BD capacitor-plugin-upgrade-v8-to-v9
Upgrades a Capacitor plugin library from v8 to v9 (prerelease, @next until GA). Runs `npx @capacitor/plugin-migration-v8-to-v9@latest`, then the manual checklist - peer/dev dependency ranges, removed Android APIs (@NativePlugin, saveCall, pluginRequestPermission, int-code startActivityForResult, CapConfig getters, PluginCall.save/isSaved/hasOption), removed iOS APIs (CAPBridge class, getWebView, isSimulator, presentVC, CAPNotifications), AGP 9.2.1 / Gradle 9.5.1 build.gradle edits (compileSdk 37, minSdk 26, no targetSdk, built-in Kotlin, core-ktx to core, unique namespace, no jcenter, proguard-android-optimize.txt), iOS 16 in podspec and Package.swift, dropping the Cordova SPM product, and UIScene lifecycle observers. Use for "update my plugin to Capacitor 9", "Cannot find 'CAPBridge' in scope", NativePlugin compile errors, AGP 9 namespace collisions. Do not use for apps (use capacitor-app-upgrade-v8-to-v9), the 8.5 UIScene app step (use capacitor-uiscene-migration), or older majors.
Upgrades a Capacitor plugin library from v8 to v9 (prerelease, @next until GA).
As a process D 49/100 · Unfinished process — References files that are not bundled: references/plugin-audit.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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:31Shell 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:33Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)!`find . -maxdepth 3 \( -path './example-app' -o -path './example' -o -path './ios' -o -path './android' \) -not -path './node_modules/*'`
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/plugin-audit.md - note
edit-residuethe text marks something as outdated (lines 40): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: references/plugin-audit.md
- 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. 14 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 25 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1663 tokens
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Description length 998: 120–800 characters recommended
- +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
- +4Structure: 7 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.