The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various Git and initialization commands as part of its primary workflow.
Runs git status, git stash, git pull, and git commit to manage repository state.
Executes npx husky init to set up Git hooks for the project.
Configures and executes gitleaks protect to scan staged files for potential secret leaks before committing.
[EXTERNAL_DOWNLOADS]: The skill fetches external packages during the initialization process.
Uses npx to download and run the husky package from the official npm registry.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the project metadata it analyzes.
Ingestion points: Reads package.json, commit histories, documentation, and conversation context to determine commit message formatting and GitHub issue references.
Boundary markers: No delimiters or instructions are used to prevent the agent from obeying instructions embedded in the analyzed code or documentation.
Capability inventory: The skill has the ability to execute shell commands (git, npx) and write configuration to local files (Husky hooks).
Sanitization: No validation or sanitization is performed on context-derived strings before they are incorporated into Git messages or command flows.

commit