Communitygithub.com

curiositech/windags-skills

专为 Apple Silicon Mac 打造的 AI 视频制作专家,精通脚本转视频流水线、混合本地/云端工作流、角色一致性 LoRA 训练以及动态图形生成。

windags-skills 是什么?

该技能是一个面向 AI 视频制作的综合专家系统,专为 Apple Silicon Mac 优化,旨在指导用户完成从脚本到最终视频的端到端生产流程。它涵盖了多种生产路径,包括基于预算和内容类型的决策树(如教育类内容推荐使用素材库,而创意类内容则推荐使用文本到视频模型或定制的图像到视频流水线)。该技能详细定义了故障模式与恢复策略,例如处理运动模糊、角色一致性漂移和成本超支,并提供了具体的检测规则和修复方法。它支持混合工作流,允许在本地(M4 Max)和云端 GPU(如 Vast.ai、RunPod)之间灵活切换,以平衡成本与质量。技能还包含了明确的质量门禁清单和不应使用的边界,确保用户不会误用它来处理实时编辑或 3D 建模等超出其范围的任务。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/ai-video-production-master

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

AI 视频制作大师

专为 Apple Silicon Mac 打造的脚本转视频生产流水线专家。专注于混合本地/云端工作流、风格一致性和动态图形生成。

决策点

方法选择树

脚本分析:
├── 内容类型 = 教育/企业/纪录片
│   ├── 预算 < 50 美元/月 → 素材库组装 (InVideo 风格)
│   └── 预算 > 50 美元/月 → 素材库 + T2V 混合
├── 内容类型 = 创意/艺术/抽象
│   ├── 时间线 < 2 天 → Sora/Runway T2V
│   └── 时间线 > 2 天 → 带有 LoRA 训练的自定义 I2V
└── 内容类型 = 品牌/角色为中心
    ├── 现有资产可用 → I2V 动画流水线
    └── 无资产 → 委托艺术家 → I2V 流水线

质量与成本决策:
├── 需要专业交付物
│   ├── 使用 Sora/Runway Gen-3 (高级 T2V)
│   └── 为 I2V 委托定制艺术品
├── 原型/测试内容
│   ├── 使用素材库 + 免费 T2V 模型
│   └── 本地 ComfyUI I2V 生成
└── 高产量生产
    ├── 云端批处理 (Vast.ai)
    └── 自动化素材库工作流

错误恢复树:
├── T2V 生成质量失败
│   ├── 切换到素材库 + 动态图形叠加
│   └── 回退到使用委托艺术品的 I2V
├── 云端 GPU 超时/失败
│   ├── 使用不同提供商重试 (Vast.ai → RunPod)
│   └── 切换到本地处理并延长时限
└── 风格一致性中断
    ├── 使用更多参考图像重新训练 LoRA
    └── 使用 IPAdapter + 一致的提示结构

处理位置决策矩阵

镜头数复杂度预算建议
1-5简单任意本地 M4 Max
6-20中等<10 美元素材库
6-20高>10 美元云端 GPU 批处理
20+任意任意需要云端 GPU

故障模式

模糊运动抖动

症状: 帧率不一致、运动卡顿、时间伪影 诊断: FPS 设置不匹配或运动引导不足 修复: 设置一致的 24fps 流水线,添加运动强度控制,使用更高的引导尺度 (7-9) 检测规则: 如果时间一致性得分 < 0.7 或帧差 > 0.3,则应用运动稳定

角色一致性漂移

症状: 角色外观在不同镜头间变化,风格不一致 诊断: 参考条件不足或 LoRA 过拟合 修复: 使用 15-20 张参考图像重新训练 LoRA,使用 IPAdapter 确保面部一致性 检测规则: 如果连续镜头间的角色相似性得分 < 0.8,则暂停并重新训练

成本超支螺旋

症状: 云端 GPU 账单超出预算 200% 以上,迭代周期缓慢 诊断: 无成本监控或批量大小效率低下 修复: 在云脚本中设置硬限制,优化批量大小,使用竞价实例 检测规则: 如果每分钟成本超过 0.50 美元或迭代时间 > 15 分钟,则切换到本地处理

音频不同步级联

症状: 口型同步漂移,音视频时间不匹配 诊断: 生成时间的可变性影响音频对齐 修复: 先生成所有视频,然后使用标记在后期中对齐音频 检测规则: 如果音频偏移 > 视频标记 200ms,则使用 FFmpeg 重新对齐

方案臃肿瘫痪

症状: 生成选项过多,分析瘫痪,项目停滞 诊断: 过度优化而未首先测试简单方法 修复: 始终从素材库的概念验证开始,逐步迭代到复杂方案 检测规则: 如果项目规划时间超过 2 小时且未生成任何内容,则默认使用素材库

工作示例

教育视频:"量子计算详解"

输入: 关于量子计算基础的 3 分钟脚本

决策过程:

  1. 内容分析:教育类 → 推荐使用素材库
  2. 预算检查:30 美元预算 → 使用 Pexels API + 动态图形
  3. 镜头分解:需要 12 个镜头
  4. 质量目标:专业但不具电影感

执行:

# 步骤 1:从脚本生成镜头列表
python scripts/script_analyzer.py --script quantum_script.txt
# 输出:识别出 12 个镜头,8 个需要素材库,4 个需要动态图形

# 步骤 2:获取素材库视频
python scripts/stock_video_generator.py --shots_file shots.json --style documentary
# 已选择:实验室画面、抽象科技视觉元素、干净背景

# 步骤 3:为复杂概念生成动态图形
python scripts/motion_graphics_generator.py --type data_viz --concept "quantum_states"
# 已创建:叠加态、纠缠态的动画图表

# 步骤 4:组装和同步
python scripts/video_assembler.py --footage stock_clips/ --graphics motion/ --audio narration.wav

专家 vs. 新手:

  • 专家:在生成图形前检查了音频电平,为平台兼容性选择了 16:9 格式
  • 新手可能会遗漏:素材选择中一致的光照,适当的动态图形持续时间与语速匹配

最终输出: 3 分 15 秒视频,成本 0 美元(免费素材),总制作时间 45 分钟

质量门禁

当满足所有条件时,视频制作完成:

  • 所有片段的帧率一致为 24fps
  • 音频电平归一化到 -23dB 到 -18dB LUFS 之间
  • 视觉风格保持一致(色彩校正、宽高比)
  • 动态图形与旁白同步,容差在 100ms 内
  • 角色/主体一致性得分在镜头间 > 0.8
  • 任何 5 秒片段中无时间伪影(闪烁、抖动)
  • 字幕/标题时序与音频峰值对齐
  • 导出在目标分辨率下无错误渲染
  • 文件大小在平台限制内(YouTube:<128GB,社交媒体:<4GB)
  • 备份文件通过版本控制存储

不适用边界

该技能不应用于:

  • 实时视频编辑 → 直接使用 DaVinci Resolve 或 Premiere Pro
  • 复杂视频特效/合成 → 交给 After Effects 或 physics-rendering-expert 技能
  • 超出基本同步的音频制作 → 使用 sound-engineer 技能进行混音、母带处理、声音设计
  • 3D 建模或复杂动画 → 使用 Blender/Maya 或 physics-rendering-expert 技能
  • 直播或广播 → 使用 OBS Studio 或广播专用工具
  • 超出基本校正的色彩分级 → 使用专业调色师工作流
  • 运动跟踪或匹配移动 → 使用专用跟踪软件
  • 多摄像机同步 → 使用专用同步工具如 PluralEyes

交接触发条件:

  • 如果项目需要超过 20 层的合成 → physics-rendering-expert
  • 如果音频需要定制声音设计 → sound-engineer
  • 如果需要 3D 元素建模 → Blender 专家
  • 如果需要实时性能 → 使用本地视频编辑软件

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

curiositech/windags-skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

相关技能