Token导航 LogoToken导航

Agent Skill · 研究检索

visual-concept(视觉概念)

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

visual-concept 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为需要联网;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 5,684。

总安装 24,747周安装 1,063GitHub Stars 公开资料未说明下载 8,674核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:visual-concept(视觉概念)
来源仓库:https://github.com/leegitw/visual-concept
安装命令:
openclaw skills install visual-concept
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install visual-concept

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

visual-concept 将技术见解转化为视觉概念指南,包括符号图像和视频创意。适合产品策划阶段提供视觉灵感支持。通过 clawhub 安装,命令为 openclaw skills install visual-concept。输出内容应结合实际项目背景,避免脱离上下文的抽象建议。

适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install visual-concept;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

visual-concept 怎么安装?

在终端执行 openclaw skills install visual-concept。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

visual-concept 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

visual-concept 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

visual-concept 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

visual-concept 用的人多吗?

公开数据是累计安装 24,747 次,近一周安装 1,063 次,下载 8,674 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

visual-concept 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
visual-concept

视觉概念 · 本页

24,747—需要联网MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
visual-concept
version
1.0.1
description
Transform technical insights into visual concept guides — symbolic imagery, color arcs, and creative direction for video
author
Live Neon <hello@liveneon.ai>
homepage
https://github.com/live-neon/skills/tree/main/creative/visual-concept
repository
leegitw/visual-concept
license
MIT
tags
[creative, visual, video, concept-art, storyboard, direction, synthesis, reflection, imagery]
layer
creative
status
active
alias
vc
user-invocable
true
emoji
🎬

visual-concept (映)

Transform technical conversations and insights into visual concept guides. Creates conceptual inspiration for music videos or visual content — symbolic imagery, color palette evolution, and thematic direction without prescriptive shot lists.

Trigger: 明示呼出 (explicit invocation) or when deep technical insight emerges

Core insight: "Visual metaphors make abstract concepts tangible. The right image can convey what words cannot."

Installation

openclaw install leegitw/visual-concept

Dependencies: None (standalone creative skill)

Data handling: This skill synthesizes content from user-supplied input or the current conversation context (default). It does NOT read files from the workspace or access project artifacts directly. Results are returned to the invoking agent, who decides how to use them.

What This Solves

Technical concepts are abstract. Visual representation makes them memorable and shareable. This skill:

  1. Translates technical concepts into visual metaphors
  2. Creates color arcs that match emotional journeys
  3. Provides creative direction without constraining execution

The insight: A well-chosen visual metaphor (trace IDs as golden threads, errors as cracks in glass) communicates instantly what paragraphs cannot.

Usage

/vc [topic]

Arguments

ArgumentRequiredDescription
topicNoTopic focus (default: synthesize current conversation)

Pre-Requisites

Before creating a visual concept, ensure:

  1. Sufficient conversation depth — Surface-level topics don't inspire visuals
  2. Clear narrative arc — Problem → Discovery → Solution → Impact
  3. Main work documented — Save current progress first if mid-task

Context Understanding Checklist

You must be able to answer:

QuestionWhat It Means
Core insight?Not "we talked about X" but "we discovered X solves Y"
Problem solved?The pain point, not just the topic
Why, not just what?The reasoning, not just the outcome
Visual potential?Can this be represented symbolically?

Red Flags (Don't Create)

  • Surface-level summary of conversation
  • Don't understand why a decision was made
  • Insight is purely procedural with no visual metaphor
  • No clear emotional arc to visualize

Output Format

Visual Concept Guide Structure

## Visual Concept Guide

**Core Visual Concept**: [Primary metaphor in one sentence]

### Visual Themes & Imagery
[3-7 major themes, conceptual not prescriptive]

### Symbolic Visual Elements
[How technical concepts become visual symbols]

### Emotional Color Arc
[Color palette evolution matching emotional journey]

### Typography & Text Elements
[If applicable, style of any on-screen text]

### Motion & Rhythm
[Movement patterns, pacing notes]

### Key Visual Contrasts
[Before/after, chaos/order, dark/light]

Visual Guide Rules

RuleDescription
Conceptual inspirationNOT a shot list or scene breakdown
NO specific durationsDon't say "5 seconds on X"
NO camera anglesDon't prescribe "wide shot" or "close-up"
NO literal breakdownDon't number scenes sequentially
Provide directionGive creative directors a north star, not constraints

Example: Good vs Bad

Bad (too prescriptive):

Scene 1 (0:00-0:05): Wide shot of server room, camera slowly zooms in
Scene 2 (0:05-0:10): Close-up of blinking lights, pan left to right

Good (conceptual):

Core Visual Concept: Darkness giving way to illumination

Visual Themes:
- Isolation in darkness (before observability)
- Golden threads appearing (trace IDs connecting)
- Gradual dawn (understanding emerging)

Color Arc:
- Opens in deep blues and blacks
- Warm gold appears as connections form
- Ends in clear, bright tones

Core Logic

Step 1: Synthesize Conversation

  • Read full conversation context
  • Identify key decisions, "aha" moments
  • Extract core insight or pattern

Step 2: Identify Narrative Arc

ElementQuestion
ProblemWhat was broken/painful?
DiscoveryWhat did we learn?
SolutionWhat pattern emerged?
ImpactWhy does this matter?

Step 3: Find Visual Metaphors

Think about:

  • What does the problem LOOK like? (chaos, darkness, fragmentation)
  • What does the solution LOOK like? (order, light, connection)
  • What symbols represent the key concepts?
  • What color palette matches the emotional journey?

Step 4: Write Concept Guide

Include:

  • Core visual concept (one sentence)
  • 3-7 visual themes
  • Symbolic elements for technical concepts
  • Color arc (start → middle → end)
  • Motion and rhythm notes
  • Key contrasts

Example

Input: Bootstrap Observability Insight

Context: Discovered reproduce-to-debug problem. Introduced Bootstrap → Learn → Enforce phases.

Narrative arc:

  • Problem: Debugging without reproduction is impossible
  • Discovery: Greenfield systems don't know what "normal" is
  • Solution: Bootstrap → Learn → Enforce phases
  • Impact: Debug with sight instead of in darkness

Output

Core Visual Concept: From blindness to sight — darkness giving way to illuminated pathways

Visual Themes & Imagery

  1. The Void — Empty black space representing systems without observability
  2. Scattered Sparks — Data points appearing, unconnected
  3. Golden Threads — Trace IDs weaving connections between sparks
  4. The Pattern Emerges — Threads form a recognizable structure
  5. Dawn Breaking — Full illumination, the system becomes visible
  6. The Watchtower — Elevated view of the now-visible landscape

Symbolic Visual Elements

ConceptVisual Symbol
Trace IDsGolden threads connecting points
ErrorsRed fractures or cracks
BaselinesHorizontal reference lines, like horizon
Bootstrap phaseSeeds planted, construction scaffolding
EnforcementSolid walls, protective barriers

Emotional Color Arc

  • Opening: Deep blues, blacks — isolation, confusion
  • Middle: Warm golds emerging — discovery, connection
  • Climax: Bright whites and golds — clarity, understanding
  • Resolution: Balanced palette — sustainable, calm confidence

Motion & Rhythm

  • Opens slow, contemplative (lost in darkness)
  • Accelerates with discovery (threads appearing rapidly)
  • Peaks with revelation (burst of light)
  • Settles into steady rhythm (system functioning)

Key Visual Contrasts

BeforeAfter
DarknessLight
ScatteredConnected
ChaosPattern
BlindnessVision
IsolationNetwork

Integration

  • Layer: Creative
  • Depends on: None (standalone)
  • Used by: side-quests (combo skill)
  • Complements: insight-song, ted-talk

Failure Modes

ConditionBehavior
Insufficient contextAsk clarifying questions first
No clear narrative arcDecline, explain what's missing
Purely procedural insightSuggest finding visual angle first

Security Considerations

Input sources:

  • User-supplied context (if provided)
  • Current conversation context (default)

What this skill does NOT do:

  • Read files from the workspace
  • Access project artifacts directly
  • Send data to external services
  • Call image generation APIs

Output behavior: This skill returns the visual concept guide directly to the invoking agent. The agent can then display, save, or pass the result to another skill as needed.

Provenance note: This skill is developed by Live Neon (https://github.com/live-neon/skills) and published to ClawHub under the leegitw account. Both refer to the same maintainer.

Quality Checklist

  • [ ] Can explain core insight in one sentence
  • [ ] Core visual concept is clear and evocative
  • [ ] 3-7 visual themes identified
  • [ ] Technical concepts have symbolic representations
  • [ ] Color arc matches emotional journey
  • [ ] NO prescriptive shot lists or durations
  • [ ] Could guide a creative director without constraining them

Acceptance Criteria

  • [ ] /vc synthesizes input or conversation into visual concept guide
  • [ ] Output includes core concept, themes, symbols, color arc
  • [ ] Guide is inspirational, not prescriptive
  • [ ] Technical concepts translated to visual metaphors
  • [ ] Result returned to invoking agent

*Part of the Live Neon Creative Suite.*

平台分布

OpenClaw

74.9%
按下载量换算6,497

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills