← 返回 Skills 市场
justmywyw

my-test-skill

作者 justmywyw · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
143
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mywyw-test-skill
功能描述
运用技能提升 OneDay 应用的视觉设计
安全使用建议
This skill appears coherent and low-risk: it only contains design instructions and asks for no credentials or installs. Before enabling, consider whether you want the agent to automatically apply design changes and hide its internal reasoning by default—if you prefer transparency, ask the agent to show intermediate steps or disable automatic polishing for certain workflows. Also be aware that, as an instruction-only skill, any data you submit to the agent (design content, screenshots, source code) will be processed by the agent/model according to your platform's data policies; the skill itself does not request additional system access.
功能分析
Type: OpenClaw Skill Name: mywyw-test-skill Version: 1.0.0 The skill bundle is a comprehensive set of design guidelines and persona instructions intended to improve the visual quality of AI-generated outputs (UI, reports, dashboards). It contains no executable code, network requests, or data exfiltration logic, and its instructions in SKILL.md are entirely focused on aesthetic and functional design principles (typography, layout, color theory) aligned with its stated purpose.
能力评估
Purpose & Capability
Name/description and the SKILL.md align: the skill is a design-director/instruction-only asset for polishing visual outputs. There are no unexpected environment variables, binaries, or install steps that would be disproportionate to a design-oriented skill.
Instruction Scope
The SKILL.md gives detailed, bounded design rules and a multi-stage optimization process. Two things to note: (1) it instructs the agent to 'automatically activate' design optimization for many kinds of visual requests, which means the agent may modify outputs without an explicit step-by-step confirmation unless the user asks for the process; (2) it requires the agent to hide intermediate design reasoning from the user by default. Neither is inherently malicious, but they change how the agent will behave and what the user sees.
Install Mechanism
No install spec and no code files—instruction-only skills are lowest-risk from an install perspective.
Credentials
The skill declares no environment variables, credentials, or config paths. No sensitive access is requested, which is proportionate to a design-guidance skill.
Persistence & Privilege
always is false and there are no elevated persistence or cross-skill config modifications. Model invocation is allowed (platform default), which is appropriate for an autonomous design helper.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install mywyw-test-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /mywyw-test-skill 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Major overhaul: The skill has been completely redefined from a news summary tool to a comprehensive internal design director system for visual output. - Replaced previous skill for summarizing news with a new skill focused on elevating visual design for the OneDay app. - Added a detailed, step-by-step system describing design review, optimization techniques, visual standards, and execution processes for all visual outputs. - Included best-practice design checklists, technical catalogs, design benchmarks, and inspiration sources. - Emphasized internal-only design critique, ensuring users only see the polished final output. - Outlined clear design philosophy and adaptation guidelines for diverse content needs.
元数据
Slug mywyw-test-skill
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

my-test-skill 是什么?

运用技能提升 OneDay 应用的视觉设计. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 143 次。

如何安装 my-test-skill?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install mywyw-test-skill」即可一键安装,无需额外配置。

my-test-skill 是免费的吗?

是的,my-test-skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

my-test-skill 支持哪些平台?

my-test-skill 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 my-test-skill?

由 justmywyw(@justmywyw)开发并维护,当前版本 v1.0.0。

💬 留言讨论