linkedin-automation – skill Agent & Tự động hóa cho agent AI
Tự động hóa tác vụ LinkedIn qua Rube MCP (Composio): tạo bài đăng, quản lý hồ sơ, thông tin công ty, bình luận và tải ảnh lên. Luôn tìm công cụ trước để lấy schema hiện tại.
Cài skill linkedin-automation bằng một lệnh
Chọn công cụ bạn đang dùng, copy lệnh và dán vào terminal. Skill sẽ nằm trong thư mục skills của công cụ đó và sẵn sàng dùng ở phiên làm việc tiếp theo.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/linkedin-automation-6429c.tgz | tar xz -C ~/.claude/skills
Gọi trong Claude Code: /linkedin-automation – rồi mô tả công việc bạn muốn làm.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/linkedin-automation-6429c.tgz | tar xz -C ~/.codex/skills
Gọi trong Codex: $linkedin-automation – rồi mô tả công việc bạn muốn làm.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/linkedin-automation-6429c.tgz | tar xz -C ~/.hermes/skills
Gọi trong Hermes Agent: /linkedin-automation – rồi mô tả công việc bạn muốn làm.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/linkedin-automation-6429c.tgz | tar xz -C ~/.deepcode/skills
Gọi trong DeepSeek: /linkedin-automation – rồi mô tả công việc bạn muốn làm.
Nội dung SKILL.md
Nội dung SKILL.md gốc bằng tiếng Anh.
LinkedIn Automation via Rube MCP
Automate LinkedIn operations through Composio's LinkedIn toolkit via Rube MCP.
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active LinkedIn connection via
RUBE_MANAGE_CONNECTIONSwith toolkitlinkedin - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. Verify current MCP authentication and LinkedIn OAuth scopes; an endpoint alone does not establish an authenticated account.
1. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
2. Call RUBE_MANAGE_CONNECTIONS with toolkit linkedin
3. If connection is not ACTIVE, follow the returned auth link to complete LinkedIn OAuth
4. Confirm connection status shows ACTIVE before running any workflows
Publication boundary
Read-only profile access does not authorize posting or comments. Resolve the exact person/organization actor, show the content/media/visibility and perform only the user-authorized publication or deletion. Verify returned post identity before reporting success; reconcile timeouts before retrying to avoid duplicate public posts.
Core Workflows
1. Create a LinkedIn Post
When to use: User wants to publish a text post on LinkedIn
Tool sequence:
1. LINKEDIN_GET_MY_INFO - Get authenticated user's profile info [Prerequisite]
2. LINKEDIN_REGISTER_IMAGE_UPLOAD - Register image upload if post includes an image [Optional]
3. LINKEDIN_CREATE_LINKED_IN_POST - Publish the post [Required]
Key parameters:
text: Post content textvisibility: 'PUBLIC' or 'CONNECTIONS'media_title: Title for attached mediamedia_description: Description for attached media
Pitfalls:
- Must retrieve user profile URN via GET_MY_INFO before creating a post
- Image uploads require a two-step process: register upload first, then include the asset in the post
- Post text has character limits enforced by LinkedIn API
- Visibility defaults may vary; always specify explicitly
2. Get Profile Information
When to use: User wants to retrieve their LinkedIn profile or company details
Tool sequence:
1. LINKEDIN_GET_MY_INFO - Get authenticated user's profile [Required]
2. LINKEDIN_GET_COMPANY_INFO - Get company page details [Optional]
Key parameters:
- No parameters needed for GET_MY_INFO (uses authenticated user)
organization_id: Company/organization ID for GET_COMPANY_INFO
Pitfalls:
- GET_MY_INFO returns the authenticated user only; cannot look up other users
- Company info requires the numeric organization ID, not the company name or vanity URL
- Some profile fields may be restricted based on OAuth scopes granted
3. Manage Post Images
When to use: User wants to upload and attach images to LinkedIn posts
Tool sequence:
1. LINKEDIN_REGISTER_IMAGE_UPLOAD - Register an image upload with LinkedIn [Required]
2. Upload the image binary to the returned upload URL [Required]
3. LINKEDIN_GET_IMAGES - Verify uploaded image status [Optional]
4. LINKEDIN_CREATE_LINKED_IN_POST - Create post with the image asset [Required]
Key parameters:
owner: URN of the image owner (user or organization)image_id: ID of the uploaded image for GET_IMAGES
Pitfalls:
- The upload is a two-phase process: register then upload binary
- Image asset URN from registration must be used when creating the post
- Supported formats typically include JPG, PNG, and GIF
- Large images may take time to process before they are available
4. Comment on Posts
When to use: User wants to comment on an existing LinkedIn post
Tool sequence:
1. LINKEDIN_CREATE_COMMENT_ON_POST - Add a comment to a post [Required]
Key parameters:
post_id: The URN or ID of the post to comment ontext: Comment contentactor: URN of the commenter (user or organization)
Pitfalls:
- Post ID must be a valid LinkedIn URN format
- The actor URN must match the authenticated user or a managed organization
- Rate limits apply to comment creation; avoid rapid-fire comments
5. Delete a Post
When to use: User wants to remove a previously published LinkedIn post
Tool sequence:
1. LINKEDIN_DELETE_LINKED_IN_POST - Delete the specified post [Required]
Key parameters:
post_id: The URN or ID of the post to delete
Pitfalls:
- Deletion is permanent and cannot be undone
- Only the post author or organization admin can delete a post
- The post_id must be the exact URN returned when the post was created
Common Patterns
ID Resolution
User URN from profile:
1. Call LINKEDIN_GET_MY_INFO
2. Extract user URN (e.g., 'urn:li:person:XXXXXXXXXX')
3. Use URN as actor/owner in subsequent callsOrganization ID from company:
1. Call LINKEDIN_GET_COMPANY_INFO with organization_id
2. Extract organization URN for posting as a company pageImage Upload Flow
- Call REGISTER_IMAGE_UPLOAD to get upload URL and asset URN
- Upload the binary image to the provided URL
- Use the asset URN when creating a post with media
- Verify with GET_IMAGES if upload status is uncertain
Known Pitfalls
Authentication:
- LinkedIn OAuth tokens have limited scopes; ensure required permissions are granted
- Tokens expire; re-authenticate if API calls return 401 errors
URN Formats:
- LinkedIn uses URN identifiers (e.g., 'urn:li:person:ABC123')
- Always use the full URN format, not just the alphanumeric ID portion
- Organization URNs differ from person URNs
Rate Limits:
- LinkedIn API has strict daily rate limits on post creation and comments
- Implement backoff strategies for bulk operations
- Monitor 429 responses and respect Retry-After headers
Content Restrictions:
- Posts have character limits enforced by the API
- Some content types (polls, documents) may require additional API features
- HTML markup in post text is not supported
Quick Reference
| Task | Tool Slug | Key Params |
|------|-----------|------------|
| Get my profile | LINKEDIN_GET_MY_INFO | (none) |
| Create post | LINKEDIN_CREATE_LINKED_IN_POST | text, visibility |
| Get company info | LINKEDIN_GET_COMPANY_INFO | organization_id |
| Register image upload | LINKEDIN_REGISTER_IMAGE_UPLOAD | owner |
| Get uploaded images | LINKEDIN_GET_IMAGES | image_id |
| Delete post | LINKEDIN_DELETE_LINKED_IN_POST | post_id |
| Comment on post | LINKEDIN_CREATE_COMMENT_ON_POST | post_id, text, actor |
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.
Skill liên quan
- llm-application-dev-langchain-agent – Bạn là chuyên gia phát triển agent LangChain, chuyên về hệ thống AI cấp production dùng…
- llm-application-dev-prompt-optimize – Cải thiện prompt cho LLM bằng đánh giá theo từng tác vụ, chỉ dẫn có cấu trúc và kiểm tra…
- llm-caching – Triển khai bộ nhớ đệm LLM đa tầng với khớp chính xác, tương đồng ngữ nghĩa và prompt…
- llm-ops – LLM Operations: RAG, embeddings, cơ sở dữ liệu vector, fine-tuning, prompt engineering…
- llm-prompt-optimizer – Dùng khi cải thiện prompt cho bất kỳ LLM nào. Áp dụng các kỹ thuật prompt engineering đã…
- loki-mode – Quy trình đa tác nhân phiên bản 2.35.x (cũ) để biến PRD đã giới hạn phạm vi thành triển…
- longbridge-derivatives – Hướng dẫn tuyển chọn từ nguồn gốc cho Longbridge Derivatives; dùng khi quy trình phù hợp…
- longbridge-quant – Hướng dẫn tuyển chọn từ nguồn gốc cho Longbridge Quant; dùng khi quy trình phù hợp với…