google-drive-automation
Automate Google Drive file operations (upload, download, search, share, organize) via Rube MCP (Composio). Upload/download files, manage folders, share with permissions, and search across drives programmatically.
What this skill does
# Google Drive Automation via Rube MCP
Automate Google Drive workflows including file upload/download, search, folder management, sharing/permissions, and organization through Composio's Google Drive toolkit.
## Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Google Drive connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `googledrive`
- 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 `googledrive`
3. If connection is not ACTIVE, follow the returned auth link to complete Google OAuth
4. Confirm connection status shows ACTIVE before running any workflows
## Core Workflows
### 1. Upload and Download Files
**When to use**: User wants to upload files to or download files from Google Drive
**Tool sequence**:
1. `GOOGLEDRIVE_FIND_FILE` - Locate target folder for upload [Prerequisite]
2. `GOOGLEDRIVE_UPLOAD_FILE` - Upload a file (max 5MB) [Required]
3. `GOOGLEDRIVE_RESUMABLE_UPLOAD` - Upload large files [Fallback]
4. `GOOGLEDRIVE_DOWNLOAD_FILE` - Download a file by ID [Required]
5. `GOOGLEDRIVE_DOWNLOAD_FILE_OPERATION` - Track long-running downloads [Fallback]
6. `GOOGLEDRIVE_GET_FILE_METADATA` - Verify file after upload/download [Optional]
**Key parameters**:
- `file_to_upload`: Object with `name`, `mimetype`, and `s3key` (file must be in internal storage)
- `folder_to_upload_to`: Target folder ID (optional; uploads to root if omitted)
- `file_id`: ID of file to download
- `mime_type`: Export format for Google Workspace files only (omit for native files)
**Pitfalls**:
- `GOOGLEDRIVE_UPLOAD_FILE` requires `file_to_upload.s3key`; files must already be in internal storage
- For non-Google formats (Excel, PDF), do NOT set `mime_type`; it causes errors for native files
- Download responses provide a temporary URL at `data.downloaded_file_content.s3url`, not inline bytes
- Use `GOOGLEDRIVE_RESUMABLE_UPLOAD` for files >5MB or when basic uploads fail
### 2. Search and List Files
**When to use**: User wants to find specific files or browse Drive contents
**Tool sequence**:
1. `GOOGLEDRIVE_FIND_FILE` - Search by name, content, type, date, or folder [Required]
2. `GOOGLEDRIVE_LIST_FILES` - Browse files with folder scoping [Alternative]
3. `GOOGLEDRIVE_LIST_SHARED_DRIVES` - Enumerate shared drives [Optional]
4. `GOOGLEDRIVE_GET_FILE_METADATA` - Get detailed file info [Optional]
5. `GOOGLEDRIVE_GET_ABOUT` - Check storage quota and supported formats [Optional]
**Key parameters**:
- `q`: Drive query string (e.g., "name contains 'report'", "mimeType = 'application/pdf'")
- `corpora`: Search scope ('user', 'domain', 'drive', 'allDrives')
- `fields`: Response fields to include (e.g., 'files(id,name,mimeType)')
- `orderBy`: Sort key ('modifiedTime desc', 'name', 'quotaBytesUsed desc')
- `pageSize`: Results per page (max 1000)
- `pageToken`: Pagination cursor from `nextPageToken`
- `folder_id`: Scope search to a specific folder
**Pitfalls**:
- 403 PERMISSION_DENIED if OAuth scopes insufficient for shared drives
- Pagination required; files are in `response.data.files`; follow `nextPageToken` until exhausted
- `corpora="domain"` may trigger 400; try `"allDrives"` with `includeItemsFromAllDrives=true`
- Query complexity limits: >5-10 OR clauses may error "The query is too complex"
- Wildcards (*) NOT supported in `name`; use `contains` for partial matching
- 'My Drive' is NOT searchable by name; use `folder_id='root'` for root folder
- User email searches: use `'[email protected]' in owners` (NOT `owner:[email protected]`)
### 3. Share Files and Manage Permissions
**When to use**: User wants to share files or manage access permissions
**Tool sequence**:
1. `GOOGLEDRIVE_FIND_FILE` - Locate the file to share [Prerequisite]
2. `GOOGLEDRIVE_ADD_FILE_SHARING_PREFERENCE` - Set sharing permission [Required]
3. `GOOGLEDRIVE_LIST_PERMISSIONS` - View current permissions [Optional]
4. `GOOGLEDRIVE_GET_PERMISSION` - Inspect a specific permission [Optional]
5. `GOOGLEDRIVE_UPDATE_PERMISSION` - Modify existing permission [Optional]
6. `GOOGLEDRIVE_DELETE_PERMISSION` - Revoke access [Optional]
**Key parameters**:
- `file_id`: ID of file to share
- `type`: 'user', 'group', 'domain', or 'anyone'
- `role`: 'owner', 'organizer', 'fileOrganizer', 'writer', 'commenter', 'reader'
- `email_address`: Required for type='user' or 'group'
- `domain`: Required for type='domain'
- `transfer_ownership`: Required when role='owner'
**Pitfalls**:
- Invalid type/email combinations trigger 4xx errors
- Using `type='anyone'` or powerful roles is risky; get explicit user confirmation
- Org policies may block certain sharing types, causing 403
- Permission changes may take time to propagate
- Use `GMAIL_SEARCH_PEOPLE` to resolve contact names to emails before sharing
### 4. Create and Organize Folders
**When to use**: User wants to create folder structures or move files between folders
**Tool sequence**:
1. `GOOGLEDRIVE_FIND_FILE` - Check if folder already exists [Prerequisite]
2. `GOOGLEDRIVE_CREATE_FOLDER` - Create a new folder [Required]
3. `GOOGLEDRIVE_GET_FILE_METADATA` - Verify created folder [Optional]
4. `GOOGLEDRIVE_MOVE_FILE` - Move files between folders [Optional]
5. `GOOGLEDRIVE_UPDATE_FILE_PUT` - Update file metadata/parents [Alternative]
**Key parameters**:
- `name`: Folder name
- `parent_id`: Parent folder ID (NOT name); omit for root
- `file_id`: File to move
- `add_parents`: Destination folder ID for move
- `remove_parents`: Source folder ID to remove from
**Pitfalls**:
- `GOOGLEDRIVE_CREATE_FOLDER` requires `parent_id` as an ID, not a folder name
- Using `parent_id="root"` creates at top level; for nested paths, chain folder IDs
- `GOOGLEDRIVE_FIND_FILE` returns ~100 items/page; follow `nextPageToken` for large drives
- Move operations can leave items with multiple parents; use `remove_parents` for true moves
- Always verify parent folder exists before creating children
## Common Patterns
### ID Resolution
- **File/folder name -> ID**: `GOOGLEDRIVE_FIND_FILE` with `q` parameter
- **Root folder**: Use `folder_id='root'` or `'root' in parents`
- **Shared drive -> driveId**: `GOOGLEDRIVE_LIST_SHARED_DRIVES`
- **Contact name -> email**: `GMAIL_SEARCH_PEOPLE` (for sharing)
### Query Syntax
Google Drive uses a specific query language:
- Name search: `"name contains 'report'"` or `"name = 'exact.pdf'"`
- Type filter: `"mimeType = 'application/pdf'"` or `"mimeType = 'application/vnd.google-apps.folder'"`
- Folder scoping: `"'FOLDER_ID' in parents"`
- Date filter: `"modifiedTime > '2024-01-01T00:00:00'"`
- Combine with `and`/`or`/`not`: `"name contains 'report' and trashed = false"`
- Boolean filters: `"sharedWithMe = true"`, `"starred = true"`, `"trashed = false"`
### Pagination
- Follow `nextPageToken` until absent for complete results
- Set `pageSize` explicitly (default 100, max 1000)
- De-duplicate results if running multiple searches
### Export Formats
For Google Workspace files, set `mime_type` to export:
- **Docs**: `application/pdf`, `text/plain`, `text/html`, `application/vnd.openxmlformats-officedocument.wordprocessingml.document`
- **Sheets**: `text/csv`, `application/vnd.openxmlformats-officedocument.spreadsheetml.sheet`
- **Slides**: `application/pdf`, `application/vnd.openxmlformats-officedocument.presentationml.presentation`
## Known Pitfalls
- **Internal storage required**: Upload requires files in internal S3 storage (s3key)
- **Export vs download**: Set `mime_type` ONLY for Google Workspace files; omit for native files
- **Temporary URLs**: Downloaded content via `s3url` is temporary; fetch promptly
- **Query complexity**: >5-10 OR clauses may error; split complex searches into multiple queries
- **Shared drive scoping**: MRelated 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.