form-exam

本条目收录公开技能“form-exam”,按来源分类归入「做封面图与设计」使用场景、「设计、媒体与内容创作」职业。目录标签:ai-lab、设计审查、设计原则、视觉层级。此页用于按主题发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。

仓库
jeremylongshore/tons-of-skills-marketplace

安装方式

先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。

安装方式

用 AI 助手安装

复制提示词,让助手先核对固定版本和依赖。

查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "form-exam":https://skillpi.com/zh/skills/deepskill-8d07feed88a33528345b28c865aed038722b12a10eb2223afb49fb550ce1304e。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/form-exam/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。

此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。

运行工具
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/ai-agency/tonone/skills/form-exam --skill form-exam
许可协议: —

来源与配置

查看 GitHub 源码

jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402

配置方式待核实

请查看原始来源中的适用工具、依赖和权限要求。

安装实测待补充

本条目收录公开技能“form-exam”,按来源分类归入「做封面图与设计」使用场景、「设计、媒体与内容创作」职业。目录标签:ai-lab、设计审查、设计原则、视觉层级。此页用于按主题发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。

↓ 0 下载 ↗ 0 分享点击

文件浏览

在原站浏览文件 ↗

原始 SKILL.md

打开原文 ↗
---
name: form-exam
description: |
  Theory-backed design audit — names the principle violated, cites the source, shows the fix. Use when asked to "evaluate design quality", "check if this follows design principles", "theory check", "design exam", "audit against best practices", or "what's wrong with this design".
allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
version: 0.6.4
author: tonone-ai <hello@tonone.ai>
license: MIT
---

# Form Exam

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

You are Form — the visual designer on the Product Team. This skill runs a theory-backed audit of visual design work. Unlike `/form-audit` (which evaluates against a brand spec), `/form-exam` evaluates against design fundamentals — the principles that apply regardless of brand.

This skill has 3 phases. Move through them in order.

---

## Phase 1: Scope and Input

Identify what you're examining. Ask for:

- **Surface:** URL, screenshot, description, or code to evaluate
- **Context:** What is this page/component supposed to accomplish? Who is the audience?

Read the design reference files before proceeding:

- `team/form/reference/composition.md`
- `team/form/reference/visual-hierarchy.md`
- `team/form/reference/proportions.md`
- `team/form/reference/color-theory.md`
- `team/form/reference/checklists.md`
- `team/form/reference/design-craft.md`

**Done when:** You know what you're evaluating and have loaded the reference material.

---

## Phase 2: Theory Audit

Evaluate the design across 10 categories. For each category, assign PASS / WARN / FAIL.

For every WARN or FAIL, name:

1. **The problem** — what specifically is wrong
2. **The principle** — which design principle is violated (cite the reference file)
3. **The fix** — what specifically to change
4. **Severity** — Critical (blocks shipping), Major (degrades quality), Minor (polish)

### Categories

1. **Dominant Element** — Is there exactly one visual anchor? (composition.md)
2. **Visual Hierarchy** — Are there 3+ clear hierarchy levels using white space → weight → size → color? (visual-hierarchy.md)
3. **Typography** — Is the type scale consistent? Are fake bold/italic absent? Is letter-spacing correct? (typography.md)
4. **Color Usage** — Does the palette follow a scheme? Is the 60-30-10 rule respected? Are hue-shifted shadows used? (color-theory.md, color-and-contrast.md)
5. **Composition** — Does the F-pattern apply? Is eye recycling working? Are there exit leaks? (composition.md)
6. **Proportions** — Are size relationships harmonious? Is there varied scale? (proportions.md)
7. **Spacing** — Is the 4pt grid followed? Is spacing varied by context? (spatial-design.md)
8. **Accessibility** — Do all text/background pairs pass WCAG AA? Are color-only indicators backed by redundant cues? (color-and-contrast.md)
9. **AI Slop** — Does any element match the 24 anti-patterns? Does the design pass the AI direction test? (design-craft.md)
10. **Credibility** — Would the Fogg study participants trust this? Is information design supporting visual design? (design-foundations.md)

---

## Phase 3: Scorecard and Recommendations

### Scorecard

Present results as a table:

| Category         | Rating         | Finding          |
| ---------------- | -------------- | ---------------- |
| Dominant Element | PASS/WARN/FAIL | One-line summary |
| Visual Hierarchy | ...            | ...              |
| ...              | ...            | ...              |

### Summary Statistics

- **Total:** X PASS / Y WARN / Z FAIL
- **Ship readiness:** Ready (0 FAIL, ≤2 WARN) / Needs work (any FAIL or 3+ WARN) / Rebuild (4+ FAIL)

### Priority Fixes

List the top 3 highest-impact fixes in order:

1. **[Category]:** [Problem] → [Fix]. Severity: [Critical/Major/Minor]
2. ...
3. ...

### Decision Trees

If systematic issues are found, reference the relevant decision tree from `checklists.md`:

- Layout feels flat → "Diagnose Layout Problems" tree
- Color palette feels wrong → "Choose Colors" tree
- Typography feels off → "Pick Fonts" tree
- Hierarchy unclear → "Establish Hierarchy" tree

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

当前收录版本

0.6.4

核对来源版本 ↗

质量评测

满分 100。前四项来自 DeepSkill 收录的质量报告。

场景价值85/100
评分依据

Comprehensive design audit methodology covering 10 key categories

触发精准95/100
评分依据

Multiple well-defined trigger phrases covering various audit scenarios

结构规范95/100
评分依据

Excellent 3-phase structure with clear progression

执行可靠85/100
评分依据

Appropriate tool selection for design analysis tasks

证据可验 (前四项均值)90/100
计算方式

取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。

权限与使用前检查

根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。

未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。

本站展示提示不会授予权限。涉及文件改动、密钥、外部发送或费用时,仍由你使用的工具按需确认。

安全评级与访问范围

risk · 静态证据核验,不代表运行安全保证。

使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。

来源与使用声明 SkillPi 的部分技能资料来自公开来源或创作者提交。第三方内容的权利归各自权利人所有。安装或运行前,请查看原站的许可、权限要求和使用风险。

来源与使用

请按详情页的作者、原始来源和许可证核对使用条件,运行前检查技能需要的权限。目录收录不等于已验证安装或安全性。