用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/InugamiDev/ultrathink-oss --skill skill-creator命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Unified design foundations — design system architecture, tokens, component specs, visual principles, creative vision, figma integration, plus brand design system loader (66 real brands via DESIGN.md). Absorbs design, design-system, design-systems, design-principles, design-router, creative-vision, figma, design-md.
Render, summarize, and present markdown documents and structured content in multiple output modes
Ultra UI skill - combines Google's DESIGN.md spec (machine-readable design tokens) with the ui-ux-pro-max knowledge base (91 styles, 161 palettes, 73 font pairings, 161 products, 104 UX guidelines, 25 chart types). Generates lint-clean DESIGN.md files, validates token references and WCAG contrast, exports Tailwind/DTCG tokens, and diffs design systems version-over-version.
基于 SOC 职业分类
正在显示 SKILL.md
| name | skill-creator |
| description | Meta-skill for creating, validating, and maintaining UltraThink skill definitions |
| layer | utility |
| category | meta |
| triggers | ["create skill","new skill","add skill","skill template","define skill"] |
| inputs | [{"skill_name":"Identifier for the skill (kebab-case)"},{"description":"What the skill does"},{"layer":"hub | utility | domain"},{"category":"The skill's functional category"},{"domain_knowledge":"Core expertise the skill should encode"}] |
| outputs | [{"skill_definition":"Complete SKILL.md with frontmatter and body"},{"validation_report":"Frontmatter schema compliance check"},{"integration_map":"How the skill connects to existing skills"}] |
| linksTo | ["research","plan"] |
| linkedFrom | ["team","cook"] |
| preferredNextSkills | ["research"] |
| fallbackSkills | ["sequential-thinking"] |
| riskLevel | low |
| memoryReadPolicy | selective |
| memoryWritePolicy | selective |
| sideEffects | ["Creates new SKILL.md file","May update linksTo/linkedFrom in related skills"] |
Create new UltraThink skills that follow the established conventions, schema, and quality standards. This meta-skill ensures every new skill has proper YAML frontmatter, meaningful content, correct cross-references, and actionable guidance. It is the skill that makes skills.
LAYERS:
hub -- Orchestration skills that coordinate other skills (plan, cook, ship)
utility -- General-purpose tools usable across domains (error-handling, logging)
domain -- Deep expertise in a specific technology or area (react, postgresql)
SKILL FILE STRUCTURE:
.claude/skills/{skill-name}/SKILL.md
FRONTMATTER (YAML) -- Required Fields:
name (string, kebab-case)
description (string, one line, under 120 chars)
layer (hub | utility | domain)
category (string, grouping label)
triggers (array of activation phrases)
inputs (array of what the skill needs)
outputs (array of what the skill produces)
linksTo (array of skills this skill calls)
linkedFrom (array of skills that call this skill)
preferredNextSkills (recommended follow-up skills)
fallbackSkills (alternative skills if this one cannot handle the task)
riskLevel (low | medium | high)
memoryReadPolicy (none | selective | full)
memoryWritePolicy (none | selective | full)
sideEffects (array of side effects)
BODY (Markdown) -- Required Sections:
# [Skill Name]
## Purpose
## Key Concepts / Key Patterns
## Workflow or Patterns
## Best Practices
## Common Pitfalls
## Examples
CONTENT REQUIREMENTS:
- Minimum 100 lines of body content
- At least one code example with comments
- Best practices list with at least 5 items
- Common pitfalls table with at least 4 entries
- No placeholder text ("TODO", "TBD", "coming soon")
NAMING CONVENTIONS:
- Skill name: kebab-case (e.g., "error-handling", "react-native")
- Category: lowercase (e.g., "frontend", "ai-ml", "database")
- Trigger phrases: lowercase, natural language
Determine the layer:
hubutilitydomainDetermine the category:
database, frontend, security)Define the interface:
Map relationships:
---
name: {skill-name}
description: {One-line description under 120 chars}
layer: {hub | utility | domain}
category: {category}
triggers:
- "{skill-name}"
- "{trigger phrase 1}"
- "{trigger phrase 2}"
inputs:
- {input}: {description}
outputs:
- {output}: {description}
linksTo:
- {skill}
linkedFrom:
- {skill}
preferredNextSkills:
- {skill}
fallbackSkills:
- {skill}
riskLevel: {low | medium | high}
memoryReadPolicy: {none | selective | full}
memoryWritePolicy: {none | selective | full}
sideEffects: []
---
# {Skill Title}
## Purpose
{What this skill does and when to use it.}
## Key Concepts
{Core knowledge and decision frameworks.}
## Workflow
{Step-by-step process or reusable patterns.}
## Best Practices
1. **{Practice}** -- {Rationale}
## Common Pitfalls
| Pitfall | Impact | Fix |
|---------|--------|-----|
| {problem} | {consequence} | {solution} |
## Examples
### Example: {Use Case}
{Concrete example with code.}
| Pitfall | Impact | Fix |
|---|---|---|
| Stub skills with no content | Triggered but provides no value | Minimum 100 lines of body |
| Overlapping triggers | Wrong skill activated | Audit triggers for uniqueness |
| Missing cross-references | Skill graph incomplete | Update both linksTo and linkedFrom |
| Too broad scope | Skill tries to do everything | Split into focused skills |
| No examples | Users cannot understand usage | Add at least one concrete example |