Best for
- Use when the user asks to list, search, or inspect ConnectWise Control (ScreenConnect) remote-support and access sessions, run a command on a guest machine, rename or tag sessions, manage instance users, or read the aud…
Servosity/msp-skills/skills/connectwise-control/SKILL.md
Use when the user asks to list, search, or inspect ConnectWise Control (ScreenConnect) remote-support and access sessions, run a command on a guest machine, rename or tag sessions, manage instance users, or read the audit log. Turns the ScreenConnect instance surface into typed commands with an offline SQLite mirror. Trigger phrases: `list connectwise control sessions`, `screenconnect session detail`, `run command on a screenconnect guest`, `connectwise control audit log`, `use connectwise contr
Decision brief
Turns the ScreenConnect instance surface into typed commands with an offline SQLite mirror. Trigger phrases: `list connectwise control sessions`, `screenconnect session detail`, `run command on a screenconnect guest`, `connectwise control audit log`, `use connectwise contr
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-control"Inspect the Agent Skill "connectwise-control" from https://github.com/Servosity/msp-skills/blob/30e109db0872897de0b88adb38d81d4c292da3ae/skills/connectwise-control/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
ConnectWise Control authenticates with HTTP Basic auth - the same user name and password you use for the web console - against your instance base URL. Set all three:
This skill drives the connectwise-control-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
This CLI uses Chrome-compatible HTTP transport for browser-facing endpoints. It does not require a resident browser process for normal API calls.
audit - Audit metadata and audit-log queries (AuditService).
When you know what you want to do but not which command does it, ask the CLI directly:
Permission review
The documentation includes network, browsing, or remote request actions.
bash <(curl -fsSL https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-control/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-control/install.sh)The documentation includes network, browsing, or remote request actions.
iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-control/install.ps1 | iexThe documentation asks the agent to run terminal commands or scripts.
Drive a ConnectWise Control (ScreenConnect) instance from the terminal or an AI agent: list and inspect remote-support and access sessions, read session detail and the audit log, manage session names and custom properties, manage instance uThe 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 | 81/100 | 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-control-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-control/install.sh)
iwr -useb https://raw.githubusercontent.com/servosity/msp-skills/main/skills/connectwise-control/install.ps1 | iex
connectwise-control-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.
Drive a ConnectWise Control (ScreenConnect) instance from the terminal or an AI agent: list and inspect remote-support and access sessions, read session detail and the audit log, manage session names and custom properties, manage instance users, and run an approved command on a guest machine. Output is JSON-first with an offline SQLite mirror for fast session lookups. Authentication is HTTP Basic with your instance login (CONNECTWISE_CONTROL_USERNAME / CONNECTWISE_CONTROL_PASSWORD) against your instance base URL (CONNECTWISE_CONTROL_BASE_URL).
This CLI uses Chrome-compatible HTTP transport for browser-facing endpoints. It does not require a resident browser process for normal API calls.
audit - Audit metadata and audit-log queries (AuditService).
connectwise-control-cli audit get-info - Returns metadata about the audit subsystem (available event types and retention).connectwise-control-cli audit query-log - Queries audit-log records by session, time window, and event type.security - Users, roles, and security configuration (SecurityService).
connectwise-control-cli security delete-user - Deletes an instance user. Requires the x-anti-forgery-token header. Wire format: positional array ['<userName>'].connectwise-control-cli security get-configuration - Returns the instance security configuration, including users and roles. Wire format: empty positional array [].connectwise-control-cli security save-user - Creates a new instance user or updates an existing one. Requires the x-anti-forgery-token header.session_groups - Session groups that organize sessions (SessionGroupService).
connectwise-control-cli session-groups - Returns all session groups configured on the instance.sessions - Remote support, access, and meeting sessions (PageService).
connectwise-control-cli sessions add-event-to - Queues a session event (such as Wake-on-LAN) against one or more sessions.connectwise-control-cli sessions get-access-token - Issues a one-time access token/URL to join a session. Wire format: positional array ['<group>', '<sessionID>'].connectwise-control-cli sessions get-detail - Returns full detail (connections and recent events) for one session.connectwise-control-cli sessions list - Returns the live session list for a session type and group.connectwise-control-cli sessions run-command - Queues a command or control event on a session.connectwise-control-cli sessions update-custom-property - Sets one custom property value on a session.connectwise-control-cli sessions update-name - Renames a session. Wire format: positional array ['<group>', '<sessionID>', '<newName>'].When you know what you want to do but not which command does it, ask the CLI directly:
connectwise-control-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.
ConnectWise Control authenticates with HTTP Basic auth - the same user name and password you use for the web console - against your instance base URL. Set all three:
export CONNECTWISE_CONTROL_BASE_URL="https://company.screenconnect.com"
export CONNECTWISE_CONTROL_USERNAME="<your-instance-user>"
export CONNECTWISE_CONTROL_PASSWORD="<your-instance-password>"
Or persist them in ~/.config/connectwise-control-cli/config.toml.
Run connectwise-control-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-control-cli session-groups --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-control-cli feedback "the --since flag is inclusive but docs say exclusive"
connectwise-control-cli feedback --stdin < notes.txt
connectwise-control-cli feedback list --json --limit 10
Entries are stored locally at ~/.local/share/connectwise-control-cli/feedback.jsonl. They are never POSTed unless CONNECTWISE_CONTROL_FEEDBACK_ENDPOINT is set AND either --send is passed or CONNECTWISE_CONTROL_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-control-cli profile save briefing --json
connectwise-control-cli --profile briefing session-groups
connectwise-control-cli profile list --json
connectwise-control-cli profile show briefing
connectwise-control-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-control-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)claude mcp add connectwise-control-mcp -- connectwise-control-mcp
claude mcp listwhich connectwise-control-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:
connectwise-control-cli <command> [subcommand] [args] --agent
connectwise-control-cli <command> --help.Alternatives
jackchuka/skills
Audit skill SKILL.md files for compliance with the agentskills.io specification and house conventions. Checks frontmatter fields (name, description, compatibility, metadata, argument-hint), metadata sub-fields (author, scope, layer, confirms), and layer/suffix consistency. Use when adding new skills, reviewing skill quality, or ensuring all skills follow the spec. Triggers: "audit skills", "check skill spec", "skill compliance", "are my skills up to spec", "/claude-skill-spec-audit".
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
GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.
affaan-m/ECC
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.