Best for
- Use when the user asks to check ConnectWise Automate fleet health, find stale or offline agents, report patch compliance by client, triage open alerts across clients, inventory end-of-life OSes, or see what changed over…
Servosity/msp-skills/skills/connectwise-automate/SKILL.md
Use when the user asks to check ConnectWise Automate fleet health, find stale or offline agents, report patch compliance by client, triage open alerts across clients, inventory end-of-life OSes, or see what changed overnight across an RMM fleet. Syncs your whole Automate server into a local SQLite mirror so it answers cross-client questions the per-server console can't. Trigger phrases: `connectwise automate fleet health`, `stale automate agents`, `automate patch compliance by client`, `triage a
Decision brief
Syncs your whole Automate server into a local SQLite mirror so it answers cross-client questions the per-server console can't. Trigger phrases: `connectwise automate fleet health`, `stale automate agents`, `automate patch compliance by client`, `triage a
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/Servosity/msp-skills --skill "skills/connectwise-automate"Inspect the Agent Skill "connectwise-automate" from https://github.com/Servosity/msp-skills/blob/30e109db0872897de0b88adb38d81d4c292da3ae/skills/connectwise-automate/SKILL.md at commit 30e109db0872897de0b88adb38d81d4c292da3ae. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Automate is per-server: set CONNECTWISEAUTOMATESERVER to your host (e.g. company.hostedrmm.com) and CONNECTWISEAUTOMATECLIENTID to your registered integration GUID (required for v2020.11+). Mint a bearer token with apitoken mint --username --password , then export CONNECTWISEAUT…
This skill drives the connectwise-automate-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
These capabilities aren't available in any other tool for this API.
Reach for this when an agent needs the whole-fleet posture in one shot instead of paging the Computers endpoint client by client.
Start the morning here to see what actually needs a human across the whole book of business.
Permission review
The documentation includes network, browsing, or remote request actions.
bash <(curl -fsSL https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-automate/install.sh)The documentation asks the agent to run terminal commands or scripts.
bash <(curl -fsSL https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-automate/install.sh)The documentation includes network, browsing, or remote request actions.
iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-automate/install.ps1 | iexThe documentation asks the agent to run terminal commands or scripts.
`connectwise-automate-cli computers command-execute` - Execute a command on one computer (WRITE - runs a real command on the agent)The documentation includes sending, uploading, or posting data to a remote service.
| `webhook:<url>` | POST the output body to the URL (`application/json` or `application/x-ndjson` when `--compact`) |Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 86/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 15 | Source | Repository attention, not individual Skill quality |
| Compatibility | 1 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
This skill drives the connectwise-automate-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
bash <(curl -fsSL https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-automate/install.sh)
iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-automate/install.ps1 | iex
connectwise-automate-cli --version~/.local/bin (macOS / Linux) or %LOCALAPPDATA%\Programs\msp-skills (Windows) is on $PATH.If --version reports "command not found" after install, the install step did not put the binary on $PATH. Do not proceed with skill commands until verification succeeds.
ConnectWise Automate's value is locked behind a per-server console built for one-endpoint-at-a-time work. This CLI syncs your whole fleet - computers, clients, locations, alerts, and patch history - into local SQLite, then answers the questions MSPs actually ask across clients: where the offline agents are (stale-agents), who's behind on patches (patch-compliance), and what changed overnight (since). Everything is offline, scriptable, and built for AI agents.
These capabilities aren't available in any other tool for this API.
fleet-health - See every agent across every client in one roll-up: online/offline, last-contact age, and open-alert count, grouped by client.
Reach for this when an agent needs the whole-fleet posture in one shot instead of paging the Computers endpoint client by client.
connectwise-automate-cli fleet-health --agent
stale-agents - List computers not seen in N days, grouped by client - the offline agents bleeding license and hiding risk.
Use before license true-ups or security reviews to find agents that stopped checking in.
connectwise-automate-cli stale-agents --days 30 --agent
patch-compliance - Per-client patch posture from synced patch history joined to computers - worst offenders first.
Pull this before a QBR or a security conversation to name the clients that are behind.
connectwise-automate-cli patch-compliance --agent
client-rollup - One-line-per-client snapshot: computers, locations, offline agents, and open alerts - built for the client review.
The fastest way to brief on a client's whole environment without clicking through the console.
connectwise-automate-cli client-rollup --agent
alert-triage - Open alerts across every client, ranked by priority and joined to computer → location → client, with duplicates collapsed.
Start the morning here to see what actually needs a human across the whole book of business.
connectwise-automate-cli alert-triage --min-priority 3 --agent
os-inventory - Fleet-wide operating-system distribution with end-of-life OSes (Windows 7, Server 2008/2012) flagged for upgrade planning.
Use for security and hardware-refresh planning when you need the EOL exposure across every client at once.
connectwise-automate-cli os-inventory --eol-only --agent
since - Fleet activity in the last N hours from the records' own timestamps: alerts created, agents that checked in, and patches installed.
Run first thing to catch overnight activity across the fleet without paging each endpoint.
connectwise-automate-cli since --hours 24 --agent
connectwise-automate-cli alert-triage --min-priority 3 --agent --select client,computer,priority,message
Narrows the alert payload to the four fields that matter so an agent doesn't burn context on the full alert objects.
connectwise-automate-cli stale-agents --days 45 --agent
Lists computers not seen in 45 days, grouped by client, straight from the local store.
connectwise-automate-cli patch-compliance --agent
Per-client patch percentages, worst first, ready to paste into a client review.
connectwise-automate-cli computers list --condition "Status='Offline'" --order-by "LastContact asc" --agent
Uses Automate's own condition/orderby query against the live API when you don't want a full sync.
alerts - Open monitor alerts across the fleet
connectwise-automate-cli alerts get - Get a single alert by Idconnectwise-automate-cli alerts list - List open alerts across all computersapitoken - Mint and refresh API bearer tokens
connectwise-automate-cli apitoken mint - Mint a bearer token from username + password (needs CONNECTWISE_AUTOMATE_SERVER + clientId header)connectwise-automate-cli apitoken refresh - Refresh an existing (still-valid) bearer tokenclients - Clients (companies / customers) in Automate
connectwise-automate-cli clients get - Get a single client by Idconnectwise-automate-cli clients list - List all clientscommands - Available commands that can be executed on agents
connectwise-automate-cli commands get - Get a single command by Idconnectwise-automate-cli commands list - List all available commandscomputers - Managed endpoints (agents) - the core RMM inventory
connectwise-automate-cli computers alerts - Open alerts for one computerconnectwise-automate-cli computers command-execute - Execute a command on one computer (WRITE - runs a real command on the agent)connectwise-automate-cli computers command-history - Recent command execution history for one computerconnectwise-automate-cli computers get - Get a single computer by Idconnectwise-automate-cli computers list - List computers across the fleet (paginated, filterable)connectwise-automate-cli computers patching-stats - Patch installation statistics for one computerconnectwise-automate-cli computers software - Installed software inventory for one computercontacts - Client contacts
connectwise-automate-cli contacts - List all client contactsgroups - Computer groups (organizational + policy grouping)
connectwise-automate-cli groups get - Get a single group by Idconnectwise-automate-cli groups list - List all groupslocations - Locations (sites) belonging to clients
connectwise-automate-cli locations get - Get a single location by Idconnectwise-automate-cli locations list - List all locationsmonitors - Monitors and their per-monitor statistics
connectwise-automate-cli monitors list - List monitors with their alerting statisticsconnectwise-automate-cli monitors sensor-checks - List sensor checksnetwork-devices - Discovered network devices (non-agent)
connectwise-automate-cli network-devices - List discovered network devicespatching - Patch history, compliance information, and patch policies
connectwise-automate-cli patching approval-policies - Patch approval policiesconnectwise-automate-cli patching deploy-approved - Deploy all approved patches (WRITE - triggers fleet patch deployment)connectwise-automate-cli patching deploy-security - Deploy all security patches (WRITE - triggers fleet patch deployment)connectwise-automate-cli patching information - Global patch information / catalog statusconnectwise-automate-cli patching list - Fleet-wide patch installation historyconnectwise-automate-cli patching microsoft-policies - Microsoft update policiesconnectwise-automate-cli patching reattempt-failed - Reattempt failed patches (WRITE - retries failed patch installs)connectwise-automate-cli patching thirdparty-policies - Third-party update policiesscripts - Automation scripts and their run state
connectwise-automate-cli scripts list - List all scriptsconnectwise-automate-cli scripts running - List scripts currently running across the fleetconnectwise-automate-cli scripts schedules - List scheduled script runsserver - Automate server metadata (used by doctor / health)
connectwise-automate-cli server db-time - Current database server timeconnectwise-automate-cli server info - Server version and metadataWhen you know what you want to do but not which command does it, ask the CLI directly:
connectwise-automate-cli which "<capability in your own words>"
which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match - fall back to --help or use a narrower query.
Automate is per-server: set CONNECTWISE_AUTOMATE_SERVER to your host (e.g. company.hostedrmm.com) and CONNECTWISE_AUTOMATE_CLIENT_ID to your registered integration GUID (required for v2020.11+). Mint a bearer token with apitoken mint --username <u> --password <p>, then export CONNECTWISE_AUTOMATE_TOKEN with the returned AccessToken. Tokens are short-lived; refresh with apitoken refresh.
Run connectwise-automate-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
Pipeable - JSON on stdout, errors on stderr
Filterable - --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
connectwise-automate-cli alerts list --agent --select id,name,status
Previewable - --dry-run shows the request without sending
Offline-friendly - sync/search commands can use the local SQLite store when available
Non-interactive - never prompts, every input is a flag
Explicit retries - use --idempotent only when an already-existing create should count as success
Commands that read from the local store or the API wrap output in a provenance envelope:
{
"meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
"results": <data>
}
Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set - piped/agent consumers and explicit-format runs get pure JSON on stdout.
When you (or the agent) notice something off about this CLI, record it:
connectwise-automate-cli feedback "the --since flag is inclusive but docs say exclusive"
connectwise-automate-cli feedback --stdin < notes.txt
connectwise-automate-cli feedback list --json --limit 10
Entries are stored locally at ~/.local/share/connectwise-automate-cli/feedback.jsonl. They are never POSTed unless CONNECTWISE_AUTOMATE_FEEDBACK_ENDPOINT is set AND either --send is passed or CONNECTWISE_AUTOMATE_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect |
|---|---|
stdout | Default; write to stdout only |
file:<path> | Atomically write output to <path> (tmp + rename) |
webhook:<url> | POST the output body to the URL (application/json or application/x-ndjson when --compact) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration.
connectwise-automate-cli profile save briefing --json
connectwise-automate-cli --profile briefing alerts list
connectwise-automate-cli profile list --json
connectwise-automate-cli profile show briefing
connectwise-automate-cli profile delete briefing --yes
Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Usage error (wrong arguments) |
| 3 | Resource not found |
| 4 | Authentication required |
| 5 | API error (upstream issue) |
| 7 | Rate limited (wait and retry) |
| 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show connectwise-automate-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)Install the MCP binary (run the install script from the Prerequisites section, or see mcp-install.md for per-agent wire-up), then register it:
claude mcp add connectwise-automate-mcp -- connectwise-automate-mcp
Verify: claude mcp list
which connectwise-automate-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:
connectwise-automate-cli <command> [subcommand] [args] --agent
connectwise-automate-cli <command> --help.Alternatives
affaan-m/ECC
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
affaan-m/ECC
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
coreyhaines31/marketingskills
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
event4u-app/agent-config
Use when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.