メニュー
Validates a generated piece against platform technical specs for aspect ratio, resolution, duration, file size, and codec
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host supports hooks (Claude, Cursor); otherwise self-paces via the host scheduler. The older /simplicio-tasks surface is a legacy alias; never escape the loop with a false promise.
Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.
One-shot bootstrap skill that wires HyperFrames (https://github.com/wesleysimplicio/hyperframes) into a marketing-engine clone as a first-class video provider — the three runtime skills, the provider class + mock, the routing matrix rows, env vars, and CLAUDE.md updates. Idempotent. Invoke when a fresh clone needs HyperFrames added, or when reapplying the integration after a rebase that dropped any piece of it.
Runs the HyperFrames CLI dev loop — init, lint, inspect, preview, render — for compositions authored under the `hyperframes` skill. Invoked after the composition HTML is on disk and before the piece is marked complete.
Translates a marketing-engine piece brief into the input shape the `hyperframes` skill expects (composition spec) and the flags the `hyperframes-cli` skill needs to render it. Selected by `video-prompt-builder` when the routing matrix resolves to the `hyperframes` provider.
Author HTML-as-source-of-truth motion compositions (kinetic type, motion quote cards, programmatic data-viz reels) for the HyperFrames renderer. Used whenever the video provider resolved by the routing matrix is `hyperframes`.
| name | qa-tech-specs |
| description | Validates a generated piece against platform technical specs for aspect ratio, resolution, duration, file size, and codec |
| version | 0.1.0 |
Pre-publish validator for asset technical compliance. Reads platform specs from .specs/product/CHANNELS.md and compares them to the actual file metadata. Blocks publishing when a critical spec is violated.
adaptlypost or any direct platform API..specs/sprints/sprint-XX/.asset_path: string. Local path or URL to the file.asset_kind: string. image, video, carousel, audio.target_platforms: array of strings. Subset of ig_feed, ig_reel, ig_story, tiktok, youtube_shorts, youtube_long, facebook_feed, linkedin, x.channels_md_path: string, optional. Override path to .specs/product/CHANNELS.md.channels_md_path (default .specs/product/CHANNELS.md) and parse the spec table for each platform: aspect ratio, min and max resolution, max duration, max file size, accepted codec, accepted container.ffprobe for video and identify for image. Extract aspect ratio, resolution, duration, file size, codec, container.target_platform, compare actual values against the spec and record violations.hard (platform will reject) versus soft (platform will accept but quality drops).hard violation appears, set the overall pass flag to false.pass: boolean. False if any hard violation exists.per_platform: object. Map of platform -> { pass, violations, fixes }.metadata: object. The actual file metadata extracted.Input: { asset_path: "outputs/quote-card.png", asset_kind: "image", target_platforms: ["ig_feed", "ig_reel"] }
Output: { pass: false, per_platform: { ig_feed: { pass: true, violations: [], fixes: [] }, ig_reel: { pass: false, violations: [{ rule: "aspect_mismatch", expected: "9:16", actual: "1:1", severity: "hard" }], fixes: ["regenerate at 1080x1920 or center-crop with safe area"] } }, metadata: { width: 1080, height: 1080, format: "png", file_size_kb: 412 } }
Input: { asset_path: "outputs/reel-001.mp4", asset_kind: "video", target_platforms: ["tiktok", "youtube_shorts"] }
Output: pass true, both platforms accept the file.
soft and recommend a re-encode.caption-multi-platform: caption side of the same publish gate.wavespeed-batch: produces batch assets that should be validated by this skill.topview-prompt-builder: produces UGC video that often needs spec validation.higgsfield-prompt-builder: produces cinematic video that may need a re-encode pass.