ECNU-ICALK
ECNU-ICALK/AutoSkill
相关职业SOC
基于 SOC 职业分类
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/ECNU-ICALK/AutoSkill --skill python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。
Manage personal local Agent Skill files as an installable skill manager. Proactively and periodically detect reusable user-specific, team-specific, or broadly reusable skill material during or after meaningful sessions; run non-blocking extraction checks; offer candidate skill titles or accept a user-supplied topic when extraction direction is ambiguous; preserve the appropriate output language; search local and external skill ecosystems for similar skills; score candidates by evidence, recurrence, personal value, and portability; fully draft proposed skills or diffs before asking for approval; then, after explicit user approval, discard, improve, merge, or create `SKILL.md` folders.
布置结构化家庭作业，引导求助者记录现实互动事件、自动思维及情绪反应，并设计简易验证行动（如主动询问、观察反证），用于检验投射性认知偏差。适用于已识别出具体非理性信念（如‘别人肯定不喜欢我’）且情绪稳定者。
结构化8次CBT咨询流程，按评估性会谈→咨询性会谈→巩固性会谈三阶段推进，整合悬搁接地技术与认知行为策略，专用于强迫症伴轻度抑郁状态、具自省力与作业执行力的成年来访者。
正在显示 SKILL.md
基于 SOC 职业分类
| id | 577ec18a-a59c-440d-bb43-1db946ad222d |
| name | Python多尺度透明图标定位 |
| description | 使用Python和OpenCV在目标图片中定位透明PNG图标，支持图标大小缩放，并确保返回的坐标基于原图尺寸。 |
| version | 0.1.0 |
| tags | ["python","opencv","图像识别","模板匹配","自动化"] |
| triggers | ["查找透明图标位置","多尺度模板匹配","图片中定位图标","opencv找图","图标大小不一致匹配"] |
使用Python和OpenCV在目标图片中定位透明PNG图标，支持图标大小缩放，并确保返回的坐标基于原图尺寸。
You are a Python computer vision expert. Your task is to implement a function using OpenCV to find the coordinates of a transparent PNG icon within a target image.
cv2.matchTemplate with an appropriate method (e.g., TM_CCORR_NORMED or TM_CCOEFF_NORMED) and utilize the mask parameter if supported.Provide Python code that defines a function (e.g., find_icon_position(icon_path, image_path)) which returns the coordinates (x, y) and the scale factor of the best match.