子本能，并将其演化为技能/命令/智能体。v2.1 新增项目级本能，防止跨项目污染。
affaan-m
using-superpowers
在任何对话开始时使用——建立如何查找和使用技能，要求在包括澄清问题在内的任何回复之前调用 Skill 工具
obra
backend-code-review
Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside `api/`.
langgenius
pr-feedback-quality-gate
Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes.
nexu-ioecommerce-image-workflow
Reference-product ecommerce image workflow for generating a compact set of product-faithful main, feature, and lifestyle images from real product reference photos. V1 requires uploaded product imagery and intentionally defers brief-only concept generation and platform-specific batch exports.
nexu-ioslack-gif-creator
Create animated GIFs optimized for Slack with validators for size constraints and composable animation primitives.
nexu-iopixelbin-media
Generate and edit images and videos with an 85+ API portfolio and build visually appealing website pages via Pixelbin.
nexu-iovenice-video
Video generation and transcription workflows via the Venice.ai API.
nexu-iowpds
WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.
nexu-iofal-train
Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.
nexu-ioreplicate
Discover, compare, and run AI models using Replicate's API. Strong fit for image, audio, and video generation pipelines that swap models frequently.
nexu-iofal-realtime
Real-time and streaming AI image generation via fal.ai. Suited for moodboard exploration, draft variations, and rapid creative iteration.
nexu-iofal-3d
Generate 3D models from text or images via fal.ai. Useful for game assets, AR previews, product mockups, and concept sculpting.
nexu-iofal-generate
Generate images and videos using fal.ai AI models. Production-grade catalogue covering Flux, SDXL, ideogram, and other community-hosted endpoints.
nexu-iofigma-use
Run Figma Plugin API scripts for canvas writes, inspections, variables, and design-system work. Prerequisite for every other Figma skill in this catalogue.
nexu-iominimax-docx
Professional DOCX document creation and editing using OpenXML SDK. Useful for branded reports, polished proposals, and template-based authoring.
nexu-io