Windows C盘清理和磁盘空间管理。当用户说C盘满了、磁盘空间不足、清理临时文件/缓存/回收站/系统日志、查找大文件、分析磁盘占用时使用。仅适用于 Windows 环境。不用于：macOS/Linux 磁盘清理、卸载软件（引导用户走系统卸载）、清理用户个人文件（只报告位置，删除决定权在用户）。
把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性，你确认后才安装。
读取 https://funcoding.ai/skills/staruhub/claudeskills/geek-skills-c-drive-cleaner/install.md ，按里面的步骤帮我安装这个 Skill。
安全导向的 Windows 磁盘清理：分析 → 模拟 → 执行 → 验证，破坏性操作永远先预览。
--execute 前用户明确确认过（清理不经过回收站，不可恢复）C:\Windows\System32 — 核心系统文件C:\Windows\WinSxS — Windows 组件存储（要瘦身走 DISM，不许直接删）C:\Program Files / C:\ProgramData — 已装程序及数据C:\Windows\Prefetch — 预读取文件，删了拖慢启动python scripts/analyze_disk.py C:\ 2 20 # 路径 深度 显示前N项
python scripts/find_large_files.py C:\ 100 50 # 路径 最小MB 最大结果数
python scripts/find_large_files.py C:\Users 200 100 .mp4,.avi,.mkv # 按类型过滤
常见大文件类型：视频 .mp4,.mkv,.mov；安装包 .iso,.exe,.msi；压缩包 .zip,.rar,.7z；备份 .bak,.sql。
python scripts/clean_temp.py # 模拟：只预览
python scripts/clean_temp.py --execute # 实际执行：需二次确认
覆盖范围：%TEMP%、C:\Windows\Temp、浏览器缓存（Chrome/Edge/Firefox）、.log/.etl/.old 日志、回收站。
重跑 analyze_disk.py，对比前后数字回报实际效果。
| 陷阱 | 具体表现 | 应对 |
|---|---|---|
| 无权限静默漏扫 | 非管理员运行，扫描结果偏小误导判断 | 提示以管理员身份运行；脚本会跳过无权目录并计数 |
| 浏览器缓存清理失败 | 浏览器进程占用文件 | 先关闭所有浏览器窗口再清 |
| 清完没效果 | 临时文件本来就不大，大头是个人文件或程序 | 回到大文件报告和目录排行,引导用户决策(卸载/转移) |
| 误以为可恢复 | 脚本删除不经回收站 | 执行前明确告知不可恢复,这也是模拟先行的原因 |
| SSD 清到贴满 | 追求 100% 利用率 | SSD 保留 15-20% 空间维持性能;低于 20% 时才建议清理 |
cleanmgr、存储感知、DISM 组件清理references/windows_cleanup_guide.md| 脚本 | 功能 | 安全特性 |
|---|---|---|
scripts/analyze_disk.py | 目录占用排行 + 大文件列表 | 只读；自动跳过无权目录 |
scripts/find_large_files.py | 按大小/类型查找文件 | 只读；显示访问时间辅助判断 |
scripts/clean_temp.py | 清理临时文件/缓存/日志/回收站 | 默认模拟；--execute 二次确认；跳过系统关键目录 |
ComposioHQ/awesome-claude-skills77kIdentifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
科研
K-Dense-AI/scientific-agent-skills48kEstimates intracellular metabolic fluxes from steady-state carbon-13 isotope-tracing measurements using validated atom maps, mfapy isotope simulation, constrained multistart fitting, and flux-profile diagnostics. Use for 13C-MFA, carbon tracing, mass isotopomer distributions (MDVs/MIDs), positional isotopomers, parallel tracer experiments, and determining whether labeling data constrain a pathway flux. Distinguishes measured-label inference from COBRA flux balance analysis and flags experiments requiring nonstationary MFA.
科研
K-Dense-AI/scientific-agent-skills48kPythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
科研
K-Dense-AI/scientific-agent-skills48kProvides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.
科研
K-Dense-AI/scientific-agent-skills48kPrepares bulk RNA-seq FASTQ, Salmon, STAR or featureCounts output for gene-level differential expression. Covers nf-core/rnaseq and standalone quantification, biological replication, strandedness, reference provenance, validated count assembly and a PyDESeq2 handoff. Use for FASTQ-to-counts analysis, nf-core/rnaseq configuration, STAR/Salmon quantification, or building a counts matrix for DESeq2. For single-cell data use scanpy; for statistical fitting alone use pydeseq2.
科研
K-Dense-AI/scientific-agent-skills48kLooks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), scores variants or scans windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and builds Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.
科研