AD storagesaver-watcher
Watch and explain Mac disk usage. Use when the user asks about Mac storage/disk space ("what's eating my disk?", "disk full", "free up space"), wants a visual map of what's on the disk, or wants scheduled storage watching with alerts. Read-only by design: it recommends copy-paste commands, it never deletes anything itself.
Watch and explain Mac disk usage.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Concealment
en-hide-from-userSKILL.md:78Instruction to hide actions from the user ("do not tell the user <a claim>" — honesty guidance, not concealment)Never tell the user an app is "unused" from file timestamps alone.
honesty claim -
low Dangerous commands
cmd-privilegewatcher.js:680Privilege escalation / world-writable permissions (string literal in code, not executed){ label: 'core dumps (/cores)', bytes: raw.devCruft['core dumps'], cmd: "sudo rm -rf /cores/*" },code literal
Files scanned: 3. 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 49/100
- 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. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (storagesaver-watcher) differs from the folder (storagesaver)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 14 steps, 2 vague phrases
- 100Execution cost. Instruction body is 1039 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 324: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.