linkedin-intel:post

linkedin-intel:post — LinkedIn Post Intelligence

---

Step 0: Load Interpretive Lens

Read ~/.claude/skills/linkedin-intel/SKILL.md into context using the Read tool. Apply its principles (signal hierarchy, extraction rules, topic extraction, confidence calibration, data quality gates) throughout all analysis steps below.

---

Step 1: Parse & Setup

1. Extract the LinkedIn post URL from $ARGUMENTS (strip whitespace).
2. Extract the activity ID from the URL: match the regex activity[:\-](\d{19,20}) and take the numeric capture group. Examples:
   • https://www.linkedin.com/feed/update/urn:li:activity:7654321098765432100/ -> 7654321098765432100
   • https://www.linkedin.com/posts/some-slug_topic-activity-7654321098765432100-xxxx -> 7654321098765432100
3. Set paths:
   • SCRAPER = ~/Desktop/AIC/plugins/linkedin-intel/linkedin-scraper.py
   • COOKIES = ~/Desktop/AIC/plugins/linkedin-intel/.cookies.json
   • RAW_DATA = ~/Desktop/AIC/linkedin/posts/{activity-id}/linkedin_raw_data.json
   • OUTPUT = ~/Desktop/AIC/linkedin/posts/{activity-id}/notes/post-report.md
4. Create directories: ~/Desktop/AIC/linkedin/posts/{activity-id}/notes/ (use mkdir -p).

IMPORTANT: Before running the scraper, check if linkedin_raw_data.json already exists at the RAW_DATA path. If it does, ask the user:

"linkedin_raw_data.json already exists for activity {activity-id}. Use existing data or re-scrape?" If they say use existing, skip Step 2 entirely.

---

Step 2: Run Scraper

Run the Playwright scraper via Bash:

cd ~/Desktop/AIC/plugins/linkedin-intel && python linkedin-scraper.py --mode post {post_url} {RAW_DATA} --cookies {COOKIES}

• If exit code != 0, show the error and STOP. Do not proceed with missing data.
• If successful, read linkedin_raw_data.json and report: