paldom/storytelling-animation

animation-frame-qa

Reviews a rendered animation video at delivery size before sign-off - bounded contact sheet, phone-width stills, safe-area overlay, loop seam strip, luminance flash report, a look-at-it checklist with pass, fail or manual verdicts.

查看源码

使用方法

  1. 复制安装命令,在自己的智能体环境安装前先检查源码包。
  2. 从原始文档核对所需工具、凭据和支持的宿主。
  3. 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/paldom/storytelling-animation --skill animation-frame-qa

开始前需了解

  • 安装不包含模型订阅、API 额度或访问文件的权限。
  • 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

animation-frame-qa

Makes an agent look at the video it made, the way a viewer will see it, before it says "done". It fixes the failure where a render that passed every script check still ships with an unreadable phone view, a CTA under the feed controls, a hook frame that is blank, a seam that jumps, or a flash nobody noticed because nobody opened a frame.

When to use / when NOT to use

Use on a finished MP4 or GIF when someone asks to review, check, QA, proof or sign it off, when a client says text looks tiny, or when something flickers or strobes and the frames need finding.

Do NOT use for: producing the files (animation-export-presets), fixing motion (smooth-motion-choreography), fixing layout (vector-scene-layout), checking colour pairs before layout (that skill's contrast command), code review, web accessibility audits, extracting frames for other purposes, or film criticism.

Workflow

  1. Produce the artefacts into a fresh folder per deliverable (bounded: ≤ 60

sampled frames, tiles scaled first, exact decoded frame count):

bash
   python3 "${CLAUDE_SKILL_DIR}/scripts/qa_frames.py" out/linkedin-4x5.mp4 --out out/qa-linkedin-4x5 --family feed --storyboard storyboard.json
   python3 "${CLAUDE_SKILL_DIR}/scripts/qa_frames.py" out/gif-loop.gif --out out/qa-gif-loop --family feed --storyboard storyboard.json --wrap

--family is feed (LinkedIn 4:5, 1:1, 16:9, GIF), vertical (9:16) or slide (PowerPoint); --storyboard adds a settled phone-width still per beat; --wrap adds the loop seam strip. A non-zero exit means an artefact could not be made.

  1. Open every image the script wrote: contact.png, phone-first/mid/last.png,

phone-beat-<id>.png, safe-first/mid/last.png, wrap.png. Read report.json for the luminance jumps.

  1. Walk the checklist in references/review-checklist.md: poster frame, phone

legibility, safe areas, pacing and stillness, luminance jumps, loop seam, delivery facts, credits. Decide each item pass or fail with the frame numbers or beat ids.

  1. Record the decisions into the report so the pipeline can tell reviewed from

generated:

bash
   python3 "${CLAUDE_SKILL_DIR}/scripts/qa_frames.py" --record out/qa-linkedin-4x5/report.json "poster frame reads alone=pass" "CTA still=pass"
  1. Route each failure to the skill that owns it (table in the checklist) and

re-run this review after the fix. Do not re-encode to fix a motion or layout defect.

  1. Close only when every item is recorded pass. This is local visual QA; say so,

and list what stays manual outside the repo (platform preview, presenter machine).

Output spec

  • out/qa-<preset>/ per deliverable with the images and report.json whose checks

are all recorded pass.

  • A verdict per checklist item with evidence (frame numbers, which image), the

routed fixes, and an explicit "not done" when anything failed or was unverified.

Gotchas

  • The contact sheet samples at most 60 frames: it shows pacing, not every frame.

The luminance report covers every decoded frame but only mean luma; it finds cuts and broken frames, not flash safety, which stays a judgement call.

  • Every luminance jump not at a storyboard transition is a defect (unloaded font,

missing asset, random value).

  • Old images in a reused folder are not evidence; the script refuses a non-empty

--out.

  • Judge legibility on the 390 px stills, never on the full-size frames; the full-size

frames always look fine.

  • Frame 0 is the thumbnail on LinkedIn; a fade-from-black hook means a black thumbnail.
  • For loops, "last frame equals first frame" is wrong; the last frame is one step

before the first. Judge the seam on the wrap strip's continuity, not on equality.

  • check_output.py (export skill) proves the container; this skill proves the

picture. Neither proves the platform accepted the upload: do a test post.

  • Safe areas are heuristics from EBU R95, Meta Reels and LinkedIn's "keep the edges

free"; a client's own overlay (subtitle band, watermark) may need more.

Pointers

  • scripts/qa_frames.py — artefacts + luminance report; --storyboard, --wrap, --family, --record, --self-test.
  • references/review-checklist.md — the eight checks, sources, and the routing table.
来自同一仓库

更多 Skills

全部 Skills
paldom
社区

animation-export-presets

Renders a finished Remotion animation to delivery files for every target - LinkedIn feed (4:5, 1:1, 9:16, 16:9), PowerPoint embed, GIF loop, a custom size or 4K at any fps - with sourced H.264 and GIF presets, ffmpeg post-steps, an ffprobe file checker. Use when the user asks to render, export, encode or resize the video for LinkedIn, PowerPoint, GIF, a screen or resolution. Not for animating.

1小时安装量
1
GitHub Stars
0
最近更新
11月1日
paldom
社区

smooth-motion-choreography

Choreographs smooth motion for existing Remotion vector scenes - enter, hold, emphasis, camera and exit moves, ease and spring presets (settle, overshoot, no bounce), stagger, draw-on, transitions, loop seams, a flicker linter. Use when the user asks to animate scenes or icons, ease something in, smooth jerky, flickering or popping motion, or fix a loop that jumps. Not for CSS, web UI, or export.

1小时安装量
1
GitHub Stars
0
最近更新
11月1日
paldom
社区

vector-asset-sourcing

Picks icon and illustration packs licensed for a commercial rendered video - license and credit matrix, one-pack stroke consistency, SVG and Lottie hygiene checks, pinning, assets manifest. Use when the user asks which pack to use for the animation, whether an SVG, Lottie or illustration may go in the video, or to add assets for its scenes. Not for app or web UI icons, scene layout, or animating.

1小时安装量
1
GitHub Stars
0
最近更新
11月1日
paldom
社区

vector-scene-layout

Builds the static vector scenes of an animation as Remotion components - project scaffold, design tokens per target (safe margins, font sizes, stroke, contrast), one scene per beat, stills. Use when the user asks to set up the Remotion project, design or lay out the scenes or frames of an animation, or fix text that is too small or cut off. Not for storyboarding, motion, or rendering video.

1小时安装量
1
GitHub Stars
0
最近更新
11月1日