automateyournetwork/zoom-meeting-context
workspace/skills/zoom-meeting-context/SKILL.md
Zoom meeting intelligence — correlates a live or referenced Zoom meeting discussion against NetClaw's historical meeting record (via the official Zoom Meetings MCP) and today's actual network state. Use when someone in a Zoom meeting references a past discussion or incident ('didn't we have this issue before?'), or asks to search prior meetings for a topic. Does not itself recognize live in-meeting questions — that happens automatically inside zoom-rtms-mcp's own extractor (spec 118) before this skill is ever invoked.
$ install --global
skillsauthnpx skillsauth add automateyournetwork/netclaw zoom-meeting-contextInstall 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: Aug 27, 2026, 4:06 AM120.0s1 file scanned
SKILL.md
- name:
- zoom-meeting-context
- description:
- Zoom meeting intelligence — correlates a live or referenced Zoom meeting discussion against NetClaw's historical meeting record (via the official Zoom Meetings MCP) and today's actual network state. Use when someone in a Zoom meeting references a past discussion or incident ('didn't we have this issue before?'), or asks to search prior meetings for a topic. Does not itself recognize live in-meeting questions — that happens automatically inside zoom-rtms-mcp's own extractor (spec 118) before this skill is ever invoked.
- version:
- 1.0.0
- license:
- Apache-2.0
- tags:
- [zoom, meetings, rtms, history, correlation, external]
- user-invocable:
- true
- { "openclaw":
- { "requires": { "bins": ["python3"], "env": ["ZOOM_MEETING_MCP_CREDENTIAL"] } } }
Zoom Meeting Context
What this is, and isn't
NetClaw for Zoom (spec 118) has two separate recognition paths — don't confuse them:
- Live in-meeting questions ("Toronto lost its BGP sessions, what happened?") are recognized
automatically, inside
zoom-rtms-mcp's ownextractor.py, and routed straight to the Border's existing investigation path (bgp/federation/zoom_channel.py). This never invokes this skill. - This skill is for the historical-correlation half only (User Story 2): "didn't we see this before?" — searching the official Zoom Meetings MCP for a prior, real meeting and comparing what was discussed then against the network's actual current state.
MCP Servers
zoom-rtms-mcp(NetClaw-authored, spec 118) —zoom_search_historical_meetingsis a thin pass-through to the official Zoom Meetings MCP; use it, not a direct connection of your own.- Zoom Meetings MCP (official, Zoom-hosted) — remote/OAuth, no local vendoring. Credential shape
is still being confirmed against Zoom's own connector setup flow (tracked in
specs/118-zoom-meeting-intelligence/research.mdR6 /tasks.mdT030). - Whatever Member Claw already answers the "what's true right now" half (pyATS, NetBox, Splunk, etc.) — reuse the existing routing path, don't build a second one.
Workflow
- Someone references a past meeting/incident by topic or approximate timeframe.
- Call
zoom_search_historical_meetings(query, time_hint). - If nothing relevant comes back, say so plainly. Do not present an unrelated result as if it were the match — this is an explicit spec requirement (FR-010's "no matching past meeting" case), not a style preference.
- If a relevant past meeting is found, summarize what was discussed/decided then.
- Check the network's current actual state for the same location/technology (via the existing
Member-Claw routing — the same path
zoom-rtms-mcp's live investigations use). - State plainly whether current state matches or differs from the historical discussion. Don't hedge past what the evidence actually shows.
What this skill must never do
- Never fabricate a historical match when the search comes back empty.
- Never treat this skill as a path to execute a configuration change — it is read-only correlation. Any actual change request, however it's phrased, still goes through NetClaw's existing device-write approval gate (Constitution Principles I–III), unchanged by this skill's existence.
Related
specs/118-zoom-meeting-intelligence/— full spec/plan/research/data-model/contractsmcp-servers/zoom-rtms-mcp/— the live-listening half (extractor, panel feed, Border channel client)docs/ZOOM-MEETING-INTELLIGENCE.md— operator setup guide
Related Skills
automateyournetwork/percepxion-oob
tools
VerifiedTrustedCommunity
Manage Lantronix out-of-band (OOB) infrastructure via Percepxion central management platform: device inventory, serial port inspection via SLC CLI, firmware compliance, config management, security auditing, and closed-loop incident remediation. Use during outages, maintenance windows, compliance cycles, and AI-assisted automation workflows.
644SKILL.mdUpdated Aug 13, 2026
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.)
638SKILL.mdUpdated Jul 11, 2026
automateyournetwork/token-tracker
tools
VerifiedTrustedCommunity
Track token consumption, enforce session budgets, and display cost for every NetClaw interaction.
638SKILL.mdUpdated Apr 3, 2026
automateyournetwork/zabbix-problem-review
tools
VerifiedTrustedCommunity
Review current and historical problems from Zabbix — severity, which host, when it started, how long it has been active, and whether anyone has acknowledged it. Use when someone asks what is broken right now, how long something has been broken, or what happened during a window that has already passed.
632SKILL.mdUpdated Aug 13, 2026