Adonis0123/adonis-skills / skills/disk-tidy
disk-tidy
VerifiedFree disk space on a developer's Mac (Linux partly) when the disk is nearly full: measure where the space went across build output, package-manager caches, app data, AI agent data, old tool versions and worktrees, fan the read-only survey out to subagents, merge it into a tiered cleanup list, clean only what the user approves, and report the real gain from free space before and after. Use whenever the user says the disk or SSD is (almost) full, asks what is eating space, what can be cleaned or deleted to free space, or why free space keeps shrinking, in any language, Chinese included. Hands organizing personal files to file-tidy and removing git worktrees to worktree-tidy. Not for organizing files without a space problem, a single known cache command, system files that need sudo, iCloud or other cloud storage plans, or disks of remote servers, containers and Kubernetes nodes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.9 KB |
| assets/locations.json | config | 6.3 KB |
| evals/evals.json | config | 4.2 KB |
| references/hotspots.md | markdown | 5.8 KB |
| scripts/disk_tidy.py | script | 14.2 KB |
| scripts/test_disk_tidy.py | script | 9.8 KB |
evals/evals.json
View on GitHub{
"skill_name": "disk-tidy",
"evals": [
{
"id": 1,
"prompt": "我的 Mac 硬盘又快满了,帮我看看都被什么占了,哪些可以清理。先只出一份清单给我,别删也别移动任何东西。",
"expected_output": "Read-only survey: free-space snapshot, slices covering build output/caches, apps, AI agent data and repos, the owner's files; one merged list in tiers A/B/C with sizes, loss and risk; caveat that du overstates because of APFS clones; Trash contents mentioned; nothing deleted.",
"files": [],
"assertions": [
{
"name": "free-space-snapshot",
"text": "The report states current free and used space of the data volume as a measured number."
},
{
"name": "build-output-covered",
"text": "The report measures build output such as .next, .turbo or Cargo target folders under the code folders and says which are safe to delete."
},
{
"name": "agent-data-covered",
"text": "The report covers AI agent data (sessions, upgrade leftovers or old CLI versions)."
},
{
"name": "tiers",
"text": "Items are grouped into rebuildable / owner decides / keep (or equivalent tiers) with a size per item."
},
{
"name": "clone-caveat",
"text": "The report warns that du sizes can overstate the space actually freed (APFS clones or hard links), or reports gains only from free-space differences."
},
{
"name": "nothing-deleted",
"text": "The run deleted, moved or emptied nothing (no rm, no Trash moves, no cache clean commands executed)."
}
]
},
{
"id": 2,
"prompt": "我代码目录里那几个 Next.js 项目和它们的 worktree 太占空间了,帮我找出能安全删掉的构建缓存(.next、.turbo 这些),正在跑 dev server 的别动。先给我 dry-run 结果看看,不要真删。",
"expected_output": "Finds the code roots, then build-output folders under them, checks git ignore status and running processes, marks the folder of a running dev server as blocked, shows a dry run with sizes and a du-based total, deletes nothing.",
"files": [],
"assertions": [
{
"name": "git-ignore-checked",
"text": "Each candidate's git ignore status is checked (git check-ignore or the skill's artifacts report)."
},
{
"name": "running-process-checked",
"text": "Running processes (dev servers or process working directories) are checked and any folder in use is excluded."
},
{
"name": "dry-run-only",
"text": "Output is a dry run listing would-delete folders with sizes; nothing was actually deleted."
},
{
"name": "worktrees-included",
"text": "Build output inside .worktrees of the repositories is included in the scan."
}
]
},
{
"id": 3,
"prompt": "上周刚清过一次硬盘,可用空间又在往下掉。帮我查查最近一周是什么东西在涨、以后还会不会继续涨,先别清理。",
"expected_output": "Looks for recently modified or recently grown large folders (build output, caches, app clones, sessions, worktrees), explains which keep growing and why, names the cause where it can, gives cleanup options with tiers, and cleans nothing.",
"files": [],
"assertions": [
{
"name": "recent-growth-measured",
"text": "The answer identifies specific folders that grew or were created recently, using modification dates or a comparison, with sizes."
},
{
"name": "cause-explained",
"text": "For at least one growing item the answer explains what recreates it (for example dev sessions rebuilding .next, browser updates leaving clones, repeated installs)."
},
{
"name": "recurrence-advice",
"text": "The answer says which items will keep growing and how to keep them in check."
},
{
"name": "nothing-cleaned",
"text": "No cache was cleaned and nothing was deleted or moved."
}
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |