The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and rely on external, potentially untrusted data from Linear tickets (titles, descriptions, and comments) to make decisions during conflict resolution and code optimization.
Ingestion points: External data is fetched via the mcp__plugin_lt-dev_linear__get_issue tool and extracted from branch names.
Boundary markers: The instructions do not define boundary markers or provide warnings to the agent regarding embedded instructions within the fetched ticket data.
Capability inventory: The skill has significant capabilities, including file system access (rebasing, resolving conflicts) and command execution (git, pnpm, bash, gh, glab).
Sanitization: The skill lacks explicit sanitization or validation of the content retrieved from external ticket management systems.
[COMMAND_EXECUTION]: The skill relies on several external CLI tools to manage the Git workflow.
Repository Management: Uses gh (GitHub) or glab (GitLab) to list and process merge/pull requests.
Linting and Formatting: Executes pnpm dlx oxfmt and pnpm dlx oxlint to download and run development tools at runtime.

rebasing-branches