BC mac-storage-cleaner
Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools. Use whenever the user says their Mac disk or storage is full or nearly full, gets a "startup disk almost full" / low-storage warning, asks to free up space, clean/clear caches, remove junk, delete leftover files from apps they uninstalled, or find what's eating their disk — in any language (e.g. English "my mac is out of space", "free up disk", "clear caches", "what's taking up my storage"; Georgian "ქეში გაასუფთავე", "მეხსიერება გადამევსო", "ადგილი აღარ მაქვს"). Surveys usage first, auto-clears only pure caches, moves anything riskier to the Trash (restorable), asks before anything expensive, logs every deletion, and reports what was freed. Do NOT use for cloud storage, RAM/memory-pressure, or a single named app's own in-app cache button.
Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-persistencereferences/cache-catalog.md:104Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- `~/Library/LaunchAgents/<id>.plist` (and `/Library/LaunchAgents`, `/Library/LaunchDaemons` — need admin)
quoted
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 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. 15 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 13 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1811 tokens
- 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
- +3Description length 872: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 9 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.