The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files to identify the current toolchain and configuration, which presents an ingestion point for potentially untrusted project data.
Ingestion points: Scans files like jest-e2e.json, .eslintrc.*, and package-lock.json in Phase 1 of reference/migration-checklist.md.
Boundary markers: Absent.
Capability inventory: Shell command execution (sed, grep), file system modification, and package manager operations across all phases.
Sanitization: Absent.
[EXTERNAL_DOWNLOADS]: The skill references an external URL to synchronize package versions with the vendor's official boilerplate repository.
Evidence: References https://raw.githubusercontent.com/lenneTech/nest-server-starter/main/package.json in Phase 2.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and scripts to automate the migration and verify the build.
Evidence: Uses sed and grep for code migration, executes package managers (npm, pnpm), and runs boot verification scripts like scripts/check-server-start.mjs.

modernizing-toolchain