Menu
Monitor brand mentions across all platforms, reply within 2-4 hours, categorize by sentiment and priority, and log unanswered mentions for follow-up.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | mention-monitor |
| description | Monitor brand mentions across all platforms, reply within 2-4 hours, categorize by sentiment and priority, and log unanswered mentions for follow-up. |
| version | 2.0.0 |
| author | Crewm8 |
| maintainer | Gokul (github.com/gokulb20) |
| license | MIT |
| homepage | https://crewm8.ai |
| tags | ["social","engagement","mentions","monitoring","brand-awareness","sentiment"] |
| related_skills | ["comment-reply","dm-respond","crisis-respond","performance-report"] |
| inputs_required | ["brand-handles-and-keywords-to-monitor","platform-access-per-platform"] |
| deliverables | ["mention-report-with-reply-status-and-sentiment"] |
| compatible_agents | ["hermes","claude-code","droid","cursor","windsurf","openai","openclaw","generic"] |
| execution_tier | 1 |
| required_tools | ["X_API_KEY"] |
| required_env_vars | ["X_API_KEY"] |
Track every time the brand is mentioned across platforms and ensure nothing goes unanswered. A thanked mention builds community. An ignored mention signals the brand doesn't care.
Brand mentions are free attention. Ignoring them is leaving social capital on the table. This skill ensures every mention is seen, categorized, and responded to within the appropriate timeframe.
| Mention Type | Priority | Response Time | Action |
|---|---|---|---|
| Direct tag/shoutout | High | Within 2 hours | Thank + add value |
| Question about product | Critical | Within 1 hour | Answer directly |
| Complaint / negative | Critical | Within 1 hour | Acknowledge, route if needed |
| Share / repost | Medium | Within 4 hours | Thank individually |
| Casual reference (untagged) | Low | Within 24 hours | Engage if natural |
| Competitor comparison | Medium | Within 4 hours | Monitor; engage only if factual correction needed |
Set up mention detection:
Daily sweep (morning + afternoon):
Categorize each mention using the Quick Reference table.
Draft responses:
Track mention metrics:
# Mention Monitor: [Date]
## Mentions Today
| Time | Platform | User | Type | Content (truncated) | Priority | Response | Status |
|------|----------|------|------|--------------------|----------|----------|--------|
| 9:15 | X | @user | Shoutout | "[text]" | High | "[reply]" | Replied |
...
## Unanswered (Flagged)
[Any that couldn't be resolved — why?]
## Weekly Summary
- Total mentions: [N] | Response rate: [N]%
- Avg response time: [N] hours
- Sentiment: Positive [N]% / Neutral [N]% / Negative [N]%
- Top mentioners: @handle1, @handle2...
The skill is complete when:
Are there mentions from the last 24 hours that went unanswered? Is the response rate above 90% for high-priority? If not, adjust monitoring frequency or templates.
Analyze A/B tests across hook variations, posting times, content formats, and CTAs — declare statistical winners, document learnings, and build an always-on optimization engine.
Track post-level metrics across all platforms — impressions, engagement rate, profile clicks, follows, link clicks — with weekly aggregation and trend detection for performance analysis.
Generate weekly and monthly performance summary reports — top/bottom posts, content type analysis, pillar performance, follower growth, conversion tracking, and actionable recommendations.
Write Instagram and LinkedIn captions with scroll-stopping hooks, value-dense bodies, platform-appropriate CTAs, and strategic hashtag sets — optimized for each platform's reading behavior and visual context.
Select and write the optimal call-to-action for any social post — follow, reply, DM, save, share, link, or signup — matched to platform, content type, content value, and audience psychology.
Generate 5-10 hook variations for any post, thread, or caption across X, LinkedIn, Instagram, and TikTok — using different styles (question, contrarian, statistic, story, observation, promise) so the best one can be tested or selected.