Communitygithub.com

affaan-m/ECC

Video und Audio sehen, verstehen und bearbeiten – mit Frameextraktion, semantischer Suche, Transkodierung und Timeline-Bearbeitung.

Was ist ECC?

ECC (Every Component Connected) ist ein leistungsstarkes KI-Agenten-Skill, das Videodaten in einer durchgehenden Pipeline verarbeitet: von der Aufnahme (lokale Dateien, URLs, RTSP-Live-Streams, Desktop-Bildschirmaufnahme) über das Verständnis (Frameextraktion, visuelle/semantische/temporale Indizierung) bis hin zur Aktion (Transkodierung, Normalisierung, Timeline-Edits wie Untertitel, Overlays, Sprachdubbing, Übersetzung). Es erzeugt abspielbare Stream-Links und Medien-Assets (Bild, Audio, Video) und eignet sich besonders für automatisierte Videoworkflows, Livestream-Monitoring, Inhaltsanalyse und barrierefreie Medienproduktion. Das Skill ist plattformunabhängig und funktioniert mit Claude Code, Cursor, Codex und ähnlichen KI-Agenten-Ökosystemen. Durch die modulare Architektur können Entwickler jedes Modul einzeln nutzen oder in bestehende CI/CD-Pipelines integrieren.

Funktioniert mit~Claude Code~Codex CLI~Cursor
npx skills add affaan-m/ECC

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Was macht ECC?

Video und Audio sehen, verstehen und bearbeiten. Sehen – Aufnahme von lokalen Dateien, URLs, RTSP/Live-Feeds oder Desktop-Bildschirmaufnahme; Rückgabe von Echtzeitkontext und abspielbaren Stream-Links. Verstehen – Frameextraktion, Aufbau visueller/semantischer/temporaler Indizes und Suche nach Momenten mit Zeitstempeln und automatischen Clips. Handeln – Transkodieren und Normalisieren (Codec, FPS, Auflösung, Seitenverhältnis), Durchführen von Timeline-Edits (Untertitel, Text-/Bildeinblendungen, Branding, Audio-Overlays, Synchronisation, Übersetzung), Generieren von Medien-Assets (Bild, Audio, Video).

Voraussetzungen

  • Betriebssystem: Linux (bevorzugt Ubuntu 22.04+), macOS (ARM64), Windows (WSL2)
  • Python 3.10+
  • FFmpeg 6.0+
  • ExifTool 12.60+
  • CUDA 12.x (optional, für GPU-Beschleunigung)
  • KI-Agent: Claude Code, Cursor, Codex oder ein anderer unterstützter CLI-Agent

Installation

  1. Repository klonen:
    git clone https://github.com/affaan-m/ECC.git
    cd ECC
    
  2. Abhängigkeiten installieren:
    pip install -r requirements.txt
    
  3. (Optional) Umgebungsvariablen setzen:
    ECC_CACHE_DIR=/pfad/zu/cache
    ECC_GPU_ENABLED=true
    ECC_LOG_LEVEL=INFO
    

Verwendung

Aufnahme (See)

python ecc.py see --source /pfad/zu/video.mp4 --output stream.m3u8
python ecc.py see --source rtsp://kamera/stream --realtime

Verstehen (Understand)

python ecc.py understand --source /pfad/zu/video.mp4 --extract-frames --build-index
python ecc.py search --index /pfad/zu/index --query "Person mit rotem Hut" --output clips/

Handeln (Act)

python ecc.py act transcode --source input.mp4 --codec h264 --fps 30 --resolution 1920x1080
python ecc.py act overlay --source input.mp4 --overlay-text "Willkommen" --duration 5 --output branded.mp4
python ecc.py act subtitle --source input.mp4 --subtitle-file untertitel.srt --burn-in --output untertitelt.mp4

Architektur

Das Skill besteht aus drei Hauptmodulen:

ModulFunktion
IngestorDatei-, URL-, RTSP- und Desktop-Aufnahme, Caching
AnalyzerFrameextraktion, semantische Indizierung (CLIP, Whisper), temporale Segmentierung
ProcessorTranskodierung, Timeline-Edits, Media-Asset-Generierung

Beispiele

1. Live-Stream überwachen und Schlüsselmomente erkennen

python ecc.py see --source rtsp://kamera --realtime --output stream.m3u8 &
python ecc.py understand --source stream.m3u8 --build-index --semantic

2. Videos automatisch transkodieren und mit Untertiteln versehen

python ecc.py act transcode --source rohvideo.mp4 --codec h265 --fps 30
python ecc.py act subtitle --source rohvideo_h265.mp4 --auto-generate --language de --output fertig.mkv

Lizenz

MIT – siehe LICENSE für Details.

Individual skills in this repo

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

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

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 (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Verwandte Skills