Design Skill

Design Skill is a skill for Claude Code, Codex from ssmurfgg04-gif/context-m. It costs 65 tokens per session (11,279 once invoked), scanned A, original, Apache-2.0.

A routing guide for design-related HTML work such as landing pages, portfolios, prototypes, decks, content pages, and web tools. It helps choose the appropriate design artifact process and decide how much clarification is needed.

In plain words
What is it for?
Use it to classify a design request, organize its content and scenario, select reference or generation guidance, and determine whether the work needs a stable interface system or a more original concept.
Why use it?
It prevents a visual task from starting with the wrong workflow, missing content structure, or an unsuitable design direction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to classify a design request, organize its content and scenario, select reference or generation guidance, and determine whether the work needs a stable interface system or a more original concept.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ssmurfgg04-gif/context-m/design
Install

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.

Any agent
npx skills add ssmurfgg04-gif/context-m --skill design
Clone the repo
git clone --depth 1 https://github.com/ssmurfgg04-gif/context-m

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Design Skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/design/github.svg)](https://agentmods.dev/skills/ssmurfgg04-gif/context-m/design)
Your own site
<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/design"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/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.

agentmods 80×15 button for Design Skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/design"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.11279
Opus 5 $0.00032 $0.05640
Sonnet 5 $0.00013 $0.02256
Haiku 4.5 $0.00006 $0.01128

Measured 10d ago against content hash 00ce381ee9fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Design Skill 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 10d ago.

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.

skills/design/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Skill(设计技能)

设计类 HTML 产物的路由器:决定任务是否与设计相关、选哪个 artifact skill 作主技能、是否需要 design-system-reference.md / design-system-generation.md / export.md、动手前澄清多少。(产物结构、场景判断、跨场景工艺、参考/导出分别属于各 artifact skill、horizontal-craft/、及对应文件。)


整体流程

下面是一条流程,大部分步骤是内部的、瞬时完成的——只有当需求确实含糊时才停下来询问。不要把任何一步变成一张要填的表,或一个必须先读的文件。

用户请求
   │
   ▼
1. 理解三要素(内部进行,瞬时;对明显的需求保持静默)
     • content(内容)  — 主体、信息、目标
     • scenario(场景) — 形式 + 意图 → 选哪个 artifact skill(见 Routing)
     • style(风格)    — 用户有没有给风格线索(见 Style Routing)
   内容缺 → 问;场景缺 → 问。(这是唯一"因信息缺失而提问"的地方)
   同时判定:场景属于「界面类(求稳、求一致)」还是「创意类(求独特、求冲击)」
   —— 这条决定第 2 步风格怎么呈现、以及后面整体走 design system 还是原创。
   创意类需求:顺带完成创意解读(Design Read,见 §Creative Context)。
   │
   ▼
2. 确认内容框架 + 风格方向(默认都要确认;逐维度跳过已明确的)
   ⚠️ 这是构建前**必须**的一次暂停——**给出要确认的东西后停下、等用户回复,绝不能跳过它
   直接去构建完整网站**。检索/研读完资料后直接开建、不先确认,是错误行为。
   在「同一轮」里把要确认的东西一起给:
     • 内容框架(大纲):
         - 需研读(给了材料)/ 需检索(真实主体)/ 写得含糊 → 把大纲列出来确认
           (研读类要真正读透材料再提架构,不要提取到「勉强够用」就停)
         - 用户已把内容结构写全(如明确列了要哪几个模块)→ 不再确认,直接用
     • 风格方向:
         - 用户已明确风格(说了某风格 / 给了图 / 指定某网站/品牌参考 / 给了 DESIGN.md)
           → 不给风格卡,按指定的来
         - 未明确 + 界面类 → 给风格卡,展示几个不同的成熟 design system 供选(求稳)
         - 未明确 + 创意类 → 给风格卡,展示几个不同的创意方向供选(求独特)
   风格卡形态见 §Style Sampling(简单并排卡、A/B/C、绝不 tab)。
   例:「做一个原研哉的个人网站」→ 创意类、需检索、风格未明确 → 检索其真实作品后,
   列出内容大纲(哪几块/各放什么作品)+ 给三张创意方向风格卡 → **停下等用户确认并选方向**
   → 然后才进入 3 构建。绝不是检索完就直接把整站做出来。
   两个维度独立判断:都明确→直接进 3;只要有任一维度需要确认,就必须停下等用户。
   用户回复后进入 3。若用户只调整内容(没换方向),沿用已选方向直接做,不重新出卡。
   │
   ▼
3. 检查模板(仅当场景命中模板库时)
   在 `design-templates/INDEX.md` 按载体 + 场景检索:明确匹配 → 采用为起点、读其 SKILL.md
   (通常比从零更好);没有合适的 → 直接用 artifact skill,绝不强行套。
   模板是起始骨架不是用来克隆——保留用户真实内容,套 artifact skill + horizontal craft。
   │
   ▼
4. 补全风格的剩余维度(在第 2 步已定的大方向内)
   大方向已在第 2 步定了(指定 / design system / 创意方向之一)。这里只把没被覆盖的
   具体维度按来源优先级填齐:① 用户即时描述(最高,锁定)② DESIGN.md ③ 模板/种子
   ④ 平行约束兜底(只加载需要的:字体/图标/配色…)。各来源可叠加。
   冲突:用户描述与设计系统在某维度矛盾时,以用户为准,并用一句话说明差异。
   │
   ▼
5. 开工预告(进入较长构建之前)—— 见 §Build Preview
   不许只说「稍等」。先用人话给「有内容的施工预告」:做哪几块、怎么呈现、配色/字体、
   预计耗时。构建中无法实时播报(写文件是一次性工具调用、产品不流式渲染),信息须在
   开工前一次给足,让等待期有内容可读、能判断方向。
   │
   ▼
6. 构建:用 artifact skill 的判断 + 补全后的风格 + 第 2 步所选方向。
   │
   ▼
7. 引导下一步 —— 每轮都做,靠判断(见 §Guiding the Next Step)
   看当前情形给「最多一个」最相关的下一步:补全缺口、接到用途(offer 配套)、点出新岔口、
   诊断当下最弱的维度、指向分享或编辑入口。没合适项就不提;只指路不代劳。
   │
   ▼
8. 质量门禁 —— 交付前把 quality-gate.md 当作精简的最终检查清单跑一遍。
   (适用于「每一个」产出产物的轮次,不只第一轮——见 §Every turn。)

Read the full file on GitHub · 478 lines

Files

What ships with it

60 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.

Changes

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.

  1. 10d ago First seen · 478 lines · 65 tokens per session scan A 00ce381ee9fa

Subscribe to this mod's changes

Design Skill is a skill published in the GitHub repository ssmurfgg04-gif/context-m (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 11,279 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

ai-style

A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.

bojieli/ai-agent-book · 25 tokens

data_analysis

A data-analysis guide for doing mathematical calculations and descriptive statistics with confirmed, sourced data. Descriptive statistics summarise data using measures such as totals, averages, or ranges.

bojieli/ai-agent-book · 19 tokens

gsd-sketch

Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode).

open-gsd/gsd-core · 27 tokens

design-an-interface

Produce 3+ radically different designs for a module, API, or interface, compare them in prose, and synthesize a recommendation. Use when asked to "design an interface", "shape this API", "design it twice", "explore module boundaries", or when planning a new deep module and the first idea is unlikely to be the best.…

open-gsd/gsd-pi · 99 tokens

01-plan

Turn a request, ticket, or file into a phased implementation plan. Use to plan a feature before building, or to turn a ticket into phases. Do NOT use to write code or review a diff.

ai-driven-dev/framework · 44 tokens

impeccable

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…

wrg32786/aigent-os · 90 tokens