360 Secure SkillHub
360 安全技能中心

Psd Automator Screenshot

通过截图与中文指令定位 PSD 文本图层并派发自动改字:高置信度自动执行,中置信度返回候选图层供确认;依赖 psd-automator 核心管线,采用 OpenClaw 命令派发,并将调用与执行记录到 skills-usage.json。

dhrxy
dhrxy
热度 66.21
最近更新 2026-05-11 17:29:05
分类:创作依赖:MCP 服务 / 内部调用大模型应用场景:品牌素材 / 工作流

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add psd-automator-screenshot
Metadata
name
psd-automator-screenshot
description
Use screenshot + natural language instruction to locate PSD text layers and dispatch automated edits with confidence gating. Requires psd-automator core.
metadata
{"openclaw":{"userInvocable":true,"commandDispatch":"tool","commandTool":"psd_automator_screenshot","commandArgMode":"raw"}}

psd-automator-screenshot

This skill dispatches screenshot-driven PSD text updates while keeping the existing psd-automator execution pipeline.

Preferred command

Use the built-in command first:

/main-image-editor <agentId> <中文需求> --screenshot ~/Desktop/修改3.png

Use /psd-automator-screenshot only when you need backward-compatible command behavior.

Usage

/psd-automator-screenshot <agentId> <截图改字指令>

Example:

/psd-automator-screenshot design-mac-01 找到banner.psd或banner.psb,将红框区域替换成"限时199元",保持字体和字号不变

Notes

  • High confidence requests are auto-dispatched.
  • Medium confidence requests return top candidates for confirmation.
  • Every invocation/execution is recorded to skills-usage.json.