The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes git rev-parse to determine the repository root and utilizes the GitHub CLI (gh) to retrieve recent Pull Request history for template generation.
[INDIRECT_PROMPT_INJECTION]: The skill adapts to existing project conventions by reading local artifacts such as CONTRIBUTING files, documentation, CI workflows, and remote Pull Request history. This creates an attack surface where malicious instructions embedded in the project data could influence the agent's behavior during template generation.
Ingestion points: Local files including .github/PULL_REQUEST_TEMPLATE*, CONTRIBUTING*, documentation, and CI workflows (SKILL.md Step 5), as well as PR history via the GitHub CLI.
Boundary markers: No specific delimiters or safety instructions are defined for the interpolation of ingested data.
Capability inventory: The skill possesses the ability to write to the file system (creating .gitkkal/config.json and .github/PULL_REQUEST_TEMPLATE.md) and execute shell commands via git and gh.
Sanitization: There is no evidence of sanitization, filtering, or escaping applied to the content retrieved from repository files or PR history before it is processed by the agent.

gitkkal-init