GitLab Automation via Rube MCP
Overview
This public intake copy packages plugins/antigravity-awesome-skills-claude/skills/gitlab-automation from https://github.com/sickn33/antigravity-awesome-skills into the native Omni Skills editorial shape without hiding its origin.
Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.
This intake keeps the copied upstream files intact and uses the external_source block in metadata.json plus ORIGIN.md as the provenance anchor for review.
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.
Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Prerequisites, Common Patterns, Known Pitfalls, Limitations.
When to Use This Skill
Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.
- This skill is applicable to execute the workflow or actions described in the overview.
- Use when the request clearly matches the imported source intent: Automate GitLab project management, issues, merge requests, pipelines, branches, and user operations via Rube MCP (Composio). Always search tools first for current schemas.
- Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.
- Use when provenance needs to stay visible in the answer, PR, or review packet.
- Use when copied upstream references, examples, or scripts materially improve the answer.
- Use when the workflow should remain reviewable in the public intake repo before the private enhancer takes over.
Operating Table
| Situation |
Start here |
Why it matters |
| First-time use |
metadata.json |
Confirms repository, branch, commit, and imported path through the external_source block before touching the copied workflow |
| Provenance review |
ORIGIN.md |
Gives reviewers a plain-language audit trail for the imported source |
| Workflow execution |
SKILL.md |
Starts with the smallest copied file that materially changes execution |
| Supporting context |
SKILL.md |
Adds the next most relevant copied source file without loading the entire package |
| Handoff decision |
## Related Skills |
Helps the operator switch to a stronger native skill when the task drifts |
Workflow
This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.
- Verify Rube MCP is available by confirming RUBESEARCHTOOLS responds
- Call RUBEMANAGECONNECTIONS with toolkit gitlab
- If connection is not ACTIVE, follow the returned auth link to complete GitLab OAuth
- Confirm connection status shows ACTIVE before running any workflows
- GITLABGETPROJECTS - Find the target project and get its ID [Prerequisite]
- GITLABLISTPROJECT_ISSUES - List and filter issues for a project [Required]
- GITLABCREATEPROJECT_ISSUE - Create a new issue [Required for create]
Imported Workflow Notes
Imported: 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.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLS responds
- Call
RUBE_MANAGE_CONNECTIONS with toolkit gitlab
- If connection is not ACTIVE, follow the returned auth link to complete GitLab OAuth
- Confirm connection status shows ACTIVE before running any workflows
Imported: Core Workflows
1. Manage Issues
When to use: User wants to create, update, list, or search issues in a GitLab project
Tool sequence:
GITLAB_GET_PROJECTS - Find the target project and get its ID [Prerequisite]
GITLAB_LIST_PROJECT_ISSUES - List and filter issues for a project [Required]
GITLAB_CREATE_PROJECT_ISSUE - Create a new issue [Required for create]
GITLAB_UPDATE_PROJECT_ISSUE - Update an existing issue (title, labels, state, assignees) [Required for update]
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:
GITLAB_GET_PROJECT - Get project details and verify access [Prerequisite]
GITLAB_GET_PROJECT_MERGE_REQUESTS - List and filter merge requests [Required]
GITLAB_GET_REPOSITORY_BRANCHES - Verify source/target branches [Optional]
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:
GITLAB_GET_PROJECTS - List all accessible projects with filters [Required]
GITLAB_GET_PROJECT - Get detailed info for a specific project [Optional]
GITLAB_LIST_USER_PROJECTS - List projects owned by a specific user [Optional]
GITLAB_CREATE_PROJECT - Create a new project [Required for create]
GITLAB_GET_REPOSITORY_BRANCHES - List branches in a project [Required for branch ops]
GITLAB_CREATE_REPOSITORY_BRANCH - Create a new branch [Optional]
GITLAB_GET_REPOSITORY_BRANCH - Get details of a specific branch [Optional]
GITLAB_LIST_REPOSITORY_COMMITS - View commit history [Optional]
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:
GITLAB_GET_PROJECT - Verify project access [Prerequisite]
GITLAB_LIST_PROJECT_PIPELINES - List pipelines with filters [Required]
GITLAB_GET_SINGLE_PIPELINE - Get detailed info for a specific pipeline [Optional]
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:
GITLAB_GET_USERS - Search and list GitLab users [Required]
GITLAB_GET_USER - Get details for a specific user by ID [Optional]
GITLAB_GET_USERS_ID_STATUS - Get user status message and availability [Optional]
GITLAB_LIST_ALL_PROJECT_MEMBERS - List all project members (direct + inherited) [Required for member listing]
GITLAB_LIST_PROJECT_USERS - List project users with search filter [Optional]
Key parameters:
search: Search by name, username, or public email
username: Get specific user by username
active / blocked: Filter by user state
id: Project ID for member listing
query: Filter members by name, email, or username
state: Filter members by "awaiting" or "active" (Premium/Ultimate)
user_ids: Filter by specific user IDs
Pitfalls:
- Many user filters (admins, auditors, extern_uid, two_factor) are admin-only
GITLAB_LIST_ALL_PROJECT_MEMBERS includes direct, inherited, and invited members
- User search is case-insensitive but may not match partial email domains
- Premium/Ultimate features (state filter, seat info) are not available on free plans
Imported: 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
Examples
Example 1: Ask for the upstream workflow directly
Use @gitlab-automation to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.
Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.
Example 2: Ask for a provenance-grounded review
Review @gitlab-automation against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.
Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.
Example 3: Narrow the copied support files before execution
Use @gitlab-automation for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.
Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.
Example 4: Build a reviewer packet
Review @gitlab-automation using the copied upstream files plus provenance, then summarize any gaps before merge.
Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.
Best Practices
Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.
- Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
- Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
- Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
- Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
- Treat generated examples as scaffolding; adapt them to the concrete task before execution.
- Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.
Troubleshooting
Problem: The operator skipped the imported context and answered too generically
Symptoms: The result ignores the upstream workflow in plugins/antigravity-awesome-skills-claude/skills/gitlab-automation, fails to mention provenance, or does not use any copied source files at all.
Solution: Re-open metadata.json, ORIGIN.md, and the most relevant copied upstream files. Check the external_source block first, then restate the provenance before continuing.
Problem: The imported workflow feels incomplete during review
Symptoms: Reviewers can see the generated SKILL.md, but they cannot quickly tell which references, examples, or scripts matter for the current task.
Solution: Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.
Problem: The task drifted into a different specialization
Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better.
Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.
Related Skills
@00-andruia-consultant - Use when the work is better handled by that native specialization after this imported skill establishes context.
@00-andruia-consultant-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
@10-andruia-skill-smith - Use when the work is better handled by that native specialization after this imported skill establishes context.
@10-andruia-skill-smith-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
Additional Resources
Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.
| Resource family |
What it gives the reviewer |
Example path |
references |
copied reference notes, guides, or background material from upstream |
references/n/a |
examples |
worked examples or reusable prompts copied from upstream |
examples/n/a |
scripts |
upstream helper scripts that change execution or validation |
scripts/n/a |
agents |
routing or delegation notes that are genuinely part of the imported package |
agents/n/a |
assets |
supporting assets or schemas copied from the source package |
assets/n/a |
Imported Reference Notes
Imported: Quick Reference
| Task |
Tool Slug |
Key Params |
| List projects |
GITLAB_GET_PROJECTS |
search, membership, visibility |
| Get project details |
GITLAB_GET_PROJECT |
id |
| User's projects |
GITLAB_LIST_USER_PROJECTS |
id, search, owned |
| Create project |
GITLAB_CREATE_PROJECT |
name, path, visibility |
| List issues |
GITLAB_LIST_PROJECT_ISSUES |
id, state, labels, search |
| Create issue |
GITLAB_CREATE_PROJECT_ISSUE |
id, title, description, labels |
| Update issue |
GITLAB_UPDATE_PROJECT_ISSUE |
id, issue_iid, state_event |
| List merge requests |
GITLAB_GET_PROJECT_MERGE_REQUESTS |
id, state, scope, labels |
| List branches |
GITLAB_GET_REPOSITORY_BRANCHES |
project_id, search |
| Get branch |
GITLAB_GET_REPOSITORY_BRANCH |
project_id, branch_name |
| Create branch |
GITLAB_CREATE_REPOSITORY_BRANCH |
project_id, branch_name, ref |
| List commits |
GITLAB_LIST_REPOSITORY_COMMITS |
project ID, branch ref |
| Project languages |
GITLAB_GET_PROJECT_LANGUAGES |
project ID |
| List pipelines |
GITLAB_LIST_PROJECT_PIPELINES |
id, status, ref |
| Get pipeline |
GITLAB_GET_SINGLE_PIPELINE |
project_id, pipeline_id |
| List pipeline jobs |
GITLAB_LIST_PIPELINE_JOBS |
id, pipeline_id, scope |
| Search users |
GITLAB_GET_USERS |
search, username, active |
| Get user |
GITLAB_GET_USER |
user ID |
| User status |
GITLAB_GET_USERS_ID_STATUS |
user ID |
| List project members |
GITLAB_LIST_ALL_PROJECT_MEMBERS |
id, query, state |
| List project users |
GITLAB_LIST_PROJECT_USERS |
id, search |
Imported: Common Patterns
ID Resolution
GitLab uses two identifier formats for projects:
- Numeric ID: Integer project ID (e.g.,
123)
- URL-encoded path: Namespace/project format (e.g.,
"my-group%2Fmy-project" or "my-group/my-project")
- Issue IID vs ID:
issue_iid is the project-internal number (#42); the global id is different
- User ID: Numeric; resolve via
GITLAB_GET_USERS with search or username
Pagination
GitLab uses offset-based pagination:
- Set
page (starting at 1) and per_page (1-100, default 20)
- Continue incrementing
page until response returns fewer items than per_page or is empty
- Total count may be available in response headers (
X-Total, X-Total-Pages)
- Always paginate to completion for accurate results
URL-Encoded Paths
When using project paths as identifiers:
- Forward slashes must be URL-encoded:
my-group/my-project becomes my-group%2Fmy-project
- Some tools accept unencoded paths; check schema for each tool
- Prefer numeric IDs when available for reliability
Imported: Known Pitfalls
ID Formats
- Project
id field accepts both integer and string (URL-encoded path)
- Issue
issue_iid is project-scoped; do not confuse with global issue ID
- Pipeline IDs are project-scoped integers
- User IDs are global integers across the GitLab instance
Rate Limits
- GitLab has per-user rate limits (typically 300-2000 requests/minute depending on plan)
- Large pipeline/issue histories should use date and status filters to reduce result sets
- Paginate responsibly with moderate
per_page values
Parameter Quirks
labels field replaces ALL labels; use add_labels/remove_labels for incremental changes
assignee_ids: [0] unassigns all; empty array does nothing
scope defaults vary: "created_by_me" for MRs, "all" for issues
author_id and author_username are mutually exclusive in MR filters
- Date parameters use ISO 8601 format:
"2024-01-15T10:30:00Z"
Plan Restrictions
- Some features require Premium/Ultimate:
epic_id, weight, iteration_id, approved_by_ids, member state filter
- Admin-only features: user management filters,
updated_at override, custom attributes
- The
mr_approved_filter feature flag is disabled by default
Imported: Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
1---2name: gitlab-automation-33description: "GitLab Automation via Rube MCP workflow skill. Use this skill when the user needs Automate GitLab project management, issues, merge requests, pipelines, branches, and user operations via Rube MCP (Composio). Always search tools first for current schemas and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off."4version: "0.0.1"5category: "cli-automation"6tags:7 - "gitlab-automation"8 - "automate"9 - "gitlab"10 - "project"11 - "management"12 - "issues"13 - "merge"14 - "requests"15 - "omni-enhanced"16complexity: "advanced"17risk: "caution"18tools:19 - "codex-cli"20 - "claude-code"21 - "cursor"22 - "gemini-cli"23 - "opencode"24source: "omni-team"25author: "Omni Skills Team"26date_added: "2026-04-15"27date_updated: "2026-05-10"28source_type: "omni-curated"29maintainer: "Omni Skills Team"30family_id: "gitlab-automation"31family_name: "GitLab Automation via Rube MCP"32variant_id: "omni"33variant_label: "Omni Curated"34is_default_variant: true35derived_from: "skills/gitlab-automation"36upstream_skill: "skills/gitlab-automation"37upstream_author: "sickn33"38upstream_source: "community"39upstream_pr: "271"40upstream_head_repo: "diegosouzapw/awesome-omni-skills"41upstream_head_sha: "93ab394af5645f7127d5003ee02c9566ae5353cd"42curation_surface: "skills_omni"43enhanced_origin: "omni-skills-private"44source_repo: "diegosouzapw/awesome-omni-skills"45replaces:46 - "gitlab-automation"47metadata:48 source: https://skillmd.com/skills/diegosouzapw/gitlab-automation-349---5051# GitLab Automation via Rube MCP5253## Overview5455This public intake copy packages `plugins/antigravity-awesome-skills-claude/skills/gitlab-automation` from `https://github.com/sickn33/antigravity-awesome-skills` into the native Omni Skills editorial shape without hiding its origin.5657Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.5859This intake keeps the copied upstream files intact and uses the `external_source` block in `metadata.json` plus `ORIGIN.md` as the provenance anchor for review.6061# 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.6263Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Prerequisites, Common Patterns, Known Pitfalls, Limitations.6465## When to Use This Skill6667Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.6869- This skill is applicable to execute the workflow or actions described in the overview.70- Use when the request clearly matches the imported source intent: Automate GitLab project management, issues, merge requests, pipelines, branches, and user operations via Rube MCP (Composio). Always search tools first for current schemas.71- Use when the operator should preserve upstream workflow detail instead of rewriting the process from scratch.72- Use when provenance needs to stay visible in the answer, PR, or review packet.73- Use when copied upstream references, examples, or scripts materially improve the answer.74- Use when the workflow should remain reviewable in the public intake repo before the private enhancer takes over.7576## Operating Table7778| Situation | Start here | Why it matters |79| --- | --- | --- |80| First-time use | `metadata.json` | Confirms repository, branch, commit, and imported path through the `external_source` block before touching the copied workflow |81| Provenance review | `ORIGIN.md` | Gives reviewers a plain-language audit trail for the imported source |82| Workflow execution | `SKILL.md` | Starts with the smallest copied file that materially changes execution |83| Supporting context | `SKILL.md` | Adds the next most relevant copied source file without loading the entire package |84| Handoff decision | `## Related Skills` | Helps the operator switch to a stronger native skill when the task drifts |8586## Workflow8788This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.89901. Verify Rube MCP is available by confirming RUBESEARCHTOOLS responds912. Call RUBEMANAGECONNECTIONS with toolkit gitlab923. If connection is not ACTIVE, follow the returned auth link to complete GitLab OAuth934. Confirm connection status shows ACTIVE before running any workflows945. GITLABGETPROJECTS - Find the target project and get its ID [Prerequisite]956. GITLABLISTPROJECT_ISSUES - List and filter issues for a project [Required]967. GITLABCREATEPROJECT_ISSUE - Create a new issue [Required for create]9798### Imported Workflow Notes99100#### Imported: Setup101102**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.1031041. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds1052. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `gitlab`1063. If connection is not ACTIVE, follow the returned auth link to complete GitLab OAuth1074. Confirm connection status shows ACTIVE before running any workflows108109#### Imported: Core Workflows110111### 1. Manage Issues112113**When to use**: User wants to create, update, list, or search issues in a GitLab project114115**Tool sequence**:1161. `GITLAB_GET_PROJECTS` - Find the target project and get its ID [Prerequisite]1172. `GITLAB_LIST_PROJECT_ISSUES` - List and filter issues for a project [Required]1183. `GITLAB_CREATE_PROJECT_ISSUE` - Create a new issue [Required for create]1194. `GITLAB_UPDATE_PROJECT_ISSUE` - Update an existing issue (title, labels, state, assignees) [Required for update]1205. `GITLAB_LIST_PROJECT_USERS` - Find user IDs for assignment [Optional]121122**Key parameters**:123- `id`: Project ID (integer) or URL-encoded path (e.g., `"my-group/my-project"`)124- `title`: Issue title (required for creation)125- `description`: Issue body text (max 1,048,576 characters)126- `labels`: Comma-separated label names (e.g., `"bug,critical"`)127- `add_labels` / `remove_labels`: Add or remove labels without replacing all128- `state`: Filter by `"all"`, `"opened"`, or `"closed"`129- `state_event`: `"close"` or `"reopen"` to change issue state130- `assignee_ids`: Array of user IDs; use `[0]` to unassign all131- `issue_iid`: Internal issue ID within the project (required for updates)132- `milestone`: Filter by milestone title133- `search`: Search in title and description134- `scope`: `"created_by_me"`, `"assigned_to_me"`, or `"all"`135- `page` / `per_page`: Pagination (default per_page: 20)136137**Pitfalls**:138- `id` accepts either integer project ID or URL-encoded path; wrong IDs yield 4xx errors139- `issue_iid` is the project-internal ID (shown as #42), different from the global issue ID140- Labels in `labels` field replace ALL existing labels; use `add_labels`/`remove_labels` for incremental changes141- Setting `assignee_ids` to empty array does NOT unassign; use `[0]` instead142- `updated_at` field requires administrator or project/group owner rights143144### 2. Manage Merge Requests145146**When to use**: User wants to list, filter, or review merge requests in a project147148**Tool sequence**:1491. `GITLAB_GET_PROJECT` - Get project details and verify access [Prerequisite]1502. `GITLAB_GET_PROJECT_MERGE_REQUESTS` - List and filter merge requests [Required]1513. `GITLAB_GET_REPOSITORY_BRANCHES` - Verify source/target branches [Optional]1524. `GITLAB_LIST_ALL_PROJECT_MEMBERS` - Find reviewers/assignees [Optional]153154**Key parameters**:155- `id`: Project ID or URL-encoded path156- `state`: `"opened"`, `"closed"`, `"locked"`, `"merged"`, or `"all"`157- `scope`: `"created_by_me"` (default), `"assigned_to_me"`, or `"all"`158- `source_branch` / `target_branch`: Filter by branch names159- `author_id` / `author_username`: Filter by MR author160- `assignee_id`: Filter by assignee (use `None` for unassigned, `Any` for assigned)161- `reviewer_id` / `reviewer_username`: Filter by reviewer162- `labels`: Comma-separated label filter163- `search`: Search in title and description164- `wip`: `"yes"` for draft MRs, `"no"` for non-draft165- `order_by`: `"created_at"` (default), `"title"`, `"merged_at"`, `"updated_at"`166- `view`: `"simple"` for minimal fields167- `iids[]`: Filter by specific MR internal IDs168169**Pitfalls**:170- Default `scope` is `"created_by_me"` which limits results; use `"all"` for complete listings171- `author_id` and `author_username` are mutually exclusive172- `reviewer_id` and `reviewer_username` are mutually exclusive173- `approved` filter requires the `mr_approved_filter` feature flag (disabled by default)174- Large MR histories can be noisy; use filters and moderate `per_page` values175176### 3. Manage Projects and Repositories177178**When to use**: User wants to list projects, create new projects, or manage branches179180**Tool sequence**:1811. `GITLAB_GET_PROJECTS` - List all accessible projects with filters [Required]1822. `GITLAB_GET_PROJECT` - Get detailed info for a specific project [Optional]1833. `GITLAB_LIST_USER_PROJECTS` - List projects owned by a specific user [Optional]1844. `GITLAB_CREATE_PROJECT` - Create a new project [Required for create]1855. `GITLAB_GET_REPOSITORY_BRANCHES` - List branches in a project [Required for branch ops]1866. `GITLAB_CREATE_REPOSITORY_BRANCH` - Create a new branch [Optional]1877. `GITLAB_GET_REPOSITORY_BRANCH` - Get details of a specific branch [Optional]1888. `GITLAB_LIST_REPOSITORY_COMMITS` - View commit history [Optional]1899. `GITLAB_GET_PROJECT_LANGUAGES` - Get language breakdown [Optional]190191**Key parameters**:192- `name` / `path`: Project name and URL-friendly path (both required for creation)193- `visibility`: `"private"`, `"internal"`, or `"public"`194- `namespace_id`: Group or user ID for project placement195- `search`: Case-insensitive substring search for projects196- `membership`: `true` to limit to projects user is a member of197- `owned`: `true` to limit to user-owned projects198- `project_id`: Project ID for branch operations199- `branch_name`: Name for new branch200- `ref`: Source branch or commit SHA for new branch creation201- `order_by`: `"id"`, `"name"`, `"path"`, `"created_at"`, `"updated_at"`, `"star_count"`, `"last_activity_at"`202203**Pitfalls**:204- `GITLAB_GET_PROJECTS` pagination is required for complete coverage; stopping at first page misses projects205- Some responses place items under `data.details`; parse the actual returned list structure206- Most follow-up calls depend on correct `project_id`; verify with `GITLAB_GET_PROJECT` first207- Invalid `branch_name`/`ref`/`sha` causes client errors; verify branch existence via `GITLAB_GET_REPOSITORY_BRANCHES` first208- Both `name` and `path` are required for `GITLAB_CREATE_PROJECT`209210### 4. Monitor CI/CD Pipelines211212**When to use**: User wants to check pipeline status, list jobs, or monitor CI/CD runs213214**Tool sequence**:2151. `GITLAB_GET_PROJECT` - Verify project access [Prerequisite]2162. `GITLAB_LIST_PROJECT_PIPELINES` - List pipelines with filters [Required]2173. `GITLAB_GET_SINGLE_PIPELINE` - Get detailed info for a specific pipeline [Optional]2184. `GITLAB_LIST_PIPELINE_JOBS` - List jobs within a pipeline [Optional]219220**Key parameters**:221- `id`: Project ID or URL-encoded path222- `status`: Filter by `"created"`, `"waiting_for_resource"`, `"preparing"`, `"pending"`, `"running"`, `"success"`, `"failed"`, `"canceled"`, `"skipped"`, `"manual"`, `"scheduled"`223- `scope`: `"running"`, `"pending"`, `"finished"`, `"branches"`, `"tags"`224- `ref`: Branch or tag name225- `sha`: Specific commit SHA226- `source`: Pipeline source (use `"parent_pipeline"` for child pipelines)227- `order_by`: `"id"` (default), `"status"`, `"ref"`, `"updated_at"`, `"user_id"`228- `created_after` / `created_before`: ISO 8601 date filters229- `pipeline_id`: Specific pipeline ID for job listing230- `include_retried`: `true` to include retried jobs (default `false`)231232**Pitfalls**:233- Large pipeline histories can be noisy; use `status`, `ref`, and date filters to narrow results234- Use moderate `per_page` values to keep output manageable235- Pipeline job `scope` accepts single status string or array of statuses236- `yaml_errors: true` returns only pipelines with invalid configurations237238### 5. Manage Users and Members239240**When to use**: User wants to find users, list project members, or check user status241242**Tool sequence**:2431. `GITLAB_GET_USERS` - Search and list GitLab users [Required]2442. `GITLAB_GET_USER` - Get details for a specific user by ID [Optional]2453. `GITLAB_GET_USERS_ID_STATUS` - Get user status message and availability [Optional]2464. `GITLAB_LIST_ALL_PROJECT_MEMBERS` - List all project members (direct + inherited) [Required for member listing]2475. `GITLAB_LIST_PROJECT_USERS` - List project users with search filter [Optional]248249**Key parameters**:250- `search`: Search by name, username, or public email251- `username`: Get specific user by username252- `active` / `blocked`: Filter by user state253- `id`: Project ID for member listing254- `query`: Filter members by name, email, or username255- `state`: Filter members by `"awaiting"` or `"active"` (Premium/Ultimate)256- `user_ids`: Filter by specific user IDs257258**Pitfalls**:259- Many user filters (admins, auditors, extern_uid, two_factor) are admin-only260- `GITLAB_LIST_ALL_PROJECT_MEMBERS` includes direct, inherited, and invited members261- User search is case-insensitive but may not match partial email domains262- Premium/Ultimate features (state filter, seat info) are not available on free plans263264#### Imported: Prerequisites265266- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)267- Active GitLab connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `gitlab`268- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas269270## Examples271272### Example 1: Ask for the upstream workflow directly273274```text275Use @gitlab-automation to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.276```277278**Explanation:** This is the safest starting point when the operator needs the imported workflow, but not the entire repository.279280### Example 2: Ask for a provenance-grounded review281282```text283Review @gitlab-automation against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.284```285286**Explanation:** Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.287288### Example 3: Narrow the copied support files before execution289290```text291Use @gitlab-automation for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.292```293294**Explanation:** This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.295296### Example 4: Build a reviewer packet297298```text299Review @gitlab-automation using the copied upstream files plus provenance, then summarize any gaps before merge.300```301302**Explanation:** This is useful when the PR is waiting for human review and you want a repeatable audit packet.303304305306## Best Practices307308Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.309310- Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.311- Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.312- Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.313- Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.314- Treat generated examples as scaffolding; adapt them to the concrete task before execution.315- Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.316317318319## Troubleshooting320321### Problem: The operator skipped the imported context and answered too generically322323**Symptoms:** The result ignores the upstream workflow in `plugins/antigravity-awesome-skills-claude/skills/gitlab-automation`, fails to mention provenance, or does not use any copied source files at all.324**Solution:** Re-open `metadata.json`, `ORIGIN.md`, and the most relevant copied upstream files. Check the `external_source` block first, then restate the provenance before continuing.325326### Problem: The imported workflow feels incomplete during review327328**Symptoms:** Reviewers can see the generated `SKILL.md`, but they cannot quickly tell which references, examples, or scripts matter for the current task.329**Solution:** Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.330331### Problem: The task drifted into a different specialization332333**Symptoms:** The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better.334**Solution:** Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.335336337338## Related Skills339340- `@00-andruia-consultant` - Use when the work is better handled by that native specialization after this imported skill establishes context.341- `@00-andruia-consultant-v2` - Use when the work is better handled by that native specialization after this imported skill establishes context.342- `@10-andruia-skill-smith` - Use when the work is better handled by that native specialization after this imported skill establishes context.343- `@10-andruia-skill-smith-v2` - Use when the work is better handled by that native specialization after this imported skill establishes context.344345## Additional Resources346347Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.348349| Resource family | What it gives the reviewer | Example path |350| --- | --- | --- |351| `references` | copied reference notes, guides, or background material from upstream | `references/n/a` |352| `examples` | worked examples or reusable prompts copied from upstream | `examples/n/a` |353| `scripts` | upstream helper scripts that change execution or validation | `scripts/n/a` |354| `agents` | routing or delegation notes that are genuinely part of the imported package | `agents/n/a` |355| `assets` | supporting assets or schemas copied from the source package | `assets/n/a` |356357358359### Imported Reference Notes360361#### Imported: Quick Reference362363| Task | Tool Slug | Key Params |364|------|-----------|------------|365| List projects | `GITLAB_GET_PROJECTS` | `search`, `membership`, `visibility` |366| Get project details | `GITLAB_GET_PROJECT` | `id` |367| User's projects | `GITLAB_LIST_USER_PROJECTS` | `id`, `search`, `owned` |368| Create project | `GITLAB_CREATE_PROJECT` | `name`, `path`, `visibility` |369| List issues | `GITLAB_LIST_PROJECT_ISSUES` | `id`, `state`, `labels`, `search` |370| Create issue | `GITLAB_CREATE_PROJECT_ISSUE` | `id`, `title`, `description`, `labels` |371| Update issue | `GITLAB_UPDATE_PROJECT_ISSUE` | `id`, `issue_iid`, `state_event` |372| List merge requests | `GITLAB_GET_PROJECT_MERGE_REQUESTS` | `id`, `state`, `scope`, `labels` |373| List branches | `GITLAB_GET_REPOSITORY_BRANCHES` | `project_id`, `search` |374| Get branch | `GITLAB_GET_REPOSITORY_BRANCH` | `project_id`, `branch_name` |375| Create branch | `GITLAB_CREATE_REPOSITORY_BRANCH` | `project_id`, `branch_name`, `ref` |376| List commits | `GITLAB_LIST_REPOSITORY_COMMITS` | project ID, branch ref |377| Project languages | `GITLAB_GET_PROJECT_LANGUAGES` | project ID |378| List pipelines | `GITLAB_LIST_PROJECT_PIPELINES` | `id`, `status`, `ref` |379| Get pipeline | `GITLAB_GET_SINGLE_PIPELINE` | `project_id`, `pipeline_id` |380| List pipeline jobs | `GITLAB_LIST_PIPELINE_JOBS` | `id`, `pipeline_id`, `scope` |381| Search users | `GITLAB_GET_USERS` | `search`, `username`, `active` |382| Get user | `GITLAB_GET_USER` | user ID |383| User status | `GITLAB_GET_USERS_ID_STATUS` | user ID |384| List project members | `GITLAB_LIST_ALL_PROJECT_MEMBERS` | `id`, `query`, `state` |385| List project users | `GITLAB_LIST_PROJECT_USERS` | `id`, `search` |386387#### Imported: Common Patterns388389### ID Resolution390GitLab uses two identifier formats for projects:391- **Numeric ID**: Integer project ID (e.g., `123`)392- **URL-encoded path**: Namespace/project format (e.g., `"my-group%2Fmy-project"` or `"my-group/my-project"`)393- **Issue IID vs ID**: `issue_iid` is the project-internal number (#42); the global `id` is different394- **User ID**: Numeric; resolve via `GITLAB_GET_USERS` with `search` or `username`395396### Pagination397GitLab uses offset-based pagination:398- Set `page` (starting at 1) and `per_page` (1-100, default 20)399- Continue incrementing `page` until response returns fewer items than `per_page` or is empty400- Total count may be available in response headers (`X-Total`, `X-Total-Pages`)401- Always paginate to completion for accurate results402403### URL-Encoded Paths404When using project paths as identifiers:405- Forward slashes must be URL-encoded: `my-group/my-project` becomes `my-group%2Fmy-project`406- Some tools accept unencoded paths; check schema for each tool407- Prefer numeric IDs when available for reliability408409#### Imported: Known Pitfalls410411### ID Formats412- Project `id` field accepts both integer and string (URL-encoded path)413- Issue `issue_iid` is project-scoped; do not confuse with global issue ID414- Pipeline IDs are project-scoped integers415- User IDs are global integers across the GitLab instance416417### Rate Limits418- GitLab has per-user rate limits (typically 300-2000 requests/minute depending on plan)419- Large pipeline/issue histories should use date and status filters to reduce result sets420- Paginate responsibly with moderate `per_page` values421422### Parameter Quirks423- `labels` field replaces ALL labels; use `add_labels`/`remove_labels` for incremental changes424- `assignee_ids: [0]` unassigns all; empty array does nothing425- `scope` defaults vary: `"created_by_me"` for MRs, `"all"` for issues426- `author_id` and `author_username` are mutually exclusive in MR filters427- Date parameters use ISO 8601 format: `"2024-01-15T10:30:00Z"`428429### Plan Restrictions430- Some features require Premium/Ultimate: `epic_id`, `weight`, `iteration_id`, `approved_by_ids`, member `state` filter431- Admin-only features: user management filters, `updated_at` override, custom attributes432- The `mr_approved_filter` feature flag is disabled by default433434#### Imported: Limitations435436- Use this skill only when the task clearly matches the scope described above.437- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.438- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.