The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes Git commands such as 'git status', 'git stash', and 'git rebase' to manage branch state and replay commits. These commands are fundamental to the skill's purpose and are executed within the user's local repository.
[DYNAMIC_EXECUTION]: The workflow calls a local Python script located at '/scripts/prose-lint.py' to verify the quality of the generated rebase report. This is a local execution of a script that is part of the skill's deployment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests commit subjects, intent descriptions, and various project files (including AGENTS.md, architecture docs, and specs) to validate the rebase. This ingestion of untrusted or externally-contributed data represents a potential injection surface. * Ingestion points: Commit messages from the branch being rebased and existing documentation/schemas on the target branch. * Boundary markers: The skill does not explicitly define delimiters or 'ignore' instructions when reading these external files. * Capability inventory: The agent has the ability to execute shell commands, perform git operations, and run a local Python script. * Sanitization: No sanitization or filtering is applied to the content of the commits or documents before they are processed by the agent.

rebase