post-scorer

Post Scorer

CRITICAL: Auto-start on load

When this skill triggers, go straight to Step 1. Do not summarise. Do not explain the scoring method. Start immediately.

Step 1. Get the post

If the user already pasted a post in the same message, use it. Otherwise say:

Paste the LinkedIn post you want scored.

Wait for the post.

Step 2. Load scoring data

The scorer needs two things: the user's voice system and real performance data.

Voice system

Read about-me.md and voice.md from the project if they exist. If missing, note it and score without voice matching.

Performance data

Check for cached LinkedIn data in the project or outputs folder. Look for files matching *-all-posts.json or *-posts.txt.

If cached data exists, use it. If not, ask the user:

[
  {
    "question": "To score your post against real data, I need your LinkedIn history. How should I get it?",
    "header": "Data source",
    "multiSelect": false,
    "options": [
      {"label": "Scrape my posts", "description": "Pull my last 100 posts from LinkedIn via Apify. Takes 1 to 2 minutes, costs about $0.50."},
      {"label": "Use Charlie Hills data", "description": "Score against Charlie Hills benchmarks (1,872 avg engagement, 500 posts analysed). Good fallback."},
      {"label": "Skip data scoring", "description": "Score against generic best practices only. Less accurate but instant."}
    ]
  }
]

If "Scrape my posts":

1. Ask for their LinkedIn username
2. Call Apify actor apimaestro/linkedin-profile-posts with input: { "username": "[their-username]", "total_posts": 100 }
3. Download results (do NOT use the fields parameter, it strips engagement data)
4. Save as [username]-all-posts.json in the project
5. Proceed to analysis

If "Use Charlie Hills data": Look for cached Charlie data at **/linkedin-data/charlie-all-posts.json. If found, use it. If not, note you are using the benchmarks from this skill file (listed below).

If "Skip data scoring": Fall back to voice-system-only scoring and general best practices.