automateyournetwork/workspace/skills/twitter-respond
workspace/skills/twitter-respond/SKILL.md
# Twitter Respond Skill **Skill ID**: twitter-respond **Category**: Social Media / Engagement **Feature**: 040-twitter-mentions ## Overview Enables bidirectional Twitter interaction by monitoring @mentions of @John_Capobianco and generating CCIE-level technical replies. All replies require human approval per Constitution Principle XIV. ## Capabilities 1. **Mention Detection** - Poll for @mentions and classify them 2. **Reply Generation** - Create context-aware, technically accurate replies
$ install --global
skillsauthnpx skillsauth add automateyournetwork/netclaw workspace/skills/twitter-respondInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 25, 2026, 3:46 AM64.5s1 file scanned
SKILL.md
Twitter Respond Skill
Skill ID: twitter-respond Category: Social Media / Engagement Feature: 040-twitter-mentions
Overview
Enables bidirectional Twitter interaction by monitoring @mentions of @John_Capobianco and generating CCIE-level technical replies. All replies require human approval per Constitution Principle XIV.
Capabilities
- Mention Detection - Poll for @mentions and classify them
- Reply Generation - Create context-aware, technically accurate replies
- Reply Posting - Post approved replies as threads when needed
- Conversation Context - Retrieve thread history for better responses
- User Memory - Track interaction history with users
MCP Tools
This skill uses the twitter-mcp server's bidirectional tools:
| Tool | Purpose |
|------|---------|
| twitter_get_mentions | Fetch recent @mentions |
| twitter_classify_mention | Categorize mention intent |
| twitter_get_conversation | Get thread context |
| twitter_generate_reply | Generate reply draft |
| twitter_reply_to_tweet | Post approved reply |
| twitter_mark_processed | Mark mention as handled |
| twitter_get_user_history | Get user interaction history |
Mention Categories
Mentions are classified into:
- netclaw_request - Questions about NetClaw automation, diagrams, skills
- technical_network - Networking questions (BGP, OSPF, Cisco, etc.)
- friendly - Thanks, greetings, positive engagement
- off_topic - Unrelated to networking/NetClaw
- spam - Bot accounts, crypto/NFT spam
Workflow
1. Check Mentions → twitter_get_mentions
2. Classify Intent → twitter_classify_mention
3. Get Context → twitter_get_conversation (if thread)
4. Get User History → twitter_get_user_history
5. Generate Reply → twitter_generate_reply
6. Human Reviews → [Approval Required]
7. Post Reply → twitter_reply_to_tweet (approved=true)
8. Mark Processed → twitter_mark_processed
Example Interaction
User: "Check my Twitter mentions"
NetClaw: Found 3 new mentions:
1. @alice_neteng: "@John_Capobianco what's the best way to debug BGP peering?"
Category: technical_network
2. @random_user: "@John_Capobianco check out this crypto deal!"
Category: spam (skipping)
3. @cisco_fan: "@John_Capobianco can NetClaw generate topology diagrams?"
Category: netclaw_request
User: "Reply to the BGP question"
NetClaw: Here's my suggested reply:
"@alice_neteng Start with: 1) show ip bgp summary - check state
2) show ip bgp neighbors - verify open/sent/rcvd messages
3) debug ip bgp events - watch notifications
Common issues: AS mismatch, source IP, eBGP multihop. #netclaw"
Post this reply? [Yes/No/Edit]
User: "Yes"
NetClaw: Reply posted: https://twitter.com/i/web/status/123456789
Configuration
Environment variables in ~/.openclaw/.env:
# Required (from feature 039)
TWITTER_API_KEY=your_consumer_key
TWITTER_API_SECRET=your_consumer_secret
TWITTER_ACCESS_TOKEN=your_access_token
TWITTER_ACCESS_SECRET=your_access_secret
# Optional mention polling
TWITTER_MENTION_POLL_INTERVAL=300 # Check every 5 minutes
Human Approval Requirement
Per Constitution Principle XIV (Human-in-the-Loop for External Communications):
- All replies are generated as drafts first
- Human must explicitly approve before posting
approved=trueparameter required fortwitter_reply_to_tweet- Audit log tracks all posted replies
Cost Estimates
Using pay-as-you-go Twitter API tier:
| Action | Cost | |--------|------| | Check mentions | ~$0.01 | | Get conversation | ~$0.01 | | Post reply | ~$0.01 | | Full interaction | ~$0.03-0.05 |
With $5 credit, expect ~100-150 interactions.
Spam Detection
Heuristics to filter spam accounts:
- Account created within 7 days
- Following/followers ratio > 100:1
- Username contains 8+ digits
- Known spam patterns (crypto, giveaway, airdrop)
Related Skills
- twitter-heartbeat - Autonomous posting (feature 039)
- twitter-share - Share NetClaw outputs to Twitter (feature 039)
Related Skills
automateyournetwork/n2n-federation
tools
VerifiedTrustedCommunity
Federate your NetClaw with other NetClaw operators over the BGP mesh — exchange capability inventories and ask your claw what a peer can do. (US1; remote invocation and chat land in later phases.)
618SKILL.mdUpdated Jul 11, 2026
automateyournetwork/ue5-network-viz
tools
VerifiedTrustedCommunity
3D network topology visualization and interactive digital twin in Unreal Engine 5.8 via the built-in UE5 MCP server.
613SKILL.mdUpdated Jul 4, 2026
automateyournetwork/humanrail-escalation
testing
VerifiedTrustedCommunity
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
613SKILL.mdUpdated May 12, 2026
automateyournetwork/subnet-calculator
testing
VerifiedTrustedCommunity
IPv4 and IPv6 subnet calculator - CIDR breakdown, usable hosts, previous/next subnets, address classification, VLSM planning, and dual-stack analysis. Use when calculating subnets, figuring out how many hosts fit in a prefix, planning IP addressing, getting wildcard masks for ACLs, or checking if two IPs are in the same subnet.
613SKILL.mdUpdated Apr 3, 2026