메뉴
Use when designing Clash media storage, asset registry rows, analysis metadata, immutable media references, copy-on-write behavior, rights metadata, or how image/video/audio/text assets map to canvas paths.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user wants to read, modify, search, add, or delete nodes on a project's canvas. Triggers on "canvas", "scene", "node", "add a clip", "edit the timeline", "what's in the canvas", "rearrange", "remove the X". Use the `clash canvas` CLI subcommands; always pass `--json` for parseable output.
Use when the user wants to list, switch, create, inspect, or delete Clash projects. Triggers on "project", "switch project", "open project", "new project", "delete project", or any reference to a project by name. Use the `clash projects` CLI subcommands.
Use when the user wants to cut, trim, split, reorder, or add media to a Project Timeline, or change its fps or composition size. Round-trip the Timeline through timelines/<id>.timeline.yaml with public `clash timeline list`, `pull`, and `apply` commands.
Use when the user wants to read, modify, search, add, or delete nodes on a project's canvas. Triggers on "canvas", "scene", "node", "add a clip", "edit the timeline", "what's in the canvas", "rearrange", "remove the X". Use the `clash canvas` CLI subcommands; always pass `--json` for parseable output.
Use when the user wants to list, switch, create, inspect, or delete Clash projects. Triggers on "project", "switch project", "open project", "new project", "delete project", or any reference to a project by name. Use the `clash projects` CLI subcommands.
AI video production with the Clash platform. Use this skill whenever the user mentions Clash, video projects, canvas editing, image/video generation, storyboards, or wants to create visual content. Also use when the user asks about managing Clash projects, tokens, or CLI setup.
| name | asset-metadata-architecture |
| description | Use when designing Clash media storage, asset registry rows, analysis metadata, immutable media references, copy-on-write behavior, rights metadata, or how image/video/audio/text assets map to canvas paths. |
Use this skill when a workflow needs media or analysis files to become durable project entities. The purpose is to keep agent-editable files useful without letting agents bypass canvas, CRDT, rights, or lineage rules.
Model these as first-class project entities:
asset: image, video, audio, text, SVG, Lottie, caption, overlay, export.analysis: transcript, beat grid, shot list, scene tags, image consistency.plan: storyboard, cut list, shot list, prompt pack, MG overlay plan.projection: CAS-protected timeline/canvas/text file.reference: public source URL, brand file, competitor example, raw footage.assets/
originals/
generated/
clips/
overlays/
exports/
analysis/
audio/
transcript/
video/
image/
plans/
cut-plans/
storyboards/
prompt-packs/
rights/
sources.json
Every asset-like file should be representable as:
{
"id": "asset-id",
"projectId": "project-id",
"kind": "image | video | audio | text | caption | overlay | export | reference",
"path": "assets/generated/example.mp4",
"source": { "type": "generated | imported | derived | public-reference" },
"lineage": { "parents": [], "operation": "string" },
"rights": { "license": "unknown", "sourceUrl": null, "allowedUses": [] },
"analysis": [],
"createdBy": "user | agent | system"
}
Call out missing media.asset-registry, media.analysis-store,
media.copy-on-write, and media.rights-ledger explicitly. Do not hide them
inside workflow prose.