Agent skill
post-linkedin
Automatically create and post content on LinkedIn to generate business visibility and sales leads. Drafts posts based on business goals, creates approval requests, and publishes via Playwright browser automation after human approval. Use when scheduled to post or when the user requests a LinkedIn post.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/post-linkedin
SKILL.md
Post to LinkedIn
Create and publish LinkedIn posts for business development and sales generation.
Workflow
1. Generate Post Content
Read vault/Business_Goals.md to understand current business objectives.
Draft a LinkedIn post that:
- Highlights business expertise or achievements
- Provides value to the target audience
- Includes a call-to-action when appropriate
- Stays professional and on-brand
- Is 150-300 words (optimal LinkedIn length)
2. Create Approval Request
All LinkedIn posts require human approval before publishing.
Create an approval file in vault/Pending_Approval/:
---
type: approval_request
request_id: "YYYYMMDD_HHMMSS_linkedin_post"
action: linkedin_post
priority: medium
created: ISO-8601
expires: ISO-8601 (24 hours from creation)
status: pending
details:
platform: "linkedin"
content_preview: "First 100 chars of post..."
---
# Approval Required: LinkedIn Post
## Proposed Post Content
[Full post text here]
## How to Respond
- **To Approve**: Move this file to the `/Approved` folder
- **To Reject**: Move this file to the `/Rejected` folder
3. Publish (After Approval)
Once the file appears in vault/Approved/:
-
Start Playwright MCP if not running:
bashbash .claude/skills/browsing-with-playwright/scripts/start-server.sh -
Navigate to LinkedIn:
bashpython3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_navigate \ -p '{"url": "https://www.linkedin.com/feed/"}' -
Click "Start a post" button:
bashpython3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_snapshot -p '{}' # Find the "Start a post" button ref, then click it -
Type the post content:
bashpython3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_type \ -p '{"element": "Post editor", "ref": "<ref>", "text": "<post content>"}' -
Click Post/Publish:
bashpython3 scripts/mcp-client.py call -u http://localhost:8808 -t browser_click \ -p '{"element": "Post button", "ref": "<ref>"}' -
Verify success by checking for confirmation
4. Log the Action
Write to vault/Logs/YYYY-MM-DD.json:
{
"timestamp": "ISO-8601",
"action_type": "linkedin_post_published",
"actor": "claude_code",
"platform": "linkedin",
"content_preview": "First 100 chars...",
"approval_status": "approved",
"approved_by": "human",
"result": "success"
}
5. Move to Done
Move the approval file from /Approved to /Done after publishing.
Post Ideas by Category
Thought Leadership
- Industry insights and trends
- Lessons learned from recent projects
- Best practices and tips
Business Updates
- New service offerings
- Team achievements
- Case studies and success stories
Engagement Posts
- Questions for the audience
- Polls about industry topics
- Celebrating milestones
Important Rules
- NEVER post without human approval - always create approval request first
- Keep posts professional and aligned with business goals
- Include relevant hashtags (3-5 per post)
- Avoid controversial topics
- Do not share confidential client information
- Log every post attempt (success or failure)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?