The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various shell commands to perform repository analysis, including git log for timeline reconstruction, find to map page routes and API endpoints, and cat to read project configuration metadata.
[COMMAND_EXECUTION]: If the GitHub CLI is available and configured, the skill uses gh issue list to fetch issue data for mapping deliverables to stories. This is performed against a well-known service (GitHub) using the project's own configuration.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from external project sources.
Ingestion points: Git commit messages via git log, file contents and paths discovered via find/cat, and GitHub issue titles and bodies via gh CLI.
Boundary markers: No specific delimiters or instructions to ignore embedded content are defined for the agent when processing these inputs.
Capability inventory: The skill has the capability to write the analyzed data to markdown files (e.g., docs/features.md) on the local filesystem.
Sanitization: The instructions do not specify any validation or sanitization of the content retrieved from git or GitHub before it is summarized into the feature matrix document.

feature-matrix