القائمة
Use before claiming a video export is done; validates rendered outputs, duration, fps, dimensions, audio, captions, safe areas, packshot/end card, rights, and source references.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | video-release-checkpoint |
| description | Use before claiming a video export is done; validates rendered outputs, duration, fps, dimensions, audio, captions, safe areas, packshot/end card, rights, and source references. |
Use this skill as the final QA gate.
Check:
For TVC/ad delivery variants, extract audited PPM frame samples from the rendered export, generate local pixel evidence, normalize visual evidence, then use the managed receipt command:
clash production extract-ad-visual-frames \
--target-asset asset-tvc \
--delivery-spec projections/delivery/asset-tvc.delivery-spec.json \
--variant tiktok-9x16-15s \
--rendered exports/tiktok-15s.mp4 \
--packshot-frame 390 \
--end-card-frame 420 \
--final-frame 449 \
--out-dir analysis/visual/frames \
--manifest analysis/visual/tiktok-15s.frame-extraction.json \
--json
clash production analyze-ad-visual-pixels \
--target-asset asset-tvc \
--delivery-spec projections/delivery/asset-tvc.delivery-spec.json \
--variant tiktok-9x16-15s \
--rendered-path exports/tiktok-15s.mp4 \
--packshot-frame analysis/visual/frames/packshot.ppm \
--packshot-color "#f04a2a" \
--end-card-frame analysis/visual/frames/end-card.ppm \
--final-frame analysis/visual/frames/final.ppm \
--out analysis/visual/tiktok-15s.pixel-evidence.json \
--json
clash production plan-ad-visual-qa \
--target-asset asset-tvc \
--delivery-spec projections/delivery/asset-tvc.delivery-spec.json \
--variant tiktok-9x16-15s \
--evidence analysis/visual/tiktok-15s.pixel-evidence.json \
--out actions/ad-visual-qa.json \
--report qa/visual/tiktok-15s.visual-qa.json \
--json
clash production validate-ad-delivery-export \
--delivery-spec projections/delivery/asset-tvc.delivery-spec.json \
--variant tiktok-9x16-15s \
--rendered exports/tiktok-15s.mp4 \
--visual-report qa/visual/tiktok-15s.visual-qa.json \
--out qa/delivery/tiktok-15s.validation.json \
--json
If --probe is omitted, the command probes the rendered file with ffprobe.
Use --probe analysis/probe/<variant>.probe.json when another renderer has
already produced a trusted media probe. The receipt is a release gate; it does
not automatically perform OCR/logo/loudness analysis. Local ffmpeg frame
extraction can produce PPM samples from rendered video; local PPM pixel analysis
covers packshot color sampling, end-card sample readability, and final-frame
hold checks. OCR/logo/loudness or non-PPM image decoding must still be supplied
as visual QA evidence or kept blocked for review.
Do not call an export complete without a receipt.