Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

academy-video-pipeline

Sterne22

Forks4

Aktualisiert24. Juni 2026 um 03:23

Programmatic HTML→video generation for the Zouroboros Academy and Alaric/Mimir explainer content, backed by HeyGen HyperFrames. Author a composition as a single HTML file (GSAP/anime.js timelines, captions, voiceovers, audio-reactive visuals) and render it to a real MP4/WebM/MOV/GIF locally with headless Chrome + ffmpeg — no manual ffmpeg zoompan pipeline, no cloud render. Use this to build title cards, faceless explainers, slideshows, product/launch videos, motion graphics, and captioned clips. The heavy multi-step orchestration skills (faceless-explainer, slideshow, etc.) live in Integrations/hyperframes/skills/.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

marlandoj

marlandoj/zouroboros

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

SKILL.md

readonly

name	academy-video-pipeline
description	Programmatic HTML→video generation for the Zouroboros Academy and Alaric/Mimir explainer content, backed by HeyGen HyperFrames. Author a composition as a single HTML file (GSAP/anime.js timelines, captions, voiceovers, audio-reactive visuals) and render it to a real MP4/WebM/MOV/GIF locally with headless Chrome + ffmpeg — no manual ffmpeg zoompan pipeline, no cloud render. Use this to build title cards, faceless explainers, slideshows, product/launch videos, motion graphics, and captioned clips. The heavy multi-step orchestration skills (faceless-explainer, slideshow, etc.) live in Integrations/hyperframes/skills/.
compatibility	Created for Zo Computer
metadata	{"author":"marlandoj.zo.computer"}
allowed-tools	Bash, Read, Write, Edit

Academy Video Pipeline (HyperFrames)

Replaces the hand-rolled ffmpeg-zoompan + ElevenLabs stills pipeline for Academy / Alaric / Mimir explainer content. You write HTML, HyperFrames renders video. Apache-2.0, runs fully local.

Validated environment (2026-06-24)

Confirmed working on this Zo host with no Docker:

Node + npx hyperframes@latest (pinned via npx, no global install needed)
Headless Chrome auto-detected (chrome-headless-shell); ffmpeg/ffprobe present
A 3s 1080p30 composition renders in ~10s wall at -q draft, 3 workers
doctor reports Docker + whisper-cpp ✗ — not needed for local render (whisper-cpp only powers transcribe; TTS uses Kokoro-82M)

Always export PUPPETEER_SKIP_DOWNLOAD=1 so npx doesn't try to fetch its own Chromium (the host's is used instead).

Quick render (the validated path)

export PUPPETEER_SKIP_DOWNLOAD=1

# 1. Scaffold a project (blank starter; --skip-skills keeps it lean)
npx -y hyperframes@latest init my-video --non-interactive --example blank --skip-skills

# 2. Author the composition by editing my-video/index.html
#    - #root carries data-duration / data-width / data-height (1920x1080)
#    - each .clip is positioned; window.__timelines["main"] drives GSAP
#    - gsap is loaded from CDN in the scaffolded <head>

# 3. Validate, then render
cd my-video
npx -y hyperframes@latest lint
npx -y hyperframes@latest render -q draft -o renders/test.mp4   # draft | standard | high

Output is a real H.264 MP4 (verify with ffprobe). Other formats: --format webm|mov|gif|png-sequence. Tune with -f/--fps, -w/--workers, -q/--quality.

When to use which orchestration skill

For anything beyond a single title card, drive one of the vendor multi-step skills in Integrations/hyperframes/skills/ (they cross-reference each other with relative paths, so run them from there). The Academy/Mimir fit:

faceless-explainer — text → narrated faceless explainer (30-90s sweet spot, every visual invented). Primary Academy/Mimir skill. SkillSpector pre-adoption scan: score 17 / LOW / SAFE.
slideshow — deck-style sequences. SkillSpector: 5 / LOW / SAFE.
Also shipped: general-video, embedded-captions, graphic-overlays, motion-graphics, music-to-video, product-launch-video, website-to-video, pr-to-video, hyperframes-animation/creative/media/cli.

If the route is unclear, read Integrations/hyperframes/skills/hyperframes/ first — it's the router.

Security posture

HyperFrames is a Claude Code plugin marketplace (.claude-plugin/). The two skills we lead with both pass the skill-security-gate (faceless-explainer 17, slideshow 5 — both SAFE). Re-gate any other vendor skill before first use:

bash Skills/skill-security-gate/scripts/gate.sh Integrations/hyperframes/skills/<name>

Underlying tool

CLI: npx -y hyperframes@latest <cmd> (init, lint, render, preview, doctor, inspect, transcribe, tts, capture, publish).
Source clone: Integrations/hyperframes/ (heygen-com/hyperframes, Apache-2.0).
Docs: hyperframes.heygen.com

Mehr aus diesem Repository

gleiches Repository

zo-swarm-orchestrator

marlandoj/zouroboros

Local-only multi-agent orchestrator with token optimization, 6-signal composite routing, and persistent memory. Routes all tasks through local executor bridges (Claude Code, Hermes, Gemini, Codex) with DAG dependencies, auto-episode creation, and cognitive profiles.

2026-07-1722

agent-model-healer

marlandoj/zouroboros

Zouroboros self-healing watchdog that monitors scheduled agent models and automatically switches failing agents to backup models, restoring originals when they recover.

2026-07-1722

zo-memory-system

marlandoj/zouroboros

Hybrid SQLite + Vector persona memory system for Zo Computer. Episodic memory with temporal queries, graph-boosted search, BFS path finding, knowledge gap analysis, auto-capture pipeline, and per-workload model routing. Default generation workloads use OpenAI `gpt-4o-mini`; embeddings use OpenAI `text-embedding-3-small`.

2026-07-1122

skill-security-gate

marlandoj/zouroboros

Security governance gate for AI agent skills, backed by NVIDIA SkillSpector. Statically scans a skill (local path, directory, zip, or Git URL) for 65 vulnerability patterns across 16 categories (prompt injection, data exfiltration, privilege escalation, supply chain, excessive agency, tool/MCP misuse, dangerous code via AST, YARA signatures) and returns a 0-100 risk score with a SAFE / REVIEW / DO_NOT_INSTALL recommendation. Use BEFORE adopting any third-party skill, and for the periodic baseline scan of the Skills/ directory.

2026-07-1122

classifier-fallback

marlandoj/zouroboros

Detector for model classifier SOFT-blocks — refusals, filtered-to-empty, truncated-with-disclaimer, content-policy flags — that masquerade as successful empty output to existing infrastructure (agent-model-healer only catches HARD failures: HTTP 4xx/5xx, timeouts, genuine empties). Classifies an output as soft_block / genuine_empty / ok using a per-provider signal catalog, then routes a per-domain fallback (security → broader-tolerance model, bio/chem → human review, distillation → refuse-by-design, never routed around). Every block + fallback is appended to an audit ledger. A quarterly system-card-diff agent flags expanded classifier scope so the catalog stays current.

2026-07-0822

visual-verifier

marlandoj/zouroboros

Rendered-output verification station for the swarm post-flight eval. After a maker subagent produces a visual deliverable (UI/route/site), the station captures a full-page screenshot via agent-browser, then an independent verifier model (not equal to author, per aiewf P0-2) reads the screenshot against seed acceptance criteria + project DESIGN.md tokens + prior screenshots. Match marks the task complete; mismatch emits a structured visual diff for the maker's next iteration. The verifier is the exit condition, not the maker. Recurring visual failure modes graduate to instincts.yaml via the extract-patterns gate (ZOU-452).

2026-07-0822

name	academy-video-pipeline
description	Programmatic HTML→video generation for the Zouroboros Academy and Alaric/Mimir explainer content, backed by HeyGen HyperFrames. Author a composition as a single HTML file (GSAP/anime.js timelines, captions, voiceovers, audio-reactive visuals) and render it to a real MP4/WebM/MOV/GIF locally with headless Chrome + ffmpeg — no manual ffmpeg zoompan pipeline, no cloud render. Use this to build title cards, faceless explainers, slideshows, product/launch videos, motion graphics, and captioned clips. The heavy multi-step orchestration skills (faceless-explainer, slideshow, etc.) live in Integrations/hyperframes/skills/.
compatibility	Created for Zo Computer
metadata	{"author":"marlandoj.zo.computer"}
allowed-tools	Bash, Read, Write, Edit

Academy Video Pipeline (HyperFrames)

Replaces the hand-rolled ffmpeg-zoompan + ElevenLabs stills pipeline for Academy / Alaric / Mimir explainer content. You write HTML, HyperFrames renders video. Apache-2.0, runs fully local.

Validated environment (2026-06-24)

Confirmed working on this Zo host with no Docker:

Node + npx hyperframes@latest (pinned via npx, no global install needed)
Headless Chrome auto-detected (chrome-headless-shell); ffmpeg/ffprobe present
A 3s 1080p30 composition renders in ~10s wall at -q draft, 3 workers
doctor reports Docker + whisper-cpp ✗ — not needed for local render (whisper-cpp only powers transcribe; TTS uses Kokoro-82M)

Always export PUPPETEER_SKIP_DOWNLOAD=1 so npx doesn't try to fetch its own Chromium (the host's is used instead).

Quick render (the validated path)

export PUPPETEER_SKIP_DOWNLOAD=1

# 1. Scaffold a project (blank starter; --skip-skills keeps it lean)
npx -y hyperframes@latest init my-video --non-interactive --example blank --skip-skills

# 2. Author the composition by editing my-video/index.html
#    - #root carries data-duration / data-width / data-height (1920x1080)
#    - each .clip is positioned; window.__timelines["main"] drives GSAP
#    - gsap is loaded from CDN in the scaffolded <head>

# 3. Validate, then render
cd my-video
npx -y hyperframes@latest lint
npx -y hyperframes@latest render -q draft -o renders/test.mp4   # draft | standard | high

Output is a real H.264 MP4 (verify with ffprobe). Other formats: --format webm|mov|gif|png-sequence. Tune with -f/--fps, -w/--workers, -q/--quality.

When to use which orchestration skill

faceless-explainer — text → narrated faceless explainer (30-90s sweet spot, every visual invented). Primary Academy/Mimir skill. SkillSpector pre-adoption scan: score 17 / LOW / SAFE.
slideshow — deck-style sequences. SkillSpector: 5 / LOW / SAFE.
Also shipped: general-video, embedded-captions, graphic-overlays, motion-graphics, music-to-video, product-launch-video, website-to-video, pr-to-video, hyperframes-animation/creative/media/cli.

If the route is unclear, read Integrations/hyperframes/skills/hyperframes/ first — it's the router.

Security posture

bash Skills/skill-security-gate/scripts/gate.sh Integrations/hyperframes/skills/<name>

Underlying tool

CLI: npx -y hyperframes@latest <cmd> (init, lint, render, preview, doctor, inspect, transcribe, tts, capture, publish).
Source clone: Integrations/hyperframes/ (heygen-com/hyperframes, Apache-2.0).
Docs: hyperframes.heygen.com