AB Swift
Writes, debugs, and optimizes Swift — concurrency, ARC leaks, optionals, generics, SwiftUI state, and packages. Use when writing or reviewing Swift code, when a build won't type-check or the compiler "is unable to type-check this expression in reasonable time", when an app crashes on a force unwrap, an unowned reference, or EXC_BAD_ACCESS, when Swift 6 raises Sendable / actor-isolated / data-race errors, when a retain cycle keeps objects alive, when JSON fails to decode, when async code hangs or deadlocks, when SwiftUI state resets or views redraw too often, when XCTest or Swift Testing tests are flaky, when a Swift package won't resolve, or when bridging to Objective-C, C, or Linux. Not for Xcode signing and IDE settings, or App Store submission and iOS app lifecycle.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4587 tokens
- 100Tools and files. No external tools needed
- 100Steps. 38 steps
- 100Failures and branches. 2 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
- low 11 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 779: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 38 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.