{
  "version": "2",
  "generatedAt": "2026-11-03T21:36:30.074Z",
  "listing": {
    "slug": "alisa0808--vox-director",
    "name": "Vox Director",
    "tagline": "Agent skill that turns one topic into a Vox-style paper-collage explainer with Atlas Cloud and ffmpeg.",
    "shortTagline": "Vox-style explainer skill",
    "description": "A Claude Code or Codex skill: the agent drafts a beat map, runs a style bake-off, generates collage posters and motion, adds narration and music, and assembles final.mp4. Every model call goes through the Atlas Cloud API; the look lives in editable prompt guides.",
    "capabilities": [
      "adaptable",
      "operable"
    ],
    "vertical": "video-streaming",
    "shape": "skill",
    "formFactor": "skill",
    "executionModel": "hybrid",
    "provenance": "unknown",
    "codeStack": {
      "languages": [
        "Python"
      ],
      "frameworks": [
        "ffmpeg",
        "Pillow"
      ],
      "packageManager": "pip",
      "database": [],
      "hostingTarget": [
        "local"
      ]
    },
    "modelStack": {
      "providers": [
        "Atlas Cloud"
      ],
      "models": [
        "google/nano-banana-2/text-to-image",
        "google/gemini-omni-flash/image-to-video",
        "kwaivgi/kling-video-o3-pro/image-to-video",
        "xai/tts-v1",
        "bytedance/seed-audio-1.0",
        "minimax/music-2.6"
      ],
      "requiredKeys": [
        "ATLASCLOUD_API_KEY"
      ],
      "promptLocations": [
        "SKILL.md",
        "references/prompt-guide.md",
        "references/beat-layer.md",
        "references/voices.md"
      ],
      "tools": [
        "scripts/ one per pipeline stage"
      ]
    },
    "repos": [
      {
        "url": "https://github.com/Alisa0808/vox-director",
        "owner": "Alisa0808",
        "name": "vox-director",
        "license": "MIT",
        "stars": 1700,
        "lastCommit": "2026-08-11"
      }
    ],
    "interface": {
      "kind": "cli",
      "url": "https://github.com/Alisa0808/vox-director/blob/main/SKILL.md",
      "official": true,
      "hosted": "local"
    },
    "operability": "native",
    "recommendedWrapper": null,
    "reach": [
      {
        "job": "Write a beat map from a topic",
        "reachable": true,
        "evidence": "README pipeline stage 1; beats.json per project; Gate 1 approval"
      },
      {
        "job": "Style bake-off across themes",
        "reachable": true,
        "evidence": "README stage 2; 9 theme presets in references/prompt-guide.md"
      },
      {
        "job": "Generate collage keyframe posters",
        "reachable": true,
        "evidence": "README stage 3 with nano-banana-2"
      },
      {
        "job": "Animate posters into motion",
        "reachable": true,
        "evidence": "README stage 4; gemini-omni-flash or Kling for real people"
      },
      {
        "job": "Narration and background music",
        "reachable": true,
        "evidence": "README stage 5; xai/tts and minimax/music"
      },
      {
        "job": "Assemble with captions, ducking, watermark",
        "reachable": true,
        "evidence": "README stage 6; ffmpeg concat and Pillow overlays"
      },
      {
        "job": "Re-style an existing talking-head video (A-roll)",
        "reachable": true,
        "evidence": "README: ASR-segmented, gemini-omni-flash/video-edit with seedance fallback"
      },
      {
        "job": "Anchor a still photo in the collage (C-roll)",
        "reachable": true,
        "evidence": "README: nano-banana-2/edit; optional voice cloning"
      },
      {
        "job": "Element-level piece-by-piece motion",
        "reachable": true,
        "evidence": "README: optional local keyframe engine in references/local-engine.md"
      }
    ],
    "editions": [
      {
        "name": "Free",
        "price": null,
        "open": true,
        "distributions": [
          {
            "kind": "source",
            "url": "https://github.com/Alisa0808/vox-director"
          },
          {
            "kind": "installable",
            "url": "https://github.com/Alisa0808/vox-director#install",
            "command": "git clone https://github.com/Alisa0808/vox-director.git ~/.claude/skills/vox-director"
          }
        ]
      }
    ],
    "skills": {
      "kind": "pure",
      "paths": [
        "SKILL.md",
        "references/",
        "vox-director.skill"
      ],
      "install": null,
      "note": "Repo is a single voice-direction skill: SKILL.md plus reference prompt files and helper scripts, no app of its own."
    },
    "customization": {
      "summary": "Export ATLASCLOUD_API_KEY, then change the look by editing references/prompt-guide.md (theme presets and prompt structures), the narrative arcs in references/beat-layer.md, and the voice roster in references/voices.md. Per-project beats.json is the working file; examples/ has starters.",
      "envVars": [
        "ATLASCLOUD_API_KEY"
      ],
      "configFiles": [
        "beats.json",
        "examples/"
      ],
      "promptFiles": [
        "SKILL.md",
        "references/prompt-guide.md",
        "references/beat-layer.md",
        "references/voices.md",
        "references/models-and-gotchas.md"
      ],
      "effort": "config-only",
      "editCount": 8
    },
    "useWhen": [
      "I want a 60-second explainer in the Vox collage look for a topic, produced while I approve two checkpoints",
      "I have a product photo or a talking-head clip and want it restyled into a collage ad"
    ],
    "accounts": [
      "Atlas Cloud"
    ],
    "active": true,
    "lastActivity": "2026-08-11",
    "gotchas": [
      "Single provider: everything runs through Atlas Cloud and costs credits per stage",
      "Model IDs drift; the skill fetches the live model list before each run",
      "Real people and brands are routed to Kling, which is pricier and has content filters"
    ],
    "fit": {
      "adaptable": 3,
      "operable": 2
    },
    "evidence": {
      "formFactor": "README: agent skill; Claude Code auto-discovers it, AGENTS.md for other agents",
      "executionModel": "README: one script per stage in fixed order; models generate images, motion, voice, music",
      "operability": "README: usable by any coding agent; the skill is the only interface",
      "effort": "README install: export ATLASCLOUD_API_KEY; 'What's in the box' lists the prompt files",
      "editions": "README license: MIT",
      "active": "GitHub pushedAt 2026-08-11"
    },
    "confidence": {
      "formFactor": 0.95,
      "executionModel": 0.9,
      "operability": 0.9,
      "effort": 0.9,
      "reach": 0.85,
      "editions": 0.95
    },
    "openQuestions": [
      "Operable fit held at 2 because the software is prompts plus scripts around one third-party API; the Curator may judge it a thin wrapper or a real product on the strength of 1.7k stars",
      "Provenance: single-author agent-skill experiment; no statement on how the scripts were written"
    ],
    "sources": [
      {
        "url": "https://github.com/Alisa0808/vox-director",
        "foundBy": "sourcing:video-streaming:curated"
      }
    ],
    "research": {
      "stage": "verified",
      "verdict": "unverified",
      "reason": "Config-only Adaptable through named prompt files and one env var; native agent workflow with complete Reach but a single-provider dependency.",
      "disputed": []
    },
    "url": "apps/alisa0808--vox-director.html",
    "coverage": "complete",
    "paid": false,
    "source": "research/verified/alisa0808--vox-director.json"
  }
}