soulmachine

@soulmachine source repo

27 skills
0 followers
17 hours ago last updated

▌
To Features · soulmachine
Generate FEATURES.md at the repo root by reading CONTEXT.md and docs/adr/, then enumerating the user-facing features the domain implies. Use after /grill-with-docs has settled the domain language and before /to-prd writes per-feature specs. Bridges the product→engineering gap between domain understanding and feature specification — the missing step that mattpocock's chain doesn't cover natively.

0
installs
▌
Swe Workflow · soulmachine bundle
Orchestrates the full five-stage flow from raw idea to shipped PR — grill-with-docs → to-prd → to-issues → triage → worktree+planning-with-files. Each stage answers one question (What do I want? / What does done look like? / What are the units of work? / What's actionable? / Build it). Use when the user has an idea but no spec yet, wants to plan a feature end-to-end, says "let's PRD this," asks "how do I start on this idea?", or grabs a ready-for-agent issue to implement.

0
installs
▌
Affix Domains · soulmachine bundle
Attach popular brand prefixes/suffixes to a seed word and check availability against the authoritative registry. Starts at `.com`; if the seed word's own `.com` is taken, escalates the whole sweep to .com/.net/.org/.ai/.io/.co/.app/.cc. Use when the user names a word and asks for prefix/suffix domain variants, or wants domains generated by adding endings like -labs/-ify/-ly or beginnings like deep-/open-/get-. Catalogs are ranked by 2025–26 hot-AI-startup evidence; scan and surface in rank order.

0
installs
▌
Ssh Claude Auth · soulmachine bundle
Claude Code auth on a headless Mac over SSH

0
installs
▌
Trusted Publish · soulmachine bundle
trusted-publish

0
installs
▌
Chrome Cdp Setup · soulmachine bundle
Set up Google Chrome on macOS to always launch with the Chrome DevTools Protocol enabled (127.0.0.1:9222) via a Dock launcher app, so local AI agents (Playwright, Puppeteer, browser-use, OpenClaw) can drive the real logged-in browser with no per-connection approval prompt. Use when the user wants to enable a CDP/remote-debugging port for Chrome, pick between the flag, chrome://inspect, and extension routes, connect an agent to Chrome, test a CDP connection, diagnose a 404 from /json/version or an "Allow remote debugging?" dialog, or troubleshoot/revert an existing Chrome-CDP Dock setup.

0
installs
▌
Ghostty Terminfo · soulmachine
Use when SSHing to a remote host from Ghostty terminal and encountering terminfo errors, missing colors, broken key bindings, "unknown terminal type" warnings, or an entry that looks installed but still does not resolve

0
installs
▌
Macos Smb Server · soulmachine bundle
Configure macOS's built-in SMB server (com.apple.smb.server) — settings apply only when committed via SCPreferences, never via defaults write. Use when a Mac's "Macintosh HD" or a home folder is visible to other machines on the LAN (virtual shares), when disabling guest access on file shares, when a com.apple.smb.server change doesn't take effect, or when proving server-side which shares a Mac offers.

0
installs
▌
Herdr Rename Hook · soulmachine bundle
Install the hook that renames the Herdr agent, pane and tab to match a Claude Code or Codex session renamed with /rename.

0
installs
▌
Mac Smb Automount · soulmachine bundle
Auto-mount another Mac's SMB shares on macOS at login and keep them mounted (LaunchAgent + NetFS), over Tailscale or LAN, authenticating with the shared Apple ID (Kerberos LKDC) so no password is stored. Use when mounting a Mac's shares automatically; when an SMB connection to a Mac prompts for a password or returns "Authentication error" despite the right password; when a mount agent keeps declaring healthy mounts stale; or when replacing local Dropbox/Google Drive sync clients with mounts of the server's copies.

0
installs
▌
Openclaw Diagnose · soulmachine
Diagnose and fix OpenClaw gateway and node host issues. Use when openclaw services have warnings, connection failures, pairing errors, or port conflicts.

0
installs
▌
Private Fork Sync · soulmachine
Make a public GitHub fork private and keep it synced with its upstream parent. Use when the user wants to make a fork private, or to pull/sync newer commits from the upstream parent into their fork.

0
installs
▌
Sync Claude Accounts · soulmachine bundle
Distribute full OAuth Claude Code credentials (claude-accounts.json) from a single designated refresh-authority Mac to the rest of a fleet, and operate the scheduled automation that does it — the com.claude.fleet-refresh and com.claude.fleet-health LaunchAgents, their logs, and the proactive refresh that keeps receivers from ever rotating a token themselves. Use when syncing or propagating Claude Code logins across Macs or a fleet, when setting up, auditing, or reading a cycle of the recurring credential push, when a scheduled push seems to have stopped, when checking whether the fleet is healthy, or when the user mentions claude-accounts.json, cswap import, cux add, claude-swap, refresh authority, or fleet-refresh-credentials. To repair an account that is already dead — "re-login needed", EXPRD, null headroom — use the refresh-claude-account skill instead.

0
installs
▌
Ubuntu Lxd Gpu Server · soulmachine bundle
Install LXD on an Ubuntu server and pass all NVIDIA GPUs into LXD system containers via CDI — install snapd+LXD (snap), run `lxd init` with a ZFS or dir storage pool, set up a host CDI spec at /etc/cdi and wire the nvidia-container-toolkit auto-refresh units so it stays fresh across driver upgrades, and grant every GPU to every instance through the default profile, then verify nvidia-smi inside a container. Use when asked to install or set up LXD/lxc on a GPU host, give LXD containers GPU access, do LXD NVIDIA GPU passthrough, share all GPUs across LXD instances, when `nvidia.runtime=true` fails with "driver rpc error: timed out" (use CDI instead), or when LXD GPU containers break after a host driver upgrade (stale or duplicate CDI spec). Assumes the host NVIDIA driver + nvidia-container-toolkit are already installed (see ubuntu-nvidia-gpu-enablement).

0
installs
▌
Build Stealth Rustdesk · soulmachine bundle
Build a patched, fully-stealth RustDesk.app from source on Apple Silicon, from a maintained private fork — no menu-bar icon, no Dock icon, no on-screen CM panel compiled in, remote keyboard still works, codesigned and ready to deploy. Use when building or version-bumping the stealth RustDesk binary; deploy the result with the deploy-stealth-rustdesk skill.

0
installs
▌
Cua Macos Lume Sandbox · soulmachine bundle
Provision a macOS VM as a cua computer-use sandbox with lume on Apple Silicon — pull or APFS-clone an image, size it, ensure autologin, install cua-driver plus a LaunchAgent, grant TCC unattended when SIP is off, set the guest resolution, and verify with a real screen capture. Use when asked to set up, rebuild, or repair a cua or computer-use sandbox VM, to register the cua-driver MCP server, or when cua-driver reports a daemon in "unknown" state, TCC grants that will not stick, or screenshots at the wrong resolution.

0
installs
▌
Refresh Claude Account · soulmachine
Repair a dead or expired Claude Code account by restoring a full OAuth login — re-seed it from a machine that still has a live copy, or re-authenticate with `claude auth login` — then capture it with `cswap add` and export `claude-accounts.json` for the `sync-claude-accounts` skill to distribute. Use when `cswap list` says "re-login needed — refresh token dead", when `cux status` shows an account as EXPRD, when `cswap auto --dry-run` reports null headroom, or when `fleet-refresh-credentials` aborts because the refresh authority holds a dead account.

0
installs
▌
Deploy Stealth Rustdesk · soulmachine bundle
Deploy a prebuilt stealth-patched RustDesk.app as an unattended macOS LaunchAgent service — no Dock icon, no menu-bar icon, no on-screen CM panel, remote keyboard still works, survives reboot with nobody logged in. Use when installing a stealth RustDesk on a target Mac; build the app first with the build-stealth-rustdesk skill.

0
installs
▌
LLM Inference Benchmark · soulmachine bundle
Benchmark OpenAI-compatible LLM inference servers

0
installs
▌
Ubuntu Zfs Mirror Install · soulmachine bundle
Install Ubuntu Server onto a 2-disk ZFS mirror root (rpool→/) plus a striped data pool (dpool→/data) via debootstrap + ZFSBootMenu, or fall back to a plain single-disk ext4 install (GRUB-EFI) when there aren't two equal-size disks. Use when asked to install Ubuntu on ZFS, build a ZFS mirror root / rpool+dpool layout, set up root-on-ZFS with ZFSBootMenu, or do a scripted Ubuntu Server install on a UEFI x86 server with one or two SSDs/NVMes.

0
installs
▌
Mac Mini As Headless Server · soulmachine bundle
Use when setting up a Mac (especially Mac Mini or Apple Silicon Mac Studio) for unattended 24/7 server operation, headless use, or remote-only access. Covers sleep prevention, screen saver, Wake-on-LAN, auto-restart, App Nap, SSH enablement, and — on Apple Silicon — a caffeinate LaunchDaemon that stops the headless display from parking (physical panel and VNC/screen-share going black even with displaysleep=0). Targets macOS 15 (Sequoia) and later.

0
installs
▌
Asus Esc8000 Gpu Bios Tuning · soulmachine bundle
Apply a low-latency GPU-serving + VM-passthrough BIOS profile to ASUS ESC8000-E12P (ASMB12/AMI-BMC, Xeon 6/GNR) servers over Redfish — diff current settings, stage, reboot, verify. Use when asked to optimize/tune BIOS for GPU inference/serving, set performance power profile, enable Resize BAR / SR-IOV / disable SNC, or replicate one server's BIOS config onto another ESC8000.

0
installs
▌
Lxd Docker Firewall Conflict · soulmachine bundle
Diagnose and fix the well-known Docker/LXD firewall conflict on a host running both. Docker sets the iptables FORWARD chain policy to DROP and accepts only its own bridges, so forwarded traffic from the LXD bridge (lxdbr0) is silently dropped and LXD containers/VMs get no outbound internet (the host itself is fine). Fix: accept the LXD bridge in the DOCKER-USER chain, then persist it with a systemd unit ordered after docker.service. Use when an LXD container has no internet or cannot reach archive.ubuntu.com, when "apt update"/"apt-get"/"curl" inside an LXD container times out or reports "Network is unreachable" / "connection timed out" / "Failed to fetch" (but the same works on the host), when a packer-lxd image build fails during "apt update", when LXD container networking breaks right after installing Docker, or when iptables shows "policy DROP" on FORWARD with an empty DOCKER-USER chain. The LXD bridge already has ipv4.nat=true and net.ipv4.ip_forward=1 — it is purely a FORWARD-chain drop, not a NAT or DN

0
installs
▌
Ubuntu Nvidia Gpu Enablement · soulmachine bundle
Enable NVIDIA GPUs on a Ubuntu server for compute/inference serving — install the open-kernel-module driver (required for Blackwell/Hopper), CUDA toolkit, turn on IOMMU (intel_iommu=on iommu=pt), set up nvidia-persistenced, and install/wire a container runtime (Docker + nvidia-container-toolkit, or the minimal CLI), then verify all GPUs, IOMMU groups, P2P, nvcc, and GPU containers. Use when asked to enable or set up NVIDIA GPUs, install the NVIDIA driver + CUDA on Ubuntu, install Docker + nvidia-container-toolkit for GPU containers, configure GPU IOMMU/passthrough, prepare a host for GPU serving (vLLM/PyTorch/TensorRT/NIM), or troubleshoot nouveau, persistence mode, GPU-in-container, or driver/CUDA/glibc problems.

0
installs
▌
Asus Esc8000 Firmware Upgrade · soulmachine bundle
Check and upgrade BMC firmware and BIOS on ASUS ESC8000-E12P (and similar ASMB12/AST2600 AMI-BMC ASUS servers) via Redfish and the BMC's HPM wizard API. Use when asked to check firmware/BIOS versions, update BMC or BIOS on ASUS GPU servers, or recover a BMC stuck in firmware-update/flash mode (login blocked, Redfish 503).

0
installs
▌
Deploy Kimi K3 On Rtx Pro 6000 · soulmachine bundle
Deploy Kimi-K3 (GGUF, llama.cpp) on 8x RTX PRO 6000 Blackwell Server Edition (sm_120)

0
installs
▌
Deploy Kimi K26 On Rtx Pro 6000 · soulmachine bundle
Deploy and serve Moonshot Kimi-K2.6 (1T MoE, MLA, 256K context, vision) in a user-chosen quantization — official INT4 QAT (moonshotai/Kimi-K2.6, compressed-tensors→Marlin; vLLM or SGLang) or NVFP4 (nvidia/Kimi-K2.6-NVFP4, ModelOpt FP4; vLLM only — SGLang NVFP4 is NaN-broken on sm_120) — on a Linux server (verified Ubuntu 26.04) with 8× NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB, sm_120) GPUs. The quantization and the engine are both chosen at deploy time with a hardware-based recommendation. Runs an official-image Docker container via nvidia-container-toolkit CDI (--device nvidia.com/gpu=all --ipc=host --network host, bind-mounted weights; --network host is required for NCCL's GPU-to-GPU transport / IB-RoCE GPUDirect RDMA, and the server binds 0.0.0.0 with off-box clients reaching it through an authenticated Caddy proxy that upstreams over loopback 127.0.0.1 — structural, no firewall), exposing an OpenAI-compatible API on :30000 behind one static systemd service `kimi-k26` (quant + engine selected vi

0
installs

27 published skills