DF swift-macos
macOS apps with Swift 6.3, SwiftUI, SwiftData, Swift Concurrency, Foundation Models, Swift Testing, and ScreenCaptureKit. Use when building native Mac apps - windows, menus, SwiftData, on-device AI, capture, AppKit bridges, notarization.
As a process F 34/100 · Will not run — weak spots: steps, result and completion, when it triggers
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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".
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 6
-
high Concealment
en-hide-from-userCHANGELOG.md:104Instruction to hide actions from the user- Swift Testing: `confirmation` for callback- and delegate-driven code, `withKnownIssue`, the `swift test` CLI surface, and the trap where Command Line Tools alone silently run no tests.
-
high Dangerous commands
cmd-persistencereferences/system-integration.md:609Persistence mechanism (cron / launchd / scheduled task / autorun registry)LaunchAgents/com.example.agent.plist
-
high Dangerous commands
cmd-persistencereferences/system-integration.md:610Persistence mechanism (cron / launchd / scheduled task / autorun registry)LaunchDaemons/com.example.daemon.plist
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellreferences/spm-build.md:302Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -L https://swift.org/install | bash
vendor-host -
medium Dangerous commands
cmd-persistencereferences/system-integration.md:589Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)// LaunchAgent (in Contents/Library/LaunchAgents/)
comment -
medium Dangerous commands
cmd-persistencereferences/system-integration.md:592Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)// LaunchDaemon (in Contents/Library/LaunchDaemons/ - requires admin approval)
comment
Files scanned: 27. 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 34/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 70Execution cost. Instruction body is 4282 tokens
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- low 16 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 237: enough signal without eating the budget
- +4Structure: 27 headings
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (23 of 23)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.