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/crazynomad/skills --skill disk-cleaner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。
Generate images (Nano Banana Pro / Imagen) and videos (Veo 3.1) through Google Flow using the account's Ultra/Pro SUBSCRIPTION credits instead of the metered Gemini/Vertex API — no per-call API cost. Use when the user wants to create a thumbnail, cover, poster, b-roll clip, image, or short video with AI and wants to avoid API billing, or explicitly mentions Flow / gflow / Veo / Nano Banana via subscription. Wraps the gflow-cli tool; encodes this machine's Flow new-UI quirk (PREFER_CLASSIC) and credit-safe retry rules learned the hard way. NOT for the paid Gemini-API nano-banana-pro path (that costs money) — this is the subscription path.
Decide whether a task in the current project is worth running as an agent loop. Analyzes the repo for evidence first (tests/CI/bench scripts = available verifiers; issue+PR queues = recurring work; module boundaries), then interviews the user one question at a time on the genuine decisions, and returns one of three verdicts — don't loop (stay in the loop yourself), timer loop (/loop, /schedule), or goal loop (/goal) — with cited evidence and, when looping is warranted, a drafted four-part contract (goal / verification / boundary / stop) bound to real commands found in the repo. Recommending NO loop is a first-class outcome. Use when the user asks 值不值得 loop / should I loop this / 要不要上 /goal / 这个活能不能挂个循环自动跑, or wants to apply loop engineering to a project.
GitHub backlog governance manager-loop. Triage open issues (type + routing labels), complete thin descriptions, maintain a bounded ready queue (Todo ≤ 5) on a GitHub Projects board, and repair board drift (closed issue still "In Progress" etc.). Config-driven — reads .claude/backlog-manager.yaml from the target repo; runs an init flow to generate it if missing. DRY-RUN by default, pass "apply" to execute writes. Use for recurring backlog grooming / issue triage of any GitHub repo, standalone or driven by /loop. Requires gh CLI with repo + project scopes.
基于 SOC 职业分类
正在显示 SKILL.md
| name | disk-cleaner |
| description | Mac 智能磁盘清理助手,基于 Mole (https://github.com/tw93/Mole) 的用户友好包装器 |
基于 Mole (https://github.com/tw93/Mole) 的用户友好包装器,负责「安装 + 执行 + 解释 + 把关 + 指路 + 统计 + 分享」。
Disk Cleaner 是对 tw93 开发的 Mole 清理工具的增强封装。它提供了更友好的中文界面、分类报告、三档清理策略(Air/Pro/Max)、CSV 完整清单、白名单配置,以及清理完成后的精美成就页面(包含省钱计算和趣味统计)。
Use this skill when users:
python scripts/mole_cleaner.py --check
python scripts/mole_cleaner.py --preview # 终端文本报告
python scripts/mole_cleaner.py --preview --html # HTML 报告(自动打开浏览器)
python scripts/mole_cleaner.py --preview --csv # CSV 完整清单(保存到桌面)
python scripts/mole_cleaner.py --preview --json # JSON 格式输出
python scripts/mole_cleaner.py --clean --tier air --confirm # Air: 最安全
python scripts/mole_cleaner.py --clean --tier pro --confirm # Pro: 推荐
python scripts/mole_cleaner.py --clean --tier max --confirm # Max: 最大化
python scripts/mole_cleaner.py --clean --confirm # 默认全量清理
python scripts/mole_cleaner.py --whitelist --show # 查看当前白名单
python scripts/mole_cleaner.py --whitelist --preset office # 添加白领办公预设
python scripts/mole_cleaner.py --whitelist --preset developer # 添加开发者预设
python scripts/mole_cleaner.py --whitelist --add ~/Documents/重要项目 # 添加自定义路径
python scripts/mole_cleaner.py --status
python scripts/mole_cleaner.py --show-achievement
首先检查 Mole 是否已安装:
python scripts/mole_cleaner.py --check
如果未安装,引导用户安装或使用 --auto-install。
运行预览获取分析报告:
python scripts/mole_cleaner.py --preview
根据预览结果,向用户展示清理方案:
请选择你想执行的方案:
1. 🌬️ Air - 最安全,只清浏览器和日志 → X.XX GB
2. ⚡ Pro - 推荐,平衡安全与空间 → X.XX GB
3. 🚀 Max - 最大化释放硬盘空间 → X.XX GB
4. 📋 先看完整清单 - 生成 CSV 详细列表
5. ⚙️ 配置白名单 - 保护特定路径
选择 1-3 (Air/Pro/Max):
# 确认后执行
python scripts/mole_cleaner.py --clean --tier air --confirm # 或 pro/max
选择 4 (CSV 清单):
python scripts/mole_cleaner.py --preview --csv
告知用户文件已保存到桌面并自动打开。
选择 5 (白名单配置): 展示预设选项:
office: 白领办公 - 保护 .doc, .docx, .xls, .xlsx, .ppt, .pptx, .pdf 等developer: 开发者 - 保护代码和配置文件media: 媒体创作 - 保护视频、音频、图像项目python scripts/mole_cleaner.py --whitelist --preset office
# 或添加自定义路径
python scripts/mole_cleaner.py --whitelist --add ~/Documents/重要项目
清理完成后自动生成成就页面,包含:
--confirm 才执行清理~/.config/mole-cleaner/logs/| 档位 | 清理范围 | 风险等级 |
|---|---|---|
| 🌬️ Air | 浏览器缓存、系统日志 | 低风险 |
| ⚡ Pro | Air + 用户应用缓存、包管理器缓存、废纸篓 | 中等风险 |
| 🚀 Max | 所有可清理项目 | 较高风险 |
| 预设 | 保护内容 |
|---|---|
| office | 办公文档 (.doc, .docx, .xls, .xlsx, .ppt, .pptx, .pdf, .pages, .numbers, .key) |
| developer | 代码和配置 (.py, .js, .ts, .go, .rs, .java, .swift, .json, .yaml, .toml) |
| media | 媒体项目 (.psd, .ai, .sketch, .fig, .aep, .prproj, .fcpx, .mov, .mp4) |
brew install tw93/tap/mole)pip install jinja2~/.config/mole-cleaner/
├── logs/ # 操作日志
├── reports/ # HTML 报告
└── achievements/ # 成就页面
~/Desktop/
└── mole-clean-list-YYYYMMDD-HHMMSS.csv # CSV 完整清单