gitlab-automation
Automate GitLab project management, issues, merge requests, pipelines, branches, and user operations via Rube MCP (Composio). Always search tools first for current schemas.
What this skill does
# GitLab Automation via Rube MCP Automate GitLab operations including project management, issue tracking, merge request workflows, CI/CD pipeline monitoring, branch management, and user administration through Composio's GitLab toolkit. ## Prerequisites - Rube MCP must be connected (RUBE_SEARCH_TOOLS available) - Active GitLab connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `gitlab` - Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas ## Setup **Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. 1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds 2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `gitlab` 3. If connection is not ACTIVE, follow the returned auth link to complete GitLab OAuth 4. Confirm connection status shows ACTIVE before running any workflows ## Core Workflows ### 1. Manage Issues **When to use**: User wants to create, update, list, or search issues in a GitLab project **Tool sequence**: 1. `GITLAB_GET_PROJECTS` - Find the target project and get its ID [Prerequisite] 2. `GITLAB_LIST_PROJECT_ISSUES` - List and filter issues for a project [Required] 3. `GITLAB_CREATE_PROJECT_ISSUE` - Create a new issue [Required for create] 4. `GITLAB_UPDATE_PROJECT_ISSUE` - Update an existing issue (title, labels, state, assignees) [Required for update] 5. `GITLAB_LIST_PROJECT_USERS` - Find user IDs for assignment [Optional] **Key parameters**: - `id`: Project ID (integer) or URL-encoded path (e.g., `"my-group/my-project"`) - `title`: Issue title (required for creation) - `description`: Issue body text (max 1,048,576 characters) - `labels`: Comma-separated label names (e.g., `"bug,critical"`) - `add_labels` / `remove_labels`: Add or remove labels without replacing all - `state`: Filter by `"all"`, `"opened"`, or `"closed"` - `state_event`: `"close"` or `"reopen"` to change issue state - `assignee_ids`: Array of user IDs; use `[0]` to unassign all - `issue_iid`: Internal issue ID within the project (required for updates) - `milestone`: Filter by milestone title - `search`: Search in title and description - `scope`: `"created_by_me"`, `"assigned_to_me"`, or `"all"` - `page` / `per_page`: Pagination (default per_page: 20) **Pitfalls**: - `id` accepts either integer project ID or URL-encoded path; wrong IDs yield 4xx errors - `issue_iid` is the project-internal ID (shown as #42), different from the global issue ID - Labels in `labels` field replace ALL existing labels; use `add_labels`/`remove_labels` for incremental changes - Setting `assignee_ids` to empty array does NOT unassign; use `[0]` instead - `updated_at` field requires administrator or project/group owner rights ### 2. Manage Merge Requests **When to use**: User wants to list, filter, or review merge requests in a project **Tool sequence**: 1. `GITLAB_GET_PROJECT` - Get project details and verify access [Prerequisite] 2. `GITLAB_GET_PROJECT_MERGE_REQUESTS` - List and filter merge requests [Required] 3. `GITLAB_GET_REPOSITORY_BRANCHES` - Verify source/target branches [Optional] 4. `GITLAB_LIST_ALL_PROJECT_MEMBERS` - Find reviewers/assignees [Optional] **Key parameters**: - `id`: Project ID or URL-encoded path - `state`: `"opened"`, `"closed"`, `"locked"`, `"merged"`, or `"all"` - `scope`: `"created_by_me"` (default), `"assigned_to_me"`, or `"all"` - `source_branch` / `target_branch`: Filter by branch names - `author_id` / `author_username`: Filter by MR author - `assignee_id`: Filter by assignee (use `None` for unassigned, `Any` for assigned) - `reviewer_id` / `reviewer_username`: Filter by reviewer - `labels`: Comma-separated label filter - `search`: Search in title and description - `wip`: `"yes"` for draft MRs, `"no"` for non-draft - `order_by`: `"created_at"` (default), `"title"`, `"merged_at"`, `"updated_at"` - `view`: `"simple"` for minimal fields - `iids[]`: Filter by specific MR internal IDs **Pitfalls**: - Default `scope` is `"created_by_me"` which limits results; use `"all"` for complete listings - `author_id` and `author_username` are mutually exclusive - `reviewer_id` and `reviewer_username` are mutually exclusive - `approved` filter requires the `mr_approved_filter` feature flag (disabled by default) - Large MR histories can be noisy; use filters and moderate `per_page` values ### 3. Manage Projects and Repositories **When to use**: User wants to list projects, create new projects, or manage branches **Tool sequence**: 1. `GITLAB_GET_PROJECTS` - List all accessible projects with filters [Required] 2. `GITLAB_GET_PROJECT` - Get detailed info for a specific project [Optional] 3. `GITLAB_LIST_USER_PROJECTS` - List projects owned by a specific user [Optional] 4. `GITLAB_CREATE_PROJECT` - Create a new project [Required for create] 5. `GITLAB_GET_REPOSITORY_BRANCHES` - List branches in a project [Required for branch ops] 6. `GITLAB_CREATE_REPOSITORY_BRANCH` - Create a new branch [Optional] 7. `GITLAB_GET_REPOSITORY_BRANCH` - Get details of a specific branch [Optional] 8. `GITLAB_LIST_REPOSITORY_COMMITS` - View commit history [Optional] 9. `GITLAB_GET_PROJECT_LANGUAGES` - Get language breakdown [Optional] **Key parameters**: - `name` / `path`: Project name and URL-friendly path (both required for creation) - `visibility`: `"private"`, `"internal"`, or `"public"` - `namespace_id`: Group or user ID for project placement - `search`: Case-insensitive substring search for projects - `membership`: `true` to limit to projects user is a member of - `owned`: `true` to limit to user-owned projects - `project_id`: Project ID for branch operations - `branch_name`: Name for new branch - `ref`: Source branch or commit SHA for new branch creation - `order_by`: `"id"`, `"name"`, `"path"`, `"created_at"`, `"updated_at"`, `"star_count"`, `"last_activity_at"` **Pitfalls**: - `GITLAB_GET_PROJECTS` pagination is required for complete coverage; stopping at first page misses projects - Some responses place items under `data.details`; parse the actual returned list structure - Most follow-up calls depend on correct `project_id`; verify with `GITLAB_GET_PROJECT` first - Invalid `branch_name`/`ref`/`sha` causes client errors; verify branch existence via `GITLAB_GET_REPOSITORY_BRANCHES` first - Both `name` and `path` are required for `GITLAB_CREATE_PROJECT` ### 4. Monitor CI/CD Pipelines **When to use**: User wants to check pipeline status, list jobs, or monitor CI/CD runs **Tool sequence**: 1. `GITLAB_GET_PROJECT` - Verify project access [Prerequisite] 2. `GITLAB_LIST_PROJECT_PIPELINES` - List pipelines with filters [Required] 3. `GITLAB_GET_SINGLE_PIPELINE` - Get detailed info for a specific pipeline [Optional] 4. `GITLAB_LIST_PIPELINE_JOBS` - List jobs within a pipeline [Optional] **Key parameters**: - `id`: Project ID or URL-encoded path - `status`: Filter by `"created"`, `"waiting_for_resource"`, `"preparing"`, `"pending"`, `"running"`, `"success"`, `"failed"`, `"canceled"`, `"skipped"`, `"manual"`, `"scheduled"` - `scope`: `"running"`, `"pending"`, `"finished"`, `"branches"`, `"tags"` - `ref`: Branch or tag name - `sha`: Specific commit SHA - `source`: Pipeline source (use `"parent_pipeline"` for child pipelines) - `order_by`: `"id"` (default), `"status"`, `"ref"`, `"updated_at"`, `"user_id"` - `created_after` / `created_before`: ISO 8601 date filters - `pipeline_id`: Specific pipeline ID for job listing - `include_retried`: `true` to include retried jobs (default `false`) **Pitfalls**: - Large pipeline histories can be noisy; use `status`, `ref`, and date filters to narrow results - Use moderate `per_page` values to keep output manageable - Pipeline job `scope` accepts single status string or array of statuses - `yaml_errors: true` returns only pipelines with invalid configurations ### 5. Manage Users and Members **When to use**: User wants to find users, list project members, or check user status **Tool sequence**: 1. `GITLAB_GET_USERS` - Sea
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.