The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the local package manager (npm, pnpm, yarn, or bun) to initialize new projects and install dependencies.
Evidence: Uses {pm} create vite@latest . -- --template react-compiler-ts --no-interactive for project creation and {pm} install -D for package management.
[INDIRECT_PROMPT_INJECTION]: The skill reads existing project configuration files to determine which setup steps are necessary, creating a surface for indirect prompt injection if project files are malicious.
Ingestion points: Reads package.json, vite.config.ts, tsconfig.json, and lock files from the current working directory.
Boundary markers: No explicit delimiters are used when the agent processes the contents of these files.
Capability inventory: The skill has the ability to write files (.prettierrc, .vscode/settings.json) and execute shell commands for package installation.
Sanitization: No explicit sanitization or validation of the contents of the read files is performed.
[SAFE]: All identified activities, including package installations and configuration file modifications, are standard operations for a development scaffolding tool and align with the skill's stated purpose. The external link to documentation (heropy.dev) is consistent with the author's known online presence.

react-vite-scaffold