Document a home network so it can be rebuilt after a move: scan and probe it, then keep a printable PDF playbook and an agent-readable JSON definition.
Plugin network-playbook from marketplace canopy-recommended in danielrosehill/Canopy-Recommended. Commands read from the repo's manifest — 5 days ago.
build-playbookRender the network definition to a dated printable Typst PDF and agent-readable JSON, then save both to Google Drive.
document-hardwareTurn photos and notes of a network cabinet into port maps, cable schedule and layout. Use on "here's a photo of the switch".
probe-infrastructureRead-only probe of router, DHCP, servers, Tailscale, Cloudflare tunnels, public IP and DNS into the network definition.
rebuild-networkReassemble a network at a new location from its playbook JSON, step by step, checking each stage. Use on "we've moved".
scan-lanARP-scan the LAN, save the results, and compare them with the network definition to find new, missing or changed devices.
setup-siteCreate the persistent workspace for documenting a home network site, outside the plugin. Use on "set up network playbook".
update-playbookKeep the network documentation current by rescanning, re-probing, recording changes and reissuing the playbook.
Agent skills for administering Ubuntu machines, desktop or server, locally or over SSH: health and diagnosis, apt/snap/flatpak packages and updates, systemd services and logs, Docker, storage and backups, networking (netplan/NetworkManager), hardware, desktop odds and ends, and shell config. Consolidates linux-desktop-mgmt, linux-server-mgmt and sysadmin-homelab.
49 skills · 2 agents
Slash commands and subagents for managing Docker containers, Compose stacks, volumes, networks, and multi-environment deployments.
12 skills · 7 commands · 5 agents
Build, test, and deploy applications on Cloudflare with platform guidance Skills and the Cloudflare MCP server.
22 skills · 1 MCP server
Agent skills for host security on Ubuntu desktops and servers: ufw firewall setup, status, scoped allows, rule removal and block diagnosis; ClamAV / rkhunter / chkrootkit / Lynis / AIDE install, definition updates, scans and scheduling; read-only security audits, security-update and spyware/telemetry checks; SSH keys, SSH server config and fail2ban; YubiKey/FIDO2 and fingerprint authentication; TLS certificate checks.
18 skills
Write, check and modernise Home Assistant YAML (automations, scripts, templates, blueprints, dashboards) with the syntax of Home Assistant 2026
4 skills · 1 agent · hooks
Bluetooth on Linux from the command line, because the desktop pairing dialogs are unreliable. Diagnose the adapter, scan, pair + trust + connect in one non-interactive bluetoothctl session, manage known devices (connect, disconnect, forget, battery) and reset the stack. BlueZ 5.x; works the same under KDE, GNOME or no desktop.
5 skills
Early access: ruflo's cockpit as a Claude Code mod (function hooks) and the one /ruflo command for every ruflo mod — overview with health alerts, swarm topology, claims flow, federation map, plugin health, learning pipeline, MetaHarness radar, memory, cost gauge, agent timeline, approvals and events; a command palette for confirm-gated actions through the ruflo CLI; auto-opens where it docks; no network by default
1 skill
Control and inspect a live Chrome browser from your coding agent. Record performance traces, analyze network requests, check console messages with source-mapped stack traces, and automate browser actions with Puppeteer.
7 skills · 1 MCP server
Cloud architecture design for AWS/Azure/GCP/OCI, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization
8 skills · 7 agents
Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.
1 skill · 3 commands · 1 agent
Persistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable hosts and never runs commands declared in Markdown. No network upload path. Installs across 60+ agents.
6 skills · 13 commands · hooks
Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.
98 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.