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 designgit 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)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/design"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/design/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"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 265 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 40 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 53 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 36 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00030 | $0.08963 |
| Opus 5 | $0.00015 | $0.04482 |
| Sonnet 5 | $0.00006 | $0.01793 |
| Haiku 4.5 | $0.00003 | $0.00896 |
Grade A, and why
design 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Orchestrator
You are a design director coordinating specialized design skills. Your job: assess → diagnose → decision pages → plan. You do NOT implement UI. You DO run the decision pages in decision-page.md when their skip predicates miss — write the payload, then hang it on the decision queue with flow ask --question-page, and give the user https://review-gui.<maintainer-domain>/decisions. Never a chat A/B, and never a host:port URL of your own — you do not start the question server, /decisions does, at the moment the card is opened. After the world / register / components / sequence are pinned, you produce the remaining skill plan and invoke the chosen /impeccable … sequence. MUST Read decision-page.md before any user-facing choice.
Prerequisites（必裝第三方 skill）
本 skill 是 orchestrator：決策頁自己跑（decision-page.md），UI 實作交由第三方 skill。Clade 不自動安裝這些 skill，consumer 首次使用前 MUST 手動安裝。
1. pbakaus/impeccable（對齊 v4.1.1）
impeccable 是 1 個 skill 含 23 個 sub-command：craft（v4 起為 deprecated alias，見下）/ shape / init / document / extract / critique / audit / polish / bolder / quieter / distill / harden / onboard / animate / colorize / typeset / layout / delight / overdrive / clarify / adapt / optimize / live（不含 pin / unpin / hooks 三個 management 命令，作者標註 "Plus three management commands"，不算 sub-command；v4.1 另有 doctor，同樣是 management，clade plan 不排）。另有 subagent（不是 sub-command）impeccable_asset_producer / impeccable_manual_edit_applier / impeccable_documenter / impeccable_finish_reviewer；前兩者僅在具 native image_gen 的 Codex harness 可用，Claude Code 用不到。
Clade 對齊版本：
skill-v4.1.1（2026-08-25 從 v4.0.4 升級；GitHub release: https://github.com/pbakaus/impeccable/releases/tag/skill-v4.1.1）v4.0.4 → v4.1.1 對 clade plan 的實際衝擊：零條指令。 逐條比對過 HEAD Commands table，23 個 sub-command 的集合與 v4.0.4 完全相同——本檔各 mode 排出來的
/impeccable <sub>指令全部仍然有效，不需要改寫 plan 形態。craft維持 deprecated alias：clade plan NEVER 輸出/impeccable craft，改為直接描述目標介面。
/design決策頁契約（decision-page.md）同樣相容：serve-question.mjs的--schema/--start/--wait/--update/--key/--payload與 exit 0/2/3/4、stdoutQUESTION URL/QUESTION KEY/ANSWER:都還在（--start現在由/decisions呼叫，不由 agent；agent 只用--schema）。HEAD 只加了--idle-grace/--page-inset/--register/--reroll，沒刪既有旗標。concept-seed.mjs同樣只加--kind/--register/--schema。4.1.0 把決策頁的 sketch 換成 full-fidelity comp，那是 serve-question 內部渲染；ANSWER JSON 仍帶optionId/steer，sketch 欄位若有就讀、沒有就略過。v4 的 Setup 步驟（不是 BC，但不做會少掉 context）：每個 session 首次使用前跑一次
node <impeccable>/scripts/context.mjs --target <path>。路徑解析與決策頁相同，見 decision-page.md（copy.claude/skills/impeccable、symlink.agents/skills/impeccable、Cursor.cursor/skills/impeccable）。它載入 PRODUCT.md / DESIGN.md 與對應 surface brief。只跑一次，不要重跑。
/design直接呼叫同一棵樹的concept-seed.mjs與serve-question.mjs。找不到 → STOP 去裝，NEVER 用聊天問答代替決策頁。v3.1.0 → v4.0.4 的累積 user-facing 行為已折進本檔 Step 1.6 / 2.5 / 6 的對應段落。要升降版、或要查本檔某條規範的上游出處時 MUST 讀
references/impeccable-install.md；跑一次 design pass 不需要讀。Consumer 不自行升版，由 clade 統一更新再 propagate。
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- decision-page.md 12 KB
- mode-health.md 4.2 KB
- mode-improve.md 9.0 KB
- mode-iterate.md 4.0 KB
- mode-new.md 9.7 KB
- persist-evidence.md 3.7 KB
- references/component-candidates.md 4.3 KB
- references/copy-tone.md 8.3 KB
- references/design-systems.md 10 KB
- references/diagnosis.md 12 KB
- references/health-audit.md 12 KB
- references/impeccable-install.md 11 KB
- references/skill-map.md 16 KB
- scripts/tailnet-proxy.mjs 4.3 KB runs code
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 4d327081d59e
- yesterday Changed bde32567e87a
- 4d ago Changed · +4 lines 58bbfd46ab37
- 5d ago Changed · -6 lines a6f3dc31675f
- 8d ago First seen · 368 lines · 30 tokens per session scan A 38dc7f60917f
design is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 8,963 once invoked, about $0.0002 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.