SKILLEMALL.ai
GitHub ↗ RU Sign in

FF maintaining-macos-health

Hands-on playbook for macOS disk cleanup, dev-machine optimization, and proactive health alerting. Use when the Mac is full or slow, when a process persistently burns CPU, when a kernel panic / watchdog timeout / vm-compressor-space-shortage / Jetsam event happened, when the user asks to free disk space, audit storage, set up disk/memory/CPU alerts, or restore the same monitoring on a new Mac. Built around Mole (`mo` CLI) for safety guards plus a custom LaunchAgent-based alerter for active warnings. Covers Apple Silicon laptops with heavy AI/Docker workloads. Not for general macOS support, hardware diagnostics, networking issues, GUI / window-manager bugs, Time Machine recovery, or broken app installs.

CodeAlive-AI/ai-driven-development Agent Skills author: CodeAlive-AI MIT 32 files · 20 scripts body ≈ 5 272 tokens Open the sourcegithub.com↗ analyzed 19 h ago

Hands-on playbook for macOS disk cleanup, dev-machine optimization, and proactive health alerting.

As a process F 46/100 · Will not run — References files that are not bundled: assets/mac-health-disk, assets/disk_*.py, assets/mac-health-check

ProcedureDockerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
F
39/100
safety, quality, tests
Safety 60%
19
Quality 40%
70
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: assets/mac-health-disk, assets/disk_*.py, assets/mac-health-check
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 21

✓ No critical or high findings

Medium and low: 21
  • medium Dangerous commands cmd-eval-dynamic assets/render-cleanup-plan.py:1323
    Dynamic code execution from decoded/untrusted input
    os.system(f"open '{url}'")
  • medium Dangerous commands cmd-persistence README.md:84
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    > ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence README.md:86
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl load -w ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence references/alerting.md:42
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence references/alerting.md:85
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    > ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence references/alerting.md:100
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl load -w ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence references/alerting.md:228
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence references/alerting.md:230
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl load -w ~/Library/LaunchAgents/com.local.mac-health-check.plist
    security skill
  • medium Dangerous commands cmd-persistence references/cleanup-tiers.md:183
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    launchctl unload ~/Library/LaunchAgents/com.jetbrains.toolbox.plist 2>/dev/null
    security skill
  • medium Dangerous commands cmd-persistence references/cleanup-tiers.md:195
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    rm -f ~/Library/LaunchAgents/com.jetbrains.toolbox.plist
    security skill
  • medium Risky intent intent-wallet-secrets references/never-touch.md:177
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - **Exodus** — `~/Library/Application Support/Exodus/` holds encrypted seed-derived wallet files. Without the 12-word recovery phrase, deletion = irreversible loss of access to funds.
  • medium Risky intent intent-wallet-secrets references/never-touch.md:179
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - **Ledger Live** (`com.ledger.live-desktop`) — `~/Library/Application Support/Ledger Live/` stores account list + transaction history. Funds are on the hardware device, but recovery phrase is needed
  • medium Risky intent intent-wallet-secrets references/never-touch.md:295
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    | Ledger Live | `~/Library/Application Support/Ledger Live/` | Account list + transaction history. Funds safe on device, but recovery phrase required to rebuild app state. |
  • medium Risky intent intent-wallet-secrets references/never-touch.md:296
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    | Exodus | `~/Library/Application Support/Exodus/` | Encrypted wallet files. Without seed phrase, deletion = permanent loss of funds. |
  • medium Risky intent intent-wallet-secrets references/never-touch.md:314
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    - Wiping a browser profile (`~/Library/Application Support/{Google/Chrome,BraveSoftware,Arc,Microsoft Edge,...}/Default/`) when MetaMask / browser-extension wallets or password sync are in use — exten
  • low Dangerous commands cmd-privilege references/cleanup-tiers.md:237
    Privilege escalation / world-writable permissions (documentation of a security skill)
    [ "$d" != "$LATEST" ] && sudo rm -rf "/Library/Application Support/Logi/LogiOptionsPlus/depots/$d"
    security skill
  • low Dangerous commands cmd-shell-rc references/cleanup-tiers.md:396
    Writes to a shell startup file (documentation of a security skill)
    echo 'alias docker-tidy="docker container prune -f && docker image prune -f && docker builder prune -f"' >> ~/.zshrc
    security skill
  • low Dangerous commands cmd-privilege references/triage.md:158
    Privilege escalation / world-writable permissions (negated — the text forbids it)
    - Don't `sudo rm -rf /private/var/vm/swapfile*` — guaranteed kernel panic.
    negated

A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5272 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: assets/mac-health-disk
  • warning missing-ref reference to a missing file: assets/disk_*.py
  • warning missing-ref reference to a missing file: assets/mac-health-check
  • warning missing-ref reference to a missing file: assets/mac-health-action
  • warning missing-ref reference to a missing file: assets/com.local.mac-health-check.plist

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: assets/mac-health-disk, assets/disk_*.py, assets/mac-health-check
  • 0Tools and files. 5 referenced file(s) missing: assets/mac-health-disk, assets/disk_*.py, assets/mac-health-check
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 16 mutating operations with no state check
  • 60Steps. 76 steps, 4 vague phrases
  • 70Execution cost. Instruction body is 5272 tokens
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 711: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 76 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.