The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Git and GitHub CLI commands to assess and resolve conflicts. Examples include git status, git diff, git config, and gh pr. These are standard tools for the stated purpose.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill uses dynamic context injection placeholders to gather repository state information when the skill is loaded. \n
Evidence: Benign commands such as git branch --show-current, git status --porcelain=v2 --branch, and git version are used to populate the context for the agent.\n- [EXTERNAL_DOWNLOADS]: The skill fetches data from remote repositories and pull requests using git fetch and gh pr view. These operations target well-known infrastructure (GitHub) and are necessary for resolving merge conflicts between branches.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from files with conflict markers. While the skill focuses on technical resolution, it presents an attack surface for instructions embedded in the code being merged.\n
Ingestion points: File content is read via Read and git diff in SKILL.md.\n
Boundary markers: No explicit markers are used to separate conflict content from agent instructions.\n
Capability inventory: The skill allows file editing (Edit) and command execution (Bash).\n
Sanitization: No sanitization is performed on the content of the files being merged.

git-conflicts