AC capacitor-app-upgrade-v4-to-v5
Upgrades a Capacitor app from v4 to v5 using `npx cap migrate` from `@capacitor/cli@latest-5`, then the manual checklist - Node 16+, Xcode 14.1+, Android Studio Flamingo with JDK 17, AGP 8.0.0, Gradle 8.0.2, compile/target SDK 33, `package` moved from AndroidManifest.xml to `namespace` in build.gradle, Jetifier removal, pinning `androidScheme` to `http`, and official plugin breaking changes (Device `uuid` to `identifier`, Android 13 notification permissions, READ_MEDIA_IMAGES). Use when `@capacitor/core` is 4.x and the target is 5.x, or on errors like "Namespace not specified" or "Android Gradle plugin requires Java 17". Do not use for other major versions, plugin library upgrades, or non-Capacitor apps.
Upgrades a Capacitor app from v4 to v5 using npx cap migrate from @capacitor/cli@latest-5, then the manual checklist - Node 16+, Xcode 14.1+, Android Studio…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
The same skill appears in 1 more place: capgo-skills
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
-
low Broad scope
meta-dynamic-shellSKILL.md:27Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)!`node -e "const fs=require('fs');if(!fs.existsSync('package.json'))process.exit(0);const pkg=JSON.parse(fs.readFileSync('package.json','utf8'));const out=[];for(const section of ['dependencies','devD
Files scanned: 4. 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 61/100
- 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. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1541 tokens
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 713: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.