The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local commands including git status, git diff, and git log to analyze the repository state. It also runs npx tsc --noEmit to identify TypeScript errors before deployment.
[PROMPT_INJECTION]: The skill processes untrusted data from the repository history and code changes, creating a surface for indirect prompt injection.
Ingestion points: The agent reads Git commit messages and code diffs from the local environment.
Boundary markers: None identified; the instructions do not use delimiters or provide warnings for processing repository data.
Capability inventory: The skill executes local development commands including git and npx.
Sanitization: No filtering or validation of the Git log or diff content is performed before processing.
[SAFE]: The skill includes beneficial security checks for accidentally staged secrets, such as credentials and environment files, and prevents the deployment if they are found.

deploy-check