メニュー
Chrome DevTools debugging via haiku subagent — console, network, DOM, screenshots. Isolates expensive MCP responses from main context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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".
| name | browse |
| description | Chrome DevTools debugging via haiku subagent — console, network, DOM, screenshots. Isolates expensive MCP responses from main context. |
| context | fork |
| model | haiku |
Debug frontend issues using Chrome DevTools MCP in an isolated forked context.
Chrome DevTools MCP is registered globally but uses deferred tool loading (~400 tokens for tool names, schemas only loaded on demand via ToolSearch). This skill runs in a context: fork to keep MCP call responses (~5-20k tokens for screenshots, DOM, network) out of the main thread.
Load tools on demand via ToolSearch:
ToolSearch("select:mcp__chrome-devtools__navigate_page")
ToolSearch("select:mcp__chrome-devtools__take_screenshot")
ToolSearch("select:mcp__chrome-devtools__list_console_messages")
ToolSearch("select:mcp__chrome-devtools__list_network_requests")
ToolSearch("select:mcp__chrome-devtools__evaluate_script")
ToolSearch("select:mcp__chrome-devtools__click")
ToolSearch("select:mcp__chrome-devtools__fill")
Return a concise findings report to the main agent:
## Browse: [URL]
**Console errors:** [count] — [summary]
**Network failures:** [count] — [summary]
**Visual:** [description or "looks correct"]
**Action needed:** [yes/no + what]
Keep response under 1500 characters. List findings, not process.