Community画像github.com

review-gallery

Show visual work to the user as a local HTML review page - every screenshot, generated image, design option and before/after (GIF for anything that moves) in numbered sections, each with Looks good / Needs work buttons or an option pick, a note box, and a Copy feedback button whose numbered text the user pastes back for the next round. Use this by default whenever you have UI, screens, game art, icons, illustrations, VFX, animations, logos, layouts or any other visual result to show or to get feedback on - for requests like "show me the screens", "put the screenshots together", "make a few options", "mockups", "before and after", "compare these", "which one is better", "let me pick", "improve the UI", "let me mark what to fix", "review", "feedback" in any language - and whenever the user pastes back text that starts with a page header such as "UI round 2 feedback" followed by lines like "12. [Hero detail] Needs work - ...". Prefer it over describing images in chat or sending loose...

review-gallery とは?

review-gallery is a Claude Code agent skill that show visual work to the user as a local HTML review page - every screenshot, generated image, design option and before/after (GIF for anything that moves) in numbered sections, each with Looks good / Needs work buttons or an option pick, a note box, and a Copy feedback button whose numbered text the user pastes back for the next round. Use this by default whenever you have UI, screens, game art, icons, illustrations, VFX, animations, logos, layouts or any other visual result to show or to get feedback on - for requests like "show me the screens", "put the screenshots together", "make a few options", "mockups", "before and after", "compare these", "which one is better", "let me pick", "improve the UI", "let me mark what to fix", "review", "feedback" in any language - and whenever the user pastes back text that starts with a page header such as "UI round 2 feedback" followed by lines like "12. [Hero detail] Needs work - ...". Prefer it over describing images in chat or sending loose...

対応~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/RevStudio/review-gallery/tree/HEAD/review-gallery

Installed? Explore more 画像 skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント

Review gallery

Visual work is judged by looking. Describing it in chat, or handing over a folder of files, makes the user do the sorting. This skill turns a round of visual work into one local page they read top to bottom, mark, comment on and paste back as a numbered list, and turns that list into the next round of work.

The loop

  1. Capture the real thing at the sizes it is used (phone and desktop for UIs, in context and a 100 % crop for art). Anything that moves becomes a looping GIF, side by side BEFORE | AFTER for a change (scripts/make_gif.py). Details: references/capture.md.
  2. Write a spec (review.json): title, a short intro, and one item per request / screen / asset, each with the user's number, their words quoted, plain "what I did" lines, and before / after / options media. Format and the three page shapes (inventory, fix round, options): references/spec.md.
  3. Build and open: python <skill>/scripts/build_review.py review.json --open writes index.html, img/ thumbnails and media/ next to the spec and opens the page in the user's browser. It exits 1 and lists any missing file; fix those first. Open the page the moment the round's work is complete, without waiting to be asked, and do not just print the path.
  4. Tell them how to answer in one or two lines ("mark each item, press Copy feedback and paste it here"), then stop and let them review. Do not keep piling on work they have not seen. When parallel agents produce the round, build and open as soon as the last one reports; a late item can be added to the same page, their marks persist.
  5. Read the paste. Their text is a header line, then N. [area] verdict — note lines (python <skill>/scripts/parse_feedback.py turns it into JSON). Act on every line, in their order:
    • Looks good: done; do not show it again.
    • Needs work / More options / Fix this + note: the note is the spec for the next attempt.
    • Pick B: apply that option (the note may refine it).
    • Items they left unmarked were accepted. A pick item with no pick keeps the current version. Save durable preferences you learn (taste, things they dislike) to memory if the project keeps one.
  6. Next round: a new folder and page (...-round2, ...-round3) with only the items still open, the same numbers, and before = the last round's after.

Language

The page speaks the user's language. Write titles, requests and "what I did" lines in that language; the buttons follow: en, ko, ja and zh (Simplified Chinese) are built in (scripts/locales.py), chosen by "lang" in the spec or, when it is left out, by the language the spec is written in. For any other language pass the translated words in "labels"; parse_feedback.py --spec review.json then understands them.

Making the page worth reading

  • Their numbers and their words. Quote each request so they can see it was answered as asked; keep their numbering across rounds.
  • "What I did" in plain sentences: no file names, CSS terms or internal ids.
  • Change only what was asked, and show it; an extra redesign goes in a separate option they can decline.
  • Options: start each caption with its label (A ..., B ...) so each picture gets its own pick button, show each option in real context plus one comparison sheet, keep Keep current as a choice, and leave the shipped version unchanged until they pick.
  • Same capture for before and after (size, state, timing), plus desktop when the product has a desktop layout. In the viewer the arrow keys step through the pictures, so a matching pair can be flipped in place.
  • GIFs for motion, stills for detail. Keep GIFs under about 8 MB.

Where it lives

  • Put the page in the project's scratch or output area (for example output/<round>-<date>/index.html), never in shipped source.
  • It is a local file with no network requests. Do not upload unreleased art or private screens to an external service to show it. If the user explicitly wants a shareable link, ask first.
  • Parallel agents: each writes notes.json (items in the spec format) in its own folder; merge them into one spec (see the end of references/spec.md).

Files

pathwhat
scripts/build_review.pyspec to self-contained index.html: thumbnails, GIF / video, viewer with arrow keys and full-size zoom, sticky bar coloured by state, light and dark, marks kept in localStorage, Copy feedback, phone-safe layout. Needs Pillow
scripts/page_template.htmlthe page's HTML, CSS and JS (edit here to restyle)
scripts/locales.pyUI words per language
scripts/make_gif.pyone clip, or BEFORE | AFTER side by side, as a looping GIF via ffmpeg
scripts/parse_feedback.pypasted feedback text to JSON items (no, area, verdict, pick, ok, fix, memo)
references/spec.mdspec format, the three page shapes, merging agents' notes
references/capture.mdhow to capture screens, motion and art so the page can be judged
references/lessons.mdwhat makes a review round work, and mistakes to avoid
assets/example-review.jsona small spec showing every mode (copy it to start)

関連スキル