Communitygithub.com

curiositech/windags-skills

專精於 Apple Silicon Mac 的腳本轉影片製作流程,擅長混合本地/雲端工作流程、角色一致的 LoRA 訓練、動態圖形生成與藝術家委託。

windags-skills 是什麼?

這個技能是專為在 Apple Silicon Mac 上進行專業「腳本轉影片」製作的 AI 代理所設計。它擅長引導使用者透過一個結構化的決策樹來選擇最佳工作流程,根據內容類型(教育、創意、品牌)、預算和時間限制,決定使用素材庫影片、文字轉影片(T2V)模型(如 Sora、Runway Gen-3),還是影像轉影片(I2V)並搭配自訂 LoRA 訓練,以達成角色一致性。技能內建了詳盡的故障排除指南,處理常見問題如模糊抖動、角色風格漂移、成本超支和音訊不同步,並提供明確的修復步驟。它強烈建議先從素材庫影片的概念驗證開始,再逐步增加複雜度,以有效管理專案風險和成本。此技能不適用於即時剪輯、複雜合成、3D 建模或專業音訊後製,並在需要這些專業領域時,明確指示應移交給其他專門技能。

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

AI 影片製作大師

專精於 Apple Silicon Mac 的腳本轉影片製作流程。擅長混合本地/雲端工作流程、風格一致性以及動態圖形生成。

決策點

方法選擇樹

腳本分析:
├── 內容類型 = 教育/企業/紀錄片
│   ├── 預算 < $50/月 → 素材庫影片組合 (InVideo 風格)
│   └── 預算 > $50/月 → 素材庫 + T2V 混合
├── 內容類型 = 創意/藝術/抽象
│   ├── 時程 < 2 天 → Sora/Runway T2V
│   └── 時程 > 2 天 → 自訂 I2V 搭配 LoRA 訓練
└── 內容類型 = 品牌/角色導向
    ├── 已有現成素材 → I2V 動畫流程
    └── 無素材 → 委託藝術家 → I2V 流程

品質 vs. 成本決策:
├── 需要專業交付物
│   ├── 使用 Sora/Runway Gen-3 (高階 T2V)
│   └── 為 I2V 委託客製藝術作品
├── 原型/測試內容
│   ├── 使用素材庫影片 + 免費 T2V 模型
│   └── 本地 ComfyUI I2V 生成
└── 大量生產
    ├── 雲端批次處理 (Vast.ai)
    └── 自動化素材庫影片工作流程

錯誤復原樹:
├── T2V 生成品質不佳
│   ├── 切換至素材庫影片 + 動態圖形疊加
│   └── 改為使用委託藝術作品的 I2V
├── 雲端 GPU 超時/故障
│   ├── 更換供應商重試 (Vast.ai → RunPod)
│   └── 切換至本地處理並延長時程
└── 風格一致性中斷
    ├── 使用更多參考影像重新訓練 LoRA
    └── 使用 IPAdapter + 一致的提示詞結構

處理地點決策矩陣

鏡頭數複雜度預算建議
1-5簡單任意本地 M4 Max
6-20中等<$10素材庫影片
6-20高>$10雲端 GPU 批次
20+任意任意需使用雲端 GPU

故障模式

模糊動態抖動

症狀: 影格率不一致、動作卡頓、時間偽影 診斷: FPS 設定不匹配或動態引導不足 修復: 設定一致的 24fps 流程、添加動態強度控制、使用更高的引導尺度 (7-9) 偵測規則: 若時間一致性分數 < 0.7 或影格差異 > 0.3,則套用動態穩定化

角色一致性漂移

症狀: 角色外觀在不同鏡頭間改變、風格不一致 診斷: 參考條件設定不足或 LoRA 過度擬合 修復: 使用 15-20 張參考影像重新訓練 LoRA、使用 IPAdapter 確保臉部一致性 偵測規則: 若連續鏡頭間的角色相似度分數 < 0.8,則暫停並重新訓練

成本超支螺旋

症狀: 雲端 GPU 帳單超出預算 >200%、迭代週期緩慢 診斷: 缺乏成本監控或批次大小設定無效率 修復: 在雲端腳本中設定硬性限制、最佳化批次大小、使用競價實例 偵測規則: 若每分鐘成本超過 $0.50 或每次迭代時間 > 15分鐘,則切換至本地處理

音訊不同步連鎖反應

症狀: 唇形同步偏移、視聽時間點不匹配 診斷: 生成時間變異影響音訊對齊 修復: 先生成所有影片,然後在後期製作中使用標記對齊音訊 偵測規則: 若音訊偏移超過影片標記 200ms,則使用 FFmpeg 重新對齊

方案膨脹癱瘓

症狀: 生成選項過多、分析癱瘓、專案停滯 診斷: 在未先測試簡單方法前就過度最佳化 修復: 總是先從素材庫影片的概念驗證開始,再逐步增加複雜度 偵測規則: 若專案規劃超過 2 小時仍未產出任何內容,則預設使用素材庫影片

實例演練

教育影片:「量子計算入門」

輸入: 關於量子計算基礎的 3 分鐘腳本

決策過程:

  1. 內容分析:教育 → 建議使用素材庫影片
  2. 預算檢查:$30 預算 → 使用 Pexels API + 動態圖形
  3. 鏡頭拆解:需要 12 個鏡頭
  4. 品質目標:專業但非電影等級

執行:

# 步驟 1:從腳本生成鏡頭列表
python scripts/script_analyzer.py --script quantum_script.txt
# 輸出:識別出 12 個鏡頭,其中 8 個需要素材庫影片,4 個需要動態圖形

# 步驟 2:來源素材庫影片
python scripts/stock_video_generator.py --shots_file shots.json --style documentary
# 選定:實驗室畫面、抽象科技視覺、乾淨背景

# 步驟 3:為複雜概念生成動態圖形
python scripts/motion_graphics_generator.py --type data_viz --concept "quantum_states"
# 建立:疊加態、纏結等動畫圖表

# 步驟 4:組合與同步
python scripts/video_assembler.py --footage stock_clips/ --graphics motion/ --audio narration.wav

專家 vs. 新手:

  • 專家:在生成圖形前檢查了音訊電平,選擇 16:9 格式以確保平台相容性
  • 新手可能會忽略:素材庫選擇中的光線一致性、動態圖形時長需匹配說話節奏

最終輸出: 3分15秒影片,成本 $0(免費素材),總製作時間 45 分鐘

品質關卡

當所有條件都符合時,影片製作才算完成:

  • 所有片段影格率一致為 24fps
  • 音訊電平標準化至 -23dB 到 -18dB LUFS 之間
  • 視覺風格保持一致(色彩校正、長寬比)
  • 動態圖形與旁白同步,容差在 100ms 以內
  • 各鏡頭間的角色/主體一致性分數 >0.8
  • 任何 5 秒片段中無時間偽影(閃爍、抖動)
  • 字幕/標題時機與音訊峰值對齊
  • 匯出渲染在目標解析度下無錯誤
  • 檔案大小在平台限制內(YouTube: <128GB, 社群媒體: <4GB)
  • 備份檔案已使用版本控制儲存

不適用範圍

此技能不應用於:

  • 即時影片剪輯 → 請直接使用 DaVinci Resolve 或 Premiere Pro
  • 複雜影片效果/合成 → 交由 After Effects 或 physics-rendering-expert 技能處理
  • 超出基本同步的音訊製作 → 使用 sound-engineer 技能進行混音、母帶處理、聲音設計
  • 3D 建模或複雜動畫 → 使用 Blender/Maya 或 physics-rendering-expert 技能
  • 直播或廣播 → 使用 OBS Studio 或廣播專用工具
  • 超出基本校正的色彩分級 → 使用專業調色師工作流程
  • 動態追蹤或移動比對 → 使用專業追蹤軟體
  • 多機同步 → 使用 PluralEyes 等專用同步工具

移交觸發條件:

  • 若專案需要超過 20 層合成 → physics-rendering-expert
  • 若音訊需要客製聲音設計 → sound-engineer
  • 若需要 3D 元素建模 → Blender 專家
  • 若需要即時效能 → 使用原生影片剪輯軟體

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.

相關技能