The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill generates setup commands that instruct users to download and install third-party dependencies using standard package managers like npm and pip.
[COMMAND_EXECUTION]: The skill provides a structured sequence of shell commands for project initialization, environment setup, and local server execution.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by using untrusted user inputs to generate executable code and configuration files.
Ingestion points: The mvp_features and project_title inputs are ingested and used to populate the project scaffold described in SKILL.md.
Boundary markers: Boundary markers are absent; the skill does not use specific delimiters or instructions to treat input data as non-executable text.
Capability inventory: The skill produces shell commands in startup_commands and executable code snippets in llm_routing_scaffold and database_scaffold within SKILL.md.
Sanitization: Sanitization is absent; the skill does not perform validation or escaping of input data before interpolating it into the generated output templates.

hackathon-repo-bootstrap