Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YuDefine/nuxt-supabase-starter --skill design-retrogit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/design-retro)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/design-retro"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/design-retro/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/design-retro"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/design-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.02095 |
| Opus 5 | $0.00038 | $0.01047 |
| Sonnet 5 | $0.00015 | $0.00419 |
| Haiku 4.5 | $0.00008 | $0.00210 |
Grade A, and why
design-retro scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Retro
分析 Design Review 歷史發現，識別跨 spec 的重複問題模式，主動提出流程改善建議。
Prerequisites
本 skill 引用的 /impeccable audit / /impeccable layout / /impeccable harden 等指令來自 pbakaus/impeccable（對齊 design skill Prerequisites 當前鎖定版本，見 design/references/impeccable-install.md）。Consumer 必須先安裝對應版本，否則 retro 報告中的「建議動作」指令會無效。
觸發條件
自動觸發（由 proactive-skills.md 規則驅動）
- 收尾後觸發 — 一件工作標
work.done且它有 design review findings 時 - 累積門檻觸發 —
docs/design-review-findings.md新增記錄後，總 change 數達 5 的倍數（5、10、15…）
手動觸發
使用者執行 /design-retro 時。可選參數：
/design-retro— 分析全部歷史/design-retro last 3— 只分析最近 3 個 change
執行流程
Phase 1: 資料收集
- 讀取
docs/design-review-findings.md - 若檔案不存在或為空 → 回報「尚無 design review 記錄」→ 結束
- 解析所有 change 記錄，建立結構化資料：
- 每筆 finding 的類別、嚴重度、發現來源（哪個 skill 發現的）
- 按 change 時間排序
Phase 2: 模式分析
對收集到的資料執行以下分析：
2.1 頻率分析
按類別統計出現次數與佔比：
| 類別 | 次數 | 佔比 | 趨勢 |
|------|------|------|------|
| spacing | 14 | 30% | ↑ 連續 4 個 change 出現 |
| a11y | 9 | 19% | → 穩定 |
| color | 3 | 6% | ↓ 最近 3 個 change 未出現 |
趨勢判定：
↑— 最近 3 個 change 中出現 ≥ 2 次→— 穩定出現但無明顯增減↓— 最近 3 個 change 中未出現
2.2 嚴重度分析
| 嚴重度 | 次數 | 佔比 |
|--------|------|------|
| critical | 5 | 11% |
| warning | 30 | 64% |
| info | 12 | 25% |
2.3 來源 skill 分析
統計哪個 design skill 發現最多問題：
| 發現來源 | 次數 | 常見類別 |
|---------|------|---------|
| /impeccable audit | 15 | a11y, color |
| /impeccable layout | 10 | spacing, layout |
| /design improve | 8 | consistency |
2.4 熱點頁面分析
統計哪些頁面/元件反覆出現問題：
| 頁面/元件 | 出現次數 | 主要類別 |
|-----------|---------|---------|
| pages/admin/projects.vue | 4 | spacing, layout |
| components/DataTable.vue | 3 | a11y, responsive |
Phase 3: 問題診斷
根據 Phase 2 的數據，診斷根因並分為三個層級：
層級 A：規劃期缺陷（Propose 階段該攔住）
問題在 propose 階段就能預防，但 spec 沒有涵蓋。
判定條件：
- 同類別問題在 ≥ 3 個 change 中重複出現
- 問題屬於可預測類型（spacing、layout、typography、consistency）
改善方向：在 /specify 產出的規格模板加入 design checklist
層級 B：實作期缺陷（Apply 階段該攔住）
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -2 lines b69d96eea497
- 4d ago Changed · +4 lines · +4 tokens per session 7e49ba9fac55
- 8d ago First seen · 208 lines · 72 tokens per session scan A 1d9b52b454b0
design-retro is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,095 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
slides
Build a Grida slides deck — a .canvas bundle in slides mode whose pages are SVG documents (16:9, one SVG per slide). Use when creating a presentation, pitch deck, slideshow, or talk.
dotcanvas
Author and edit a Grida .canvas board — a .canvas.json manifest plus document files (references, generated images, notes) placed on an infinite canvas. Use when working on a .canvas bundle or arranging visuals/design work spatially. For a linear deck/presentation, use the slides skill instead.
svg
Author and edit .svg files in a Grida editor session — live-canvas binding, SVG output style, and parse-error recovery. Use when creating or modifying an SVG document.
before-after
Produce a before/after visual comparison of an evlog surface (landing, docs, telemetry, playgrounds) and share it as public Blob URLs. Load when a change is visual, when someone asks for screenshots or a visual diff, or when a shipped PR touches apps/docs or apps/telemetry and deserves visual evidence.
nw-fp-usable-design
Naming conventions, API ergonomics, and usability patterns for functional code.
nw-design-methodology
Apple LeanUX++ design workflow, journey schema, emotional arc patterns, and CLI UX patterns. Load when transitioning from discovery to visualization or when designing journey artifacts.