instagram-automation
Automate Instagram tasks via Rube MCP (Composio): create posts, carousels, manage media, get insights, and publishing limits. Always search tools first for current schemas.
What this skill does
# Instagram Automation via Rube MCP Automate Instagram operations through Composio's Instagram toolkit via Rube MCP. ## Prerequisites - Rube MCP must be connected (RUBE_SEARCH_TOOLS available) - Active Instagram connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `instagram` - Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas - Instagram Business or Creator account required (personal accounts not supported) ## 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 `instagram` 3. If connection is not ACTIVE, follow the returned auth link to complete Instagram/Facebook OAuth 4. Confirm connection status shows ACTIVE before running any workflows ## Core Workflows ### 1. Create a Single Image/Video Post **When to use**: User wants to publish a single photo or video to Instagram **Tool sequence**: 1. `INSTAGRAM_GET_USER_INFO` - Get Instagram user ID [Prerequisite] 2. `INSTAGRAM_CREATE_MEDIA_CONTAINER` - Create a media container with the image/video URL [Required] 3. `INSTAGRAM_GET_POST_STATUS` - Check if the media container is ready [Optional] 4. `INSTAGRAM_CREATE_POST` or `INSTAGRAM_POST_IG_USER_MEDIA_PUBLISH` - Publish the container [Required] **Key parameters**: - `image_url`: Public URL of the image to post - `video_url`: Public URL of the video to post - `caption`: Post caption text - `ig_user_id`: Instagram Business account user ID **Pitfalls**: - Media URLs must be publicly accessible; private/authenticated URLs will fail - Video containers may take time to process; poll GET_POST_STATUS before publishing - Caption supports hashtags and mentions but has a 2200 character limit - Publishing a container that is not yet finished processing returns an error ### 2. Create a Carousel Post **When to use**: User wants to publish multiple images/videos in a single carousel post **Tool sequence**: 1. `INSTAGRAM_CREATE_MEDIA_CONTAINER` - Create individual containers for each media item [Required, repeat per item] 2. `INSTAGRAM_CREATE_CAROUSEL_CONTAINER` - Create the carousel container referencing all media containers [Required] 3. `INSTAGRAM_GET_POST_STATUS` - Check carousel container readiness [Optional] 4. `INSTAGRAM_POST_IG_USER_MEDIA_PUBLISH` - Publish the carousel [Required] **Key parameters**: - `children`: Array of media container IDs for the carousel - `caption`: Carousel post caption - `ig_user_id`: Instagram Business account user ID **Pitfalls**: - Carousels require 2-10 media items; fewer or more will fail - Each child container must be created individually before the carousel container - All child containers must be fully processed before creating the carousel - Mixed media (images + videos) is supported in carousels ### 3. Get Media and Insights **When to use**: User wants to view their posts or analyze post performance **Tool sequence**: 1. `INSTAGRAM_GET_IG_USER_MEDIA` or `INSTAGRAM_GET_USER_MEDIA` - List user's media [Required] 2. `INSTAGRAM_GET_IG_MEDIA` - Get details for a specific post [Optional] 3. `INSTAGRAM_GET_POST_INSIGHTS` or `INSTAGRAM_GET_IG_MEDIA_INSIGHTS` - Get metrics for a post [Optional] 4. `INSTAGRAM_GET_USER_INSIGHTS` - Get account-level insights [Optional] **Key parameters**: - `ig_user_id`: Instagram Business account user ID - `media_id`: ID of the specific media post - `metric`: Metrics to retrieve (e.g., impressions, reach, engagement) - `period`: Time period for insights (e.g., day, week, lifetime) **Pitfalls**: - Insights are only available for Business/Creator accounts - Some metrics require minimum follower counts - Insight data may have a delay of up to 48 hours - The `period` parameter must match the metric type ### 4. Check Publishing Limits **When to use**: User wants to verify they can publish before attempting a post **Tool sequence**: 1. `INSTAGRAM_GET_IG_USER_CONTENT_PUBLISHING_LIMIT` - Check remaining publishing quota [Required] **Key parameters**: - `ig_user_id`: Instagram Business account user ID **Pitfalls**: - Instagram enforces a 25 posts per 24-hour rolling window limit - Publishing limit resets on a rolling basis, not at midnight - Check limits before bulk posting operations to avoid failures ### 5. Get Media Comments and Children **When to use**: User wants to view comments on a post or children of a carousel **Tool sequence**: 1. `INSTAGRAM_GET_IG_MEDIA_COMMENTS` - List comments on a media post [Required] 2. `INSTAGRAM_GET_IG_MEDIA_CHILDREN` - List children of a carousel post [Optional] **Key parameters**: - `media_id`: ID of the media post - `ig_media_id`: Alternative media ID parameter **Pitfalls**: - Comments may be paginated; follow pagination cursors for complete results - Carousel children are returned as individual media objects - Comment moderation settings on the account affect what is returned ## Common Patterns ### ID Resolution **Instagram User ID**: ``` 1. Call INSTAGRAM_GET_USER_INFO 2. Extract ig_user_id from response 3. Use in all subsequent API calls ``` **Media Container Status Check**: ``` 1. Call INSTAGRAM_CREATE_MEDIA_CONTAINER 2. Extract container_id from response 3. Poll INSTAGRAM_GET_POST_STATUS with container_id 4. Wait until status is 'FINISHED' before publishing ``` ### Two-Phase Publishing - Phase 1: Create media container(s) with content URLs - Phase 2: Publish the container after it finishes processing - Always check container status between phases for video content - For carousels, all children must complete Phase 1 before creating the carousel container ## Known Pitfalls **Media URLs**: - All image/video URLs must be publicly accessible HTTPS URLs - URLs behind authentication, CDN restrictions, or that require cookies will fail - Temporary URLs (pre-signed S3, etc.) may expire before processing completes **Rate Limits**: - 25 posts per 24-hour rolling window - API rate limits apply separately from publishing limits - Implement exponential backoff for 429 responses **Account Requirements**: - Only Business or Creator Instagram accounts are supported - Personal accounts cannot use the Instagram Graph API - The account must be connected to a Facebook Page **Response Parsing**: - Media IDs are numeric strings - Insights data may be nested under different response keys - Pagination uses cursor-based tokens ## Quick Reference | Task | Tool Slug | Key Params | |------|-----------|------------| | Get user info | INSTAGRAM_GET_USER_INFO | (none) | | Create media container | INSTAGRAM_CREATE_MEDIA_CONTAINER | image_url/video_url, caption | | Create carousel | INSTAGRAM_CREATE_CAROUSEL_CONTAINER | children, caption | | Publish post | INSTAGRAM_CREATE_POST | ig_user_id, creation_id | | Publish media | INSTAGRAM_POST_IG_USER_MEDIA_PUBLISH | ig_user_id, creation_id | | Check post status | INSTAGRAM_GET_POST_STATUS | ig_container_id | | List user media | INSTAGRAM_GET_IG_USER_MEDIA | ig_user_id | | Get media details | INSTAGRAM_GET_IG_MEDIA | ig_media_id | | Get post insights | INSTAGRAM_GET_POST_INSIGHTS | media_id, metric | | Get user insights | INSTAGRAM_GET_USER_INSIGHTS | ig_user_id, metric, period | | Get publishing limit | INSTAGRAM_GET_IG_USER_CONTENT_PUBLISHING_LIMIT | ig_user_id | | Get media comments | INSTAGRAM_GET_IG_MEDIA_COMMENTS | ig_media_id | | Get carousel children | INSTAGRAM_GET_IG_MEDIA_CHILDREN | ig_media_id | ## When to Use This skill is applicable to execute the workflow or actions described in the overview. ## 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.
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.