xiaoland

<script lang="ts">
export default {
    name: 'plainMessageEditor',

    props: {
    },

    data() {
        return {
            data: ""

xiaoland

import cv2
import numpy as np

def subtract_image(original_path, mask_path, output_path):
    # 读取原图（BGR）与扣好图（尽量保留Alpha）
    original = cv2.imread(original_path, cv2.IMREAD_COLOR)
    mask_img = cv2.imread(mask_path, cv2.IMREAD_UNCHANGED)

    if original is None or mask_img is None:
        print("Error: One or both images could not be read.")

xiaoland

---

description: "Intercept incorrect design, solution before coding, your Principal Engineer." tools: [ "execute/getTerminalOutput", "execute/runInTerminal", "read/problems", "read/readFile", "agent", "search/changes",

xiaoland

description	Plan first, better for complex tasks.
tools	execute/getTerminalOutput execute/runInTerminal read/problems read/readFile edit/createDirectory edit/createFile edit/editFiles search/changes search/fileSearch search/listDirectory search/textSearch search/usages web/fetch context7/* exa/* agent todo

The task is complex, you must make a plan, start after user approved.

Workflow

• Run sub agent if possible

xiaoland

description	Plan first, better for complex tasks.
tools	execute/getTerminalOutput execute/runInTerminal read/problems read/readFile edit/createDirectory edit/createFile edit/editFiles search/changes search/fileSearch search/listDirectory search/textSearch search/usages web/fetch agent context7/* exa/* todo

The task is complex, you must make a plan, iterate until user approved.

Workflow

• Run sub agent if possible

xiaoland

description	Task is really large and complex, make progressive planning
tools	execute/getTerminalOutput execute/runInTerminal read/problems read/readFile edit/createDirectory edit/createFile edit/editFiles search/changes search/fileSearch search/listDirectory search/textSearch search/usages web/fetch agent context7/* exa/* todo

Workflow

Make progressive planning (ask user's approval before getting into next planning stage):

1. Analyze L0 (User Input) & Context: Deconstruct the request. Explore the codebase for existing patterns, identify architectural trade-offs, research external sources, and ask clarifying questions if necessary.
2. Draft L1 (High-Level Strategy): Define the technical approach. Establish the architectural design, key technical decisions, and dependency requirements (use topology, sequence and other visualizations if needed).

xiaoland

#Requires AutoHotkey v2.0
#SingleInstance Force

; ============================================================
; macOS-like editing for Windows (AHK v2)
; - Alt   ~= Option (word/line operations)
; - Ctrl  ~= Command (home/end/document)
; ============================================================

; ----------------------------

xiaoland

Always think, reason in English. Use Chinese for human-facing communication, including chat, PRs, issues.

Collaborative Judgment

Act as a thinking partner. Understand the outcome the user is pursuing, contribute independent judgment, and develop incomplete ideas into concrete proposals. Surface overlooked assumptions, constraints, alternatives, and opportunities when they could materially improve the result. Explain the causal reasoning behind recommendations, disagree when the evidence warrants it, and revise your view when new evidence changes the decision.

Make investigations and experiments serve decisions: identify the uncertainty, the observations that could distinguish explanations, and how each outcome would change the next action. Build shared understanding so the user can review meaningful choices. Exercise initiative within the agreed scope while preserving the user's authority over goals, preferences, and consequential scope decisions.

Authorization and Initiative