Not in the top 1,000 by GitHub stars

DogukanK/claude-pc-cleanup

Claude Code skill: scan a macOS machine for reclaimable disk space and clean it up safely, tier by tier, with explicit confirmation before deleting anything.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 95ae35e407ea

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 95ae35e407ea8ad7dddc9dc3e5a4b425307652bc

1GitHub star
-15stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.1
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 1, 202616

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

pc-cleanup

When your agent uses it

Scan a macOS machine for reclaimable disk space and clean it up safely. Use this whenever the user reports low disk space, a "disk almost full" warning, wants to free up storage, asks to delete unnecessary/junk/system files, mentions "sistem verileri" (macOS's System Data category) taking up too much room, asks what's safe to delete on their Mac, wants to reclaim space from old node_modules/Docker or Podman images/build caches piled up across dev projects, or wants a recurring PC/disk cleanup routine — even if they never say the words "disk" or "clean up" outright. Always run the read-only scan first, present a tiered summary, and get explicit confirmation before deleting anything — never delete first and explain later.

What it loads into context

Frontmatter

165 tokens

Always available to the agent

SKILL.md

4,034 tokens

When the skill is activated

Reference documents

1,306 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Phase 1 — Scan (read-only, always safe to run without asking)
  2. Phase 2 — Classify into tiers
  3. Phase 3 — Confirm
  4. Phase 4 — Delete
  5. Phase 5 — Report
  6. Maintenance

Scripts executed separately

  • scripts/safe_delete.sh
  • scripts/scan.sh
  • scripts/selftest.sh

Files

  • .gitignoreasset10 bytes
  • LICENSEasset1,071 bytes
  • README.mddoc5,247 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • SKILL.mdcore16,692 bytes
  • evals/evals.jsonasset4,086 bytes
  • scripts/safe_delete.shruns5,792 bytes
  • scripts/scan.shruns8,022 bytes
  • scripts/selftest.shruns3,852 bytes
Read SKILL.md

# PC Cleanup (macOS)

Free up disk space by finding what is safe to delete, showing the user exactly
what that is and why it's safe, getting their explicit go-ahead, and only then
deleting it. This is a recurring maintenance task the user runs periodically —
optimize for a routine that is fast to run, trustworthy, and never surprises
them with something gone that they needed.

The core discipline: **almost everything on a dev machine that takes up a lot
of space is either a cache or a build artifact that something else can
regenerate.** The job is to prove that regenerability before suggesting
deletion, not to assume it.

## Phase 1 — Scan (read-only, always safe to run without asking)
View the complete source on GitHub

Skills included

  • pc-cleanup

Repository facts

License
MIT
Created
Sep 6, 2026
Last pushed
Sep 6, 2026
Forks
0
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 7 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 17 signals by file

README.md

  • Network accessline 3
    A [Claude Code](https://claude.com/claude-code) skill that scans a macOS
  • Network accessline 46
    git clone https://github.com/DogukanK/claude-pc-cleanup.git ~/.claude/skills/pc-cleanup
  • Dangerous shell operationline 63
    rm -rf ~/.claude/skills/pc-cleanup

SKILL.md

  • Dangerous shell operationline 200
    than raw `rm -rf`:
  • Dangerous shell operationline 230
    - Podman/Docker machine → `podman machine rm <name>` (stop it first if running)
  • Dangerous shell operationline 231
    - Claude Desktop `vm_bundles` → `rm -rf` (it re-downloads on next use)
  • Dangerous shell operationline 237
    - A Downloads item the user specifically named → `rm -rf` on that exact path

evals/evals.json

  • Instruction override signalline 31
    "id": 2,       "prompt": "gereksiz dosyaları hepsini sil kanka, disk çok dolu, özellikle sistem verileri kısmı çok yer kaplıyor gibi görünüyor. (Bu bir dry-run/test çalıştırması: yine de hiçbir şeyi fiilen silme — sadece neyi silmeyi önerec
  • Instruction override signalline 32
    "prompt": "gereksiz dosyaları hepsini sil kanka, disk çok dolu, özellikle sistem verileri kısmı çok yer kaplıyor gibi görünüyor. (Bu bir dry-run/test çalıştırması: yine de hiçbir şeyi fiilen silme — sadece neyi silmeyi önereceğini ve neden 
  • Instruction override signalline 33
    "expected_output": "Even though the phrasing sounds like blanket permission ('delete everything unnecessary'), the response still scans first, classifies into tiers, explains what macOS 'System Data' actually consists of on this machine, an

scripts/safe_delete.sh

  • Executable scriptline 1
    #!/bin/bash
  • Dangerous shell operationline 115
    find "$path" -mindepth 1 -maxdepth 1 -exec rm -rf {} + 2>/dev/null
  • Dangerous shell operationline 133
    rm -rf "$path"
  • Dangerous shell operationline 135
    echo "FAILED: $path (still exists after rm -rf)"

scripts/scan.sh

  • Executable scriptline 1
    #!/bin/bash

scripts/selftest.sh

  • Executable scriptline 1
    #!/bin/bash
  • Dangerous shell operationline 19
    cleanup() { rm -rf "$TMP"; }

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 14 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.