The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a variety of local Python scripts and standard development CLI tools to manage the repository.
Evidence: Use of python scripts/bump_version.py, python scripts/validate_skill.py, python scripts/audit_skill_system.py, git tag, and gh workflow run.
[EXTERNAL_DOWNLOADS]: The skill references external distribution and installation commands for the author's toolset.
Evidence: The document mentions npx skills add milanhorvatovic/skill-system-foundry as a primary installation method.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing external data as part of its core functionality.
Ingestion points: The agent is instructed to read git commit messages and the CHANGELOG.md file to automate release notes and versioning decisions.
Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions when parsing these external text sources.
Capability inventory: The skill possesses the capability to modify manifest files, create git tags, and trigger GitHub Action workflows based on the data it processes.
Sanitization: Validation is performed via regex and logic within the provided generate_changelog.py and bump_version.py scripts to ensure inputs conform to expected formats.

git-release