AC capacitor-plugin-upgrade-v4-to-v5
Upgrades a Capacitor plugin library from v4 to v5 using `npx @capacitor/plugin-migration-v4-to-v5@latest`, then the manual checklist - `@capacitor/*` dev deps to `latest-5`, compile/target SDK 33 defaults, AGP 8.0.0, Gradle 8.0.2, `namespace` in build.gradle instead of manifest `package`, Java 17, Jetifier removal, Kotlin 1.8.20 with `kotlin-stdlib`, plus code changes - `CAPBridgedPlugin` requirements moved to instance level (`pluginId` -> `identifier`, `pluginMethods` typed `[CAPPluginMethod]`) and Android `PluginCall.getObject()` / `getArray()` may return null. Use when a plugin's peer dependency is Capacitor 4 and it must support 5, or apps on v5 fail with "Namespace not specified" in the plugin module. Do not use for app upgrades, other major versions, or non-Capacitor libraries.
Upgrades a Capacitor plugin library from v4 to v5 using npx @capacitor/plugin-migration-v4-to-v5@latest, then the manual checklist - @capacitor/ dev deps to…
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 · 2
✓ No critical or high findings
Medium and low: 2
-
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=['package.name='+(pkg.name||''),'package.vers -
low Broad scope
meta-dynamic-shellSKILL.md:30Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)!`find . -maxdepth 3 \( -path './example-app' -o -path './ios' -o -path './android' \)`
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 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. 4 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. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1068 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 794: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.