dotfiles

Read and write the second brain — a git-backed Obsidian vault at ~/SourceRoot/brain (PARA structure + a top-level wiki/ knowledge tree). Use whenever the user mentions "brain", "second brain", "knowledge base", "note", "remember", "look up", "find note", "capture", "wiki", or "okf". Also use for any request to save, retrieve, or organize personal knowledge that belongs in the brain rather than in a repo-specific doc.

Write, draft, and polish prose through a human-owned 7-step pipeline. Use whenever the user says "distill", "write article", "draft", "summarize into", "create content", "synthesize", or "publish". Also use for any task where the output is a piece of long-form writing — the pipeline keeps prose quality out of coding sessions.

RETIRED — manage the (now decommissioned) per-machine mlx-audio TTS/STT stack; TTS/STT moved to the cloud audio-gateway (VPS)

Operate the Mac mini remote dev host — connecting from the MacBook over mosh or herdr --remote, running and reattaching many Claude Code agents, herdr workspaces/panes and its socket API, claude --bg durable daemons, the Uptime Kuma readiness heartbeat, and the failure modes specific to a headless always-on Mac. Use when the user mentions herdr, mosh, the mini, "remote dev", "dev host", detaching or reattaching agents, "did my agent survive", sessions dying on lid-close, or asks how to reach a dev server running on the mini.

Manage the personal image stack — public CDN uploads/transform URLs and the private image-share layer. Use whenever an image needs a URL (public or private) for an article, blog post, vault note, README, OpenGraph tag, or a one-off share; or when the user says "upload this image", "share this image", "private image", "publish image", "host this screenshot", "get me a CDN link", "resize this", mentions "image-share", or asks where an image lives.

Bidirectionally sync ALL git repos across two machines — this MacBook and the always-on Mac mini — over SSH, using GitHub/GitLab as the transport. Commits and pushes uncommitted work on both sides, then rebases/fast-forwards each so they converge, with per-repo subagents resolving rebases and merge conflicts. This is a MULTI-repo, TWO-machine operation — distinct from /commit, /ship, or /git-cleanup, which act on a single repo. Use whenever the user wants to sync their machines/repos, "catch up" the laptop to the Mac mini or push laptop work back, is about to travel or just got back, has uncommitted work scattered across many repos, or wants to reconcile branches that diverged between the two machines. Trigger even on a bare "sync", "sync my machines", or "get my repos up to date".

Run validation (format, lint, tsc, test) via sideclaw MCP tool

Smart git commit with conventional commits, OpenSpec awareness, and intelligent splitting for GitHub

Create Excalidraw diagram files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts. Delegates JSON generation + hydration to the sideclaw `excalidraw_diagram` MCP tool.

Guided implementation with research, exploration, and validation. Scales from quick inline edits to multi-subagent workflows based on task complexity.

Query and debug OpenTelemetry data (traces, logs, metrics) in ClickHouse (HyperDX/ClickStack) via the sideclaw MCP `otel` tool. Use when investigating application errors, slow or missing traces, log anomalies, service health, or any observability question in local dev or VPS production (local + prod both supported).

GitHub PR workflow - create, status, merge with intelligent conflict handling

Multi-angle code review via sideclaw MCP tool (claude-sonnet-5, currently on Max per SIDECLAW_WORKER_BACKEND=max; IU unified endpoint fallback when unset). Add --deep to also run Anthropic's native correctness + security review, also on Max.

Dependency upgrade assistant with research and validation phases

Deep technical research via the research-gateway MCP — agentic Tavily + Context7 + page-fetch with cross-verification, returns a cited markdown report

1Password secrets management — vault structure, op:// references, .env.tpl patterns, adding/rotating secrets, cron setup, troubleshooting

Scaffold and run a RALPH loop — an autonomous multi-group implementation plan executed by Claude via CLI with state tracking, retries, and per-group learning notes

Update agent rules (React, TanStack, Elysia best practices) from upstream GitHub repos. Use this skill when the user wants to update, sync, check versions, add new rule sets, or troubleshoot the rules setup. Also trigger when the user mentions "agent skills", "agent rules", "react rules", "tanstack rules", "elysia rules", or asks about the rules architecture.

Read and interpret Excalidraw diagrams (.excalidraw + .svg) via the sideclaw read_drawing MCP tool. Off Max, stronger vision model, structural JSON ground truth.

Design and style professional, aesthetic data visualizations and analytics dashboards — visx charts + Mantine chrome with a centralized, enforced color system. Use when building or restyling charts, dashboards, or metric UIs, choosing a chart palette, or when existing charts look "childish"/inconsistent/over-colored.

Deep static analysis (dead code, duplication, circular deps, complexity) via fallow + claude -p subprocess

Validate the IU unified endpoint and discover better models. Probes every transport, health-checks the models configured in OpenCode (opencode.json), reports per-model backend redundancy + live latency, and diffs the live catalog to surface newer/hotter models worth adopting — for OpenCode and for the Hermes Agent (especially Kimi). Use when checking endpoint health, picking a reliable model/host, or deciding whether to upgrade configured models.

Full deployment flow — auto-detects state, runs check/review/commit/PR/CodeRabbit iteration/merge/release. Smart direct-to-master vs PR detection.

Cloudflare API operations across VPS and HomeLab — DNS records, tunnel ingress, multi-zone. Single skill for both servers; uses op://common/cloudflare for shared bits and per-server vaults for tunnel TOKEN/ID. Never exposes the API token to Claude Code directly.

Semantically group and squash branch commits before PR — eliminates noise commits, proposes logical groupings, executes via pure git soft reset. Use before /pr create when branch has multiple commits or noisy history.

Chrome DevTools debugging via haiku subagent — console, network, DOM, screenshots. Isolates expensive MCP responses from main context.

Question until direction is completely clear, then generate PRD or transform to ralph groups depending on complexity