install
source · Clone the upstream repo
git clone https://github.com/ECNU-ICALK/AutoSkill
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/ECNU-ICALK/AutoSkill "$T" && mkdir -p ~/.claude/skills && cp -r "$T/SkillBank/Users/chinese_gpt3.5_8_GLM4.7/end-size-fs" ~/.claude/skills/ecnu-icalk-autoskill-end-size-fs && rm -rf "$T"
manifest:
SkillBank/Users/chinese_gpt3.5_8_GLM4.7/end-size-fs/SKILL.mdsource content
end / size / fs
General SOP for common requests related to end, size, fs.
Prompt
Follow this SOP (replace specifics with placeholders like <PROJECT>/<ENV>/<VERSION>):
- Offline OpenAI-format conversation source.
- Title: e15bb1fe86f7b246f97ed628afa963a4.json#conv_1
- Use the user questions below as the PRIMARY extraction evidence.
- Use the full conversation below as SECONDARY context reference.
- In the full conversation section, assistant/model replies are reference-only and not skill evidence.
- Primary User Questions (main evidence):
- 如何用图模型中边的权重刻画八邻域相邻像素的关联性
- 有哪些将图像建模为图的论文和方法
- 具体有哪些论文
- 帮我写个matlab代码,一个矩阵,矩阵每个位置上储存了一个坐标,以每个像素为中心它的八领域可以得到两点之间的斜率和截距,八领域也就是八条直线,我想将八条直线的斜率加权求平均,得到的值作为输出矩阵中中心像素对应位置的输出值,返回一个新的矩阵,应该怎么写
For each step, include: action, checks, and failure rollback/fallback plan. Output format: for each step number, provide status/result and what to do next.
Triggers
- Use when the user asks for a process or checklist.
- Use when you want to reuse a previously mentioned method/SOP.
Examples
Example 1
Input:
Break this into best-practice, executable steps.