The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute various shell commands for clearing caches, reinstalling dependencies, and running diagnostics. Evidence found in SKILL.md and references/new-architecture.md includes commands like npx expo install expo@latest, rm -rf node_modules .expo, watchman watch-del-all, cd ios && pod install --repo-update, and cd android && ./gradlew clean.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx, bunx, pod, and gradle to download and install external packages and native dependencies from the npm registry and other official sources. These references target well-known services within the Expo and React Native ecosystems, such as expo, expo-doctor, and react-native-worklets.
[PROMPT_INJECTION]: An indirect prompt injection surface is identified as the skill processes local project configuration files (package.json, app.json, babel.config.js, metro.config.js).
Ingestion points: Local configuration files in the project root (SKILL.md).
Boundary markers: None present in the instructions to delimit or ignore embedded instructions within processed files.
Capability inventory: Extensive file system modification and command execution via npx, rm, pod, and gradlew (SKILL.md, references/new-architecture.md).
Sanitization: No explicit sanitization or validation of the input file content is described before execution or modification.

upgrading-expo