From gitlab
Loads GitLab MR context for a branch: title, description, changes, pipeline status, reviews using MCP tools. Invoke manually or auto-activates on feature branches.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gitlab:load-mr-contextThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
gitlab:load-mr-context - Load merge request context for the current branch
gitlab:load-mr-context - Load merge request context for the current branch
/load-mr-context [project-path] [branch]
Loads the full context of an open merge request for the given branch, including description, changes, pipeline status, and review comments. Uses GitLab MCP tools for structured data access.
Given project-path and branch arguments:
mcp__plugin_gitlab_gitlab__list_merge_requests with project_id: "PROJECT_PATH", source_branch: "BRANCH", state: "opened" to find the MRmcp__plugin_gitlab_gitlab__get_merge_request with the MR IID to read description, labels, reviewers, and metadatamcp__plugin_gitlab_gitlab__get_merge_request_diffs to understand what has changedUser: /load-mr-context my-group/my-project feat/mr-context
Claude: ## MR !42: Add MR context detection hooks
- **Status**: Open, 1 review pending
- **Description**: Adds SessionStart hooks to GitLab plugin that detect open MRs on the current branch
- **Changes**: 4 files (+120, -8)
- **Pipeline**: All stages passing
- **Reviews**: 1 approved, 1 pending from @reviewer
Ready to assist with this MR.
project-path (required): GitLab project path (e.g., group/project or numeric ID)branch (required): Branch name to find the MR fornpx claudepluginhub thebushidocollective/han --plugin gitlabLoads GitHub PR context for a branch: title, description, file changes, CI status, reviews via MCP tools. Manual /load-pr-context or auto on feature branches.
Reviews GitLab merge requests including metadata, commits, diffs, pipeline status, code suggestions, and approval recommendations. Invoke via /review-mr.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.