The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs shell operations using Git to stage changes and create commits (git add, git commit). These operations are conditional upon user confirmation as defined in the execution flow.
[PROMPT_INJECTION]: The skill identifies tasks and metadata by parsing the content of PROGRESS.md. Since it ingests untrusted data from a project file and uses it to drive subsequent actions, it presents an indirect prompt injection surface.
Ingestion points: Reads the PROGRESS.md file from the project root to detect completed tasks and phases.
Boundary markers: The skill does not define specific boundary markers or instructions to isolate the parsed file content from the agent's internal reasoning.
Capability inventory: The skill is capable of writing new markdown files to the local file system (docs/progress/archive/) and executing Git commands.
Sanitization: There is no explicit mechanism for sanitizing task names or descriptions extracted from the file before they are interpolated into commit messages or file paths.

progress-archive