القائمة
يُحدَّد Prompt الذي يراجع المصدر أولًا بشكل افتراضي. يمكنك التبديل إلى أمر مباشر أو تنزيل نسخة محلية.
اقرأ SKILL.md وأي ملفات مرافقة يعرضها SkillsMP قبل أن تقرر التثبيت.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/dvcrn/openclaw-skills-marketplace --skill mini-swe-agentيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
监控 OpenClaw GitHub 版本更新，获取最新版本发布说明，翻译成中文， 并推送到 Telegram 和 Feishu。用于：(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
استنادا إلى تصنيف SOC المهني
عرض SKILL.md
| name | mini-swe-agent |
| description | mini-swe-agent |
Run complex software engineering tasks autonomously using the mini-swe-agent CLI.
Use this skill when the user asks to fix a bug, implement a feature, or resolve a GitHub issue that requires end-to-end codebase exploration and editing. This acts as a "sub-contractor" to do the heavy lifting for complex tasks.
When a complex coding task is requested, formulate a concise, descriptive problem statement and run the mini CLI using a bash tool.
mini --yolo "Fix the authentication logic in /src/auth.py to ensure tokens expire after 3600 seconds"
Rules
Autonomy: Always use the --yolo flag so the agent runs autonomously without waiting for user input.
Formatting: Escape double quotes inside the problem statement if necessary.
Verification: Monitor the output. Once mini finishes, verify the changes if requested by the user.
Scope Limitation: Do NOT use this for simple one-line text replacements or minor typo fixes. Use standard file editing tools for those to save time and compute.
---
### 2. How to Build/Install It
Instead of creating it manually, you can run this single command in your terminal. It will create the necessary OpenClaw skills directory (if it doesn't already exist) and write the `SKILL.md` file directly into it.
```bash
mkdir -p ~/.openclaw/skills/mini-swe-agent && cat << 'EOF' > ~/.openclaw/skills/mini-swe-agent/SKILL.md
# mini-swe-agent
Run complex software engineering tasks autonomously using the mini-swe-agent CLI.
## Description
Use this skill when the user asks to fix a bug, implement a feature, or resolve a GitHub issue that requires end-to-end codebase exploration and editing. This acts as a "sub-contractor" to do the heavy lifting for complex tasks.
## Usage
When a complex coding task is requested, formulate a concise, descriptive problem statement and run the `mini` CLI using a bash tool.
` ` `bash
mini --yolo "Fix the authentication logic in /src/auth.py to ensure tokens expire after 3600 seconds"
` ` `
## Rules
* **Autonomy:** Always use the `--yolo` flag so the agent runs autonomously without waiting for user input.
* **Formatting:** Escape double quotes inside the problem statement if necessary.
* **Verification:** Monitor the output. Once `mini` finishes, verify the changes if requested by the user.
* **Scope Limitation:** Do NOT use this for simple one-line text replacements or minor typo fixes. Use standard file editing tools for those to save time and compute.
EOF