メニュー
Use when UI changes must be proven safe across breakpoints using baseline and diff workflows. AE.LTD visual quality gate for release confidence.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/aegntic/cldcde --skill ae-ltd-visual-regression-forgeコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
SOC 職業分類に基づく
Run a 5-adviser council to stress-test any decision. Five distinct lenses (Contrarian, First-Principles, Expansionist, Outsider, Executor) answer independently, then anonymously peer-review each other, and a Chairman synthesizes a single clear recommendation. Kills sycophancy and groupthink on high-stakes calls.
Diligence-grade product and technical analysis for the ae.ltd proof-agent concept, including comparison against Cursor and Omnara, MVP and production architecture, red-team review, and build-vs-buy evaluation. Use when Codex needs to create or critique PRDs, tech specs, competitive diligence, leadership memos, or multi-agent evaluation packs for agent-runtime, demo-agent, or proof-agent products.
Use when creating or upgrading CLAUDE.md instructions and selecting the right template baseline for repo size, architecture, and team constraints. AE.LTD template decision workflow.
| name | ae-ltd-visual-regression-forge |
| description | Use when UI changes must be proven safe across breakpoints using baseline and diff workflows. AE.LTD visual quality gate for release confidence. |
Proves UI changes are safe across breakpoints using baseline and diff workflows. Visual quality gate for release confidence. Niche gem source: visual-regression plugin from awesome-claude-code-toolkit.
User: "Did my CSS change break anything?"
→ Define scope → Capture baseline → Run diff → Report pass/fail
Define snapshot scope. Pick critical pages/components and three base viewports: mobile, tablet, desktop.
Capture clean baselines. Wait for network idle and mask dynamic regions.
Capture current state with matching settings. Use identical viewport/device/browser settings for comparability.
Run diff and classify. Compute pixel deltas and mark pass/warn/fail against threshold.
Convert failures into actionable fixes. Map each diff to CSS/layout/asset causes and patch.