twitter-automation
Automate Twitter/X tasks via Rube MCP (Composio): posts, search, users, bookmarks, lists, media. Always search tools first for current schemas.
What this skill does
# Twitter/X Automation via Rube MCP Automate Twitter/X operations through Composio's Twitter toolkit via Rube MCP. ## Prerequisites - Rube MCP must be connected (RUBE_SEARCH_TOOLS available) - Active Twitter connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `twitter` - 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 `twitter` 3. If connection is not ACTIVE, follow the returned auth link to complete Twitter OAuth 4. Confirm connection status shows ACTIVE before running any workflows ## Core Workflows ### 1. Create and Manage Posts **When to use**: User wants to create, delete, or look up tweets/posts **Tool sequence**: 1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user info [Prerequisite] 2. `TWITTER_UPLOAD_MEDIA` / `TWITTER_UPLOAD_LARGE_MEDIA` - Upload media [Optional] 3. `TWITTER_CREATION_OF_A_POST` - Create a new post [Required] 4. `TWITTER_POST_LOOKUP_BY_POST_ID` - Look up a specific post [Optional] 5. `TWITTER_POST_DELETE_BY_POST_ID` - Delete a post [Optional] **Key parameters**: - `text`: Post text content (max 280 weighted characters) - `media__media_ids`: Array of media ID strings for attachments - `reply__in_reply_to_tweet_id`: Tweet ID to reply to - `quote_tweet_id`: Tweet ID to quote - `id`: Post ID for lookup/delete **Pitfalls**: - Post text is limited to 280 weighted characters; some characters count as more than one - Posting is NOT idempotent; retrying on timeout will create duplicate posts - Media IDs must be numeric strings, not integers - UPLOAD_LARGE_MEDIA is for videos/GIFs; UPLOAD_MEDIA for images - Always call USER_LOOKUP_ME first to get the authenticated user's ID ### 2. Search Posts **When to use**: User wants to find tweets matching specific criteria **Tool sequence**: 1. `TWITTER_RECENT_SEARCH` - Search recent tweets (last 7 days) [Required] 2. `TWITTER_FULL_ARCHIVE_SEARCH` - Search full archive (Academic access) [Optional] 3. `TWITTER_RECENT_SEARCH_COUNTS` - Get tweet count matching query [Optional] **Key parameters**: - `query`: Search query using Twitter search operators - `max_results`: Results per page (10-100) - `next_token`: Pagination token - `start_time`/`end_time`: ISO 8601 time range - `tweet__fields`: Comma-separated fields to include - `expansions`: Related objects to expand **Pitfalls**: - RECENT_SEARCH covers only the last 7 days; use FULL_ARCHIVE_SEARCH for older tweets - FULL_ARCHIVE_SEARCH requires Academic Research or Enterprise access - Query operators: `from:username`, `to:username`, `is:retweet`, `has:media`, `-is:retweet` - Empty results return `meta.result_count: 0` with no `data` field - Rate limits vary by endpoint and access level; check response headers ### 3. Look Up Users **When to use**: User wants to find or inspect Twitter user profiles **Tool sequence**: 1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user [Optional] 2. `TWITTER_USER_LOOKUP_BY_USERNAME` - Look up by username [Optional] 3. `TWITTER_USER_LOOKUP_BY_ID` - Look up by user ID [Optional] 4. `TWITTER_USER_LOOKUP_BY_IDS` - Batch look up multiple users [Optional] **Key parameters**: - `username`: Twitter handle without @ prefix - `id`: Numeric user ID string - `ids`: Comma-separated user IDs for batch lookup - `user__fields`: Fields to return (description, public_metrics, etc.) **Pitfalls**: - Usernames are case-insensitive but must not include the @ prefix - User IDs are numeric strings, not integers - Suspended or deleted accounts return errors, not empty results - LOOKUP_BY_IDS accepts max 100 IDs per request ### 4. Manage Bookmarks **When to use**: User wants to save, view, or remove bookmarked tweets **Tool sequence**: 1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user ID [Prerequisite] 2. `TWITTER_BOOKMARKS_BY_USER` - List bookmarked posts [Required] 3. `TWITTER_ADD_POST_TO_BOOKMARKS` - Bookmark a post [Optional] 4. `TWITTER_REMOVE_A_BOOKMARKED_POST` - Remove bookmark [Optional] **Key parameters**: - `id`: User ID (from USER_LOOKUP_ME) for listing bookmarks - `tweet_id`: Tweet ID to bookmark or unbookmark - `max_results`: Results per page - `pagination_token`: Token for next page **Pitfalls**: - Bookmarks require the authenticated user's ID, not username - Bookmarks are private; only the authenticated user can see their own - Pagination uses `pagination_token`, not `next_token` ### 5. Manage Lists **When to use**: User wants to view or manage Twitter lists **Tool sequence**: 1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user ID [Prerequisite] 2. `TWITTER_GET_A_USER_S_OWNED_LISTS` - List owned lists [Optional] 3. `TWITTER_GET_A_USER_S_LIST_MEMBERSHIPS` - List memberships [Optional] 4. `TWITTER_GET_A_USER_S_PINNED_LISTS` - Get pinned lists [Optional] 5. `TWITTER_GET_USER_S_FOLLOWED_LISTS` - Get followed lists [Optional] 6. `TWITTER_LIST_LOOKUP_BY_LIST_ID` - Get list details [Optional] **Key parameters**: - `id`: User ID for listing owned/member/followed lists - `list_id`: List ID for specific list lookup - `max_results`: Results per page (1-100) **Pitfalls**: - List IDs and User IDs are numeric strings - Lists endpoints require the user's numeric ID, not username ### 6. Interact with Posts **When to use**: User wants to like, unlike, or view liked posts **Tool sequence**: 1. `TWITTER_USER_LOOKUP_ME` - Get authenticated user ID [Prerequisite] 2. `TWITTER_RETURNS_POST_OBJECTS_LIKED_BY_THE_PROVIDED_USER_ID` - Get liked posts [Optional] 3. `TWITTER_UNLIKE_POST` - Unlike a post [Optional] **Key parameters**: - `id`: User ID for listing liked posts - `tweet_id`: Tweet ID to unlike **Pitfalls**: - Like/unlike endpoints require user ID from USER_LOOKUP_ME - Liked posts pagination may be slow for users with many likes ## Common Patterns ### Search Query Syntax **Operators**: - `from:username` - Posts by user - `to:username` - Replies to user - `@username` - Mentions user - `#hashtag` - Contains hashtag - `"exact phrase"` - Exact match - `has:media` - Contains media - `has:links` - Contains links - `is:retweet` / `-is:retweet` - Include/exclude retweets - `is:reply` / `-is:reply` - Include/exclude replies - `lang:en` - Language filter **Combinators**: - Space for AND - `OR` for either condition - `-` prefix for NOT - Parentheses for grouping ### Media Upload Flow ``` 1. Upload media with TWITTER_UPLOAD_MEDIA (images) or TWITTER_UPLOAD_LARGE_MEDIA (video/GIF) 2. Get media_id from response 3. Pass media_id as string in media__media_ids array to TWITTER_CREATION_OF_A_POST ``` ## Known Pitfalls **Character Limits**: - Standard posts: 280 weighted characters - Some Unicode characters count as more than 1 - URLs are shortened and count as fixed length (23 characters) **Rate Limits**: - Vary significantly by access tier (Free, Basic, Pro, Enterprise) - Free tier: very limited (e.g., 1,500 posts/month) - Check `x-rate-limit-remaining` header in responses **Idempotency**: - Post creation is NOT idempotent; duplicate posts will be created on retry - Implement deduplication logic for automated posting ## Quick Reference | Task | Tool Slug | Key Params | |------|-----------|------------| | Create post | TWITTER_CREATION_OF_A_POST | text | | Delete post | TWITTER_POST_DELETE_BY_POST_ID | id | | Look up post | TWITTER_POST_LOOKUP_BY_POST_ID | id | | Recent search | TWITTER_RECENT_SEARCH | query | | Archive search | TWITTER_FULL_ARCHIVE_SEARCH | query | | Search counts | TWITTER_RECENT_SEARCH_COUNTS | query | | My profile | TWITTER_USER_LOOKUP_ME | (none) | | User by name | TWITTER_USER_LOOKUP_BY_USERNAME | username | | User by ID | TWITTER_USER_LOOKUP_BY_ID | id | | Users by IDs | TWITTER_USER_LOOKUP_BY_IDS | ids | | Upload media | TWITTER_UPLOAD_MEDIA | media | | Upload video | TWITTER_UPLOAD_LARGE_M
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.