dinglebear-ai
OrganizationRust MCP server and CLI for Apprise notification fan-out across dozens of delivery backends, with stdio/HTTP transports, auth, and plugin packaging.
Categories
Indexed Skills (20)
apprise
Send push notifications through apprise-rmcp — a standalone Rust MCP bridge to the Apprise universal notification library (Slack, Discord, email, Telegram, and 100+ more). Use this skill whenever the user wants to send a notification, push an alert, notify a service, fire off a push message, or use Apprise in any way — even if they just say "send me an alert" or "let me know when X is done". Covers three tiers: MCP tool (preferred), CLI binary, and direct REST API curl calls. Trigger phrases include: send notification, push alert, Apprise notify, send push notification, alert via Apprise, notify service, send alert, notify via apprise, ping me, fire an alert, send a Slack notification, Discord alert, Telegram message, send me an email, notify via Pushover, route to Slack/Discord/Telegram/email/PagerDuty.
unraid
Query and monitor an Unraid NAS/homelab server — array health, disk temperatures, Docker containers, virtual machines, system metrics, notifications, alerts, shares, UPS status, log files, network, plugins, parity history, registration, rclone backups, remote access, and Unraid Connect. Use this skill whenever the user asks about their Unraid server, array state, disk health, SMART status, parity check, Docker containers running on Unraid, Unraid VMs, Unraid memory or CPU usage, Unraid notifications or alerts, Unraid shares, UPS battery on Unraid, Unraid logs, or anything related to an Unraid system. Always invoke this skill when the user mentions "unraid", "array", "parity", "Unraid docker", "Unraid metrics", or asks about NAS health on an Unraid box — even if they don't use the word "skill".
tailscale
tailscale-rmcp MCP server — query and manage your Tailscale network from Claude. Use this skill whenever the user mentions Tailscale devices, tailnet status, VPN nodes, MagicDNS, Tailscale ACL, access control policy, subnet routes, tailnet members, API keys, or wants to authorize or delete a device. Trigger phrases include: "list my Tailscale devices", "show tailnet status", "what's on my tailnet", "check my VPN devices", "Tailscale ACL", "MagicDNS", "Tailscale DNS", "tailnet users", "authorize this device", "delete device from Tailscale", "device routes", "subnet routes", "Tailscale API keys", "tailscale network". Always use this skill — do not try to query Tailscale without it.
cortex
This skill should be used when the user asks to "search logs", "check errors", "tail logs", "show recent logs", "find log entries", "correlate events", "list hosts", "log stats", "syslog", "check homelab logs", or mentions system logs, syslog, log analysis, or log intelligence across homelab hosts.
frustration-assessment
This skill should be used after running cortex action=abuse_investigate to analyze the resulting evidence bundle. Use when the user asks to assess frustration incidents, evaluate abuse signals, analyze agent or user friction, produce a frustration report, or follow up on abuse_investigate results.
hook-friction-assessment
This skill should be used after running cortex assess hooks [--hook <name>] (or the underlying hook_investigate MCP action that produces HookIncidentEvidence) to analyze why a Claude Code/Codex/Gemini hook failed, timed out, misfired, or otherwise degraded the agent session. Use when the user asks to assess hook reliability, evaluate why a PreToolUse/PostToolUse/Stop/SessionStart hook failed or blocked a flow, propose hook script or hook-config changes, or follow up on hook incident evidence.
incidents
Triage and manage cortex-detected incidents — unacknowledged error signatures, recent notification firings, similar past incidents, and full incident context around a time window. Use whenever the user asks "what errors haven't been addressed", "what's still firing", "have we seen this before", "ack this error", "acknowledge this signature", "what notifications went out recently", or wants a full picture of what happened around an incident.
mcp-friction-assessment
This skill should be used after running cortex assess mcp <tool-or-server> (or the underlying cortex sessions mcpinvestigate pipeline that produces McpIncidentEvidence) to analyze why an MCP tool or server call failed, misfired, or confused the agent. Use when the user asks to assess MCP tool reliability, evaluate why a tool call failed or was misused, propose tool-doc or server-config changes, or follow up on MCP incident evidence.
report
This skill should be used when the user asks for a homelab health report, syslog summary, fleet status report, log analysis summary, 'what happened in the last 24 hours', 'show me this week's errors', 'summarize recent activity', or any time-bounded log analysis that should produce a written markdown report.
searching-sessions
Search and explore AI/Claude/Codex conversation history stored in cortex. **Trigger when:** the user asks to "search sessions", "find conversations", "what did I work on", "session history", "past conversations", "ask history", "when did I last use X", "show recent sessions", "list AI projects", "what tools have I used"; OR when **referencing past work** like "we've done this before", "we fixed something similar", "haven't we implemented this", "this was already working", "why did we do that again", "I thought we already solved this"; OR when **questioning past decisions** like "why did we implement it this way", "what was the reasoning for", "didn't we discuss this already", "this seems familiar"; OR when the user is **under the something was done before** or wants to find context about previous implementations, fixes, or decisions. Use for session search, conversation discovery, past work retrieval, implementation history, or decision archaeology.
skill-improvement-assessment
This skill should be used after running cortex assess skill <skill> (or the cortex sessions skillinvestigate pipeline that produces PR 3's SkillIncidentEvidence) to analyze whether a Claude Code/Codex/Gemini skill performed well. Use when the user asks to assess skill quality, evaluate why a skill failed or underperformed, propose SKILL.md doc changes, or follow up on skill incident evidence.
topology
Answer homelab topology and cross-host correlation questions using cortex's graph-backed inventory — what services run on a host, what depends on what, fleet-wide heartbeat state, correlating events across hosts around a point in time, and graph entity/neighborhood/explanation queries. Use whenever the user asks "what's running on <host>", "what depends on <service>", "fleet health", "what else happened around this time", "correlate this across hosts", or wants an evidence-backed explanation of how two things in the homelab are connected.
troubleshoot
Troubleshoot cortex connection failures, missing logs, unhealthy containers, restart loops, or vague "logs aren't working" reports.
gotify
How to interact with the Gotify self-hosted push notification server via the gotify-mcp MCP tool, CLI binary, or direct REST API. Use this skill whenever the user wants to send a push notification, check notification history, manage Gotify applications or clients, check Gotify server health, delete messages, or do anything with Gotify — even if they just say "send an alert" or "notify me when X is done". Also invoke this when the user asks about notification history, wants to know if their Gotify server is up, or mentions monitoring, alerting, or push notifications in a self-hosted context.
synapse2
Use when the user needs to inspect or manage Synapse2-managed Docker/Compose infrastructure via flux, or SSH/local host files, processes, logs, ZFS, and allowlisted commands via scout. Prefer MCP tools first, CLI second, REST last; use write or confirmation-gated actions only when explicitly requested or necessary.
ytdl
Download audio or video from YouTube, Vimeo, or any yt-dlp-supported site and transfer it to a configured local, SSH, or rclone target. Use when the user wants to grab/download/save/rip a song, video, album, playlist, or channel from a URL, pull audio off a YouTube link, or archive media to their server. Triggers on "download this", "grab the audio", "rip this playlist", "save this video", or any media URL the user wants pulled.
unifi
Use this skill whenever the user asks about their UniFi network — connected clients, who's on the WiFi, which devices are online, access points, switches, gateways, network health, site health, active alarms, network events, WiFi configurations (SSIDs), controller sysinfo, or their authenticated UniFi identity. This skill covers the unifi-rmcp MCP server, a Rust bridge to official and internal UniFi APIs via X-API-KEY. Legacy convenience actions are read-only; mutating actions require explicit admin authorization. Trigger phrases include: "UniFi clients", "connected clients", "who's on the network", "UniFi devices", "access points", "APs", "UniFi switches", "WiFi networks", "WLAN config", "SSIDs", "network health", "UniFi health", "site health", "UniFi alarms", "network alerts", "network events", "UniFi events", "sysinfo", "controller version", "UniFi me". Always use this skill rather than guessing at curl commands or API paths — the UniFi REST API has several gotchas around path prefixes and auth that this s
rarcane
Use when the user wants to inspect or manage Arcane Docker resources through rarcane, including projects, containers, images, networks, volumes, registries, vulnerability scans, image updates, environments, system operations, or GitOps syncs.
logs
Tail or follow cortex service logs from Docker Compose. Use when the user asks for cortex service logs, startup logs, crash logs, plugin deployment logs, Docker logs, or follow mode. This is for the service's stdout/stderr, not client syslog entries.
version-check
Check whether the running cortex Docker container matches the local Compose image. Use when the user asks whether cortex is current, stale, deployed, updated, running the latest plugin image, or needs a restart/recreate after an upgrade. Supports an optional --pull mode for Docker image comparison.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.