zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
What this skill does
# Zoom Automation via Rube MCP Automate Zoom operations including meeting scheduling, webinar management, cloud recording retrieval, participant tracking, and usage reporting through Composio's Zoom toolkit. ## Prerequisites - Rube MCP must be connected (RUBE_SEARCH_TOOLS available) - Active Zoom connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `zoom` - Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas - Most features require a paid Zoom account (Pro plan or higher) ## 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 `zoom` 3. If connection is not ACTIVE, follow the returned auth link to complete Zoom OAuth 4. Confirm connection status shows ACTIVE before running any workflows ## Core Workflows ### 1. Create and Schedule Meetings **When to use**: User wants to create a new Zoom meeting with specific time, duration, and settings **Tool sequence**: 1. `ZOOM_GET_USER` - Verify authenticated user and check license type [Prerequisite] 2. `ZOOM_CREATE_A_MEETING` - Create the meeting with topic, time, duration, and settings [Required] 3. `ZOOM_GET_A_MEETING` - Retrieve full meeting details including join_url [Optional] 4. `ZOOM_UPDATE_A_MEETING` - Modify meeting settings or reschedule [Optional] 5. `ZOOM_ADD_A_MEETING_REGISTRANT` - Register participants for registration-enabled meetings [Optional] **Key parameters**: - `userId`: Always use `"me"` for user-level apps - `topic`: Meeting subject line - `type`: `1` (instant), `2` (scheduled), `3` (recurring no fixed time), `8` (recurring fixed time) - `start_time`: ISO 8601 format (`yyyy-MM-ddTHH:mm:ssZ` for UTC or `yyyy-MM-ddTHH:mm:ss` with timezone field) - `timezone`: Timezone ID (e.g., `"America/New_York"`) - `duration`: Duration in minutes - `settings__auto_recording`: `"none"`, `"local"`, or `"cloud"` - `settings__waiting_room`: Boolean to enable waiting room - `settings__join_before_host`: Boolean (disabled when waiting room is enabled) - `settings__meeting_invitees`: Array of invitee objects with email addresses **Pitfalls**: - `start_time` must be in the future; Zoom stores and returns times in UTC regardless of input timezone - If no `start_time` is set for type `2`, it becomes an instant meeting that expires after 30 days - The `join_url` for participants and `start_url` for host come from the create response - persist these - `start_url` expires in 2 hours (or 90 days for `custCreate` users) - Meeting creation is rate-limited to 100 requests/day - Setting names use double underscores for nesting (e.g., `settings__host_video`) ### 2. List and Manage Meetings **When to use**: User wants to view upcoming, live, or past meetings **Tool sequence**: 1. `ZOOM_LIST_MEETINGS` - List meetings by type (scheduled, live, upcoming, previous) [Required] 2. `ZOOM_GET_A_MEETING` - Get detailed info for a specific meeting [Optional] 3. `ZOOM_UPDATE_A_MEETING` - Modify meeting details [Optional] **Key parameters**: - `userId`: Use `"me"` for authenticated user - `type`: `"scheduled"` (default), `"live"`, `"upcoming"`, `"upcoming_meetings"`, `"previous_meetings"` - `page_size`: Records per page (default 30) - `next_page_token`: Pagination token from previous response - `from` / `to`: Date range filters **Pitfalls**: - `ZOOM_LIST_MEETINGS` excludes instant meetings and only shows unexpired scheduled meetings - For past meetings, use `type: "previous_meetings"` - Pagination: always follow `next_page_token` until empty to get complete results - Token expiration: `next_page_token` expires after 15 minutes - Meeting IDs can exceed 10 digits; store as long integers, not standard integers ### 3. Manage Recordings **When to use**: User wants to list, retrieve, or delete cloud recordings **Tool sequence**: 1. `ZOOM_LIST_ALL_RECORDINGS` - List all cloud recordings for a user within a date range [Required] 2. `ZOOM_GET_MEETING_RECORDINGS` - Get recordings for a specific meeting [Optional] 3. `ZOOM_DELETE_MEETING_RECORDINGS` - Move recordings to trash or permanently delete [Optional] 4. `ZOOM_LIST_ARCHIVED_FILES` - List archived meeting/webinar files [Optional] **Key parameters**: - `userId`: Use `"me"` for authenticated user - `from` / `to`: Date range in `yyyy-mm-dd` format (max 1 month range) - `meetingId`: Meeting ID or UUID for specific recording retrieval - `action`: `"trash"` (recoverable) or `"delete"` (permanent) for deletion - `include_fields`: Set to `"download_access_token"` to get JWT for downloading recordings - `trash`: Set `true` to list recordings from trash **Pitfalls**: - Date range maximum is 1 month; API auto-adjusts `from` if range exceeds this - Cloud Recording must be enabled on the account - UUIDs starting with `/` or containing `//` must be double URL-encoded - `ZOOM_DELETE_MEETING_RECORDINGS` defaults to `"trash"` action (recoverable); `"delete"` is permanent - Download URLs require the OAuth token in the Authorization header for passcode-protected recordings - Requires Pro plan or higher ### 4. Get Meeting Participants and Reports **When to use**: User wants to see who attended a past meeting or get usage statistics **Tool sequence**: 1. `ZOOM_GET_PAST_MEETING_PARTICIPANTS` - List attendees of a completed meeting [Required] 2. `ZOOM_GET_A_MEETING` - Get meeting details and registration info for upcoming meetings [Optional] 3. `ZOOM_GET_DAILY_USAGE_REPORT` - Get daily usage statistics (meetings, participants, minutes) [Optional] 4. `ZOOM_GET_A_MEETING_SUMMARY` - Get AI-generated meeting summary [Optional] **Key parameters**: - `meetingId`: Meeting ID (latest instance) or UUID (specific occurrence) - `page_size`: Records per page (default 30) - `next_page_token`: Pagination token for large participant lists **Pitfalls**: - `ZOOM_GET_PAST_MEETING_PARTICIPANTS` only works for completed meetings on paid plans - Solo meetings (no other participants) return empty results - UUID encoding: UUIDs starting with `/` or containing `//` must be double-encoded - Always paginate with `next_page_token` until empty to avoid dropping attendees - `ZOOM_GET_A_MEETING_SUMMARY` requires a paid plan with AI Companion enabled; free accounts get 400 errors - `ZOOM_GET_DAILY_USAGE_REPORT` has a Heavy rate limit; avoid frequent calls ### 5. Manage Webinars **When to use**: User wants to list webinars or register participants for webinars **Tool sequence**: 1. `ZOOM_LIST_WEBINARS` - List scheduled or upcoming webinars [Required] 2. `ZOOM_GET_A_WEBINAR` - Get detailed webinar information [Optional] 3. `ZOOM_ADD_A_WEBINAR_REGISTRANT` - Register a participant for a webinar [Optional] **Key parameters**: - `userId`: Use `"me"` for authenticated user - `type`: `"scheduled"` (default) or `"upcoming"` - `page_size`: Records per page (default 30) - `next_page_token`: Pagination token **Pitfalls**: - Webinar features require Pro plan or higher with Webinar add-on - Free/basic accounts cannot use webinar tools - Only shows unexpired webinars - Registration must be enabled on the webinar for `ZOOM_ADD_A_WEBINAR_REGISTRANT` to work ## Common Patterns ### ID Resolution - **User ID**: Always use `"me"` for user-level apps to refer to the authenticated user - **Meeting ID**: Numeric ID (store as long integer); use for latest instance - **Meeting UUID**: Use for specific occurrence of recurring meetings; double-encode if starts with `/` or contains `//` - **Occurrence ID**: Use with recurring meetings to target a specific occurrence ### Pagination Most Zoom list endpoints use token-based pagination: - Follow `next_page_token` until it is empty or missing - Token expires after 15 minutes - Set explicit `page_size` (default 30, varies by endpoint) - Do not use `page_number` (deprecated on many endpoints) ### Time Handling - Zoom stores all times in UTC internally - P
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.