The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several CLI tools to perform project validation and infrastructure planning, including terraform, tofu, rg (ripgrep), rsync, perl, uv, and gh (GitHub CLI). These are standard tools for managing infrastructure-as-code and CI/CD workflows.
[DYNAMIC_EXECUTION]: In Step 6, a perl one-liner dynamically modifies the source attribute in a temporary configuration file (main.tf) created from an example. This substitution redirects module sourcing from a remote repository to the local checkout for validation purposes. Additionally, the skill uses uv run to execute local Python scripts (scripts/validate_tailscale_large_scale_examples.py, scripts/validate_v3_final_polish_examples.py, and scripts/smoke_v3_plan_matrix.py) which contain specialized validation logic.
[INDIRECT_PROMPT_INJECTION]: The skill operates on files within a local git repository, which presents a surface for processing untrusted data if used on third-party code.
Ingestion points: Reads and scans Terraform configuration files (.tf, .tf.json) and project examples from the local worktree.
Boundary markers: None identified.
Capability inventory: Execution of shell commands, dynamic file modification via perl, and execution of local Python and shell scripts.
Sanitization: No explicit sanitization or filtering of file contents is performed before they are processed by validation tools or the perl substitution.

test-changes