菜单
Use when managing remote dev server EC2 instances — starting, stopping, connecting, creating new instances, or troubleshooting the `dev` CLI. Also use when the user mentions "dev server", "dev instance", "remote development", or asks to spin up a cloud dev environment.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Michael's operating + emotional coach. Operational mode — daily startup/shutdown, weekly review, pomodoro, inbox capture, daily notes (auto-loads in ~/ws/notes). Emotional/decision mode (Joe Hudson style) — use on "coach me"/"joe coach", stuck/looping/overthinking, harsh self- or other-judgment, a binary either/or decision that won't resolve, or fear, shame, loneliness, anxiety, burnout, or grief, when Michael wants to be met in a feeling rather than handed advice. Not for clinical crises (refer out).
Use when creating or processing Todoist tasks, triaging inbox items, doing daily task review, calibrating Todoist triage behavior, or turning corrections into reusable preferences. Routes to operations (CLI actions) vs calibrated triage (policy, context recovery, preference memory, evals). Trigger this whenever the user asks what to do with Todoist items, wants better task triage, or is refining how Todoist decisions should work.
Run real Deep Research across ChatGPT, Claude, and Gemini in parallel via the user's own logged-in browser (Chrome extension, zero API cost), save each original report to Notion, then synthesize. Use whenever the user wants a "deep dive", "deep research", a thorough multi-source investigation, or to research a topic across the models and compare what each finds. Drives the paid subscription products, NOT the API. NOT for single-fact lookups or ordinary web search — use web-search for those.
Use when setting up, auditing, or improving AI agent infrastructure in a repo — AGENTS.md/CLAUDE.md files, linters, architectural constraints, feedback loops, context tiering, agent specialization, or entropy management. Also triggers on "harness engineering", "agent-friendly repo", "make my repo work well with coding agents", "set up my repo for agents", or "why is my agent struggling".
Interactive Todoist triage with preference learning. Use when the user says "triage", "process my inbox", "clean up tasks", "triage my todoist", "file these captures", or mentions inbox zero. Also use when the user has a batch of raw items (voice notes, links, ideas) that need classifying and routing to Todoist projects or Obsidian. Runs an interactive confirm/correct loop that learns your routing preferences over time.
Use when the user asks to save session context, identify the current session or thread, create a resumable handoff, or prepare a Todoist/note summary that must include the working directory and session id. Works across Codex and Claude Code by detecting runtime-specific session identifiers and normalizing them into one summary.
| name | dev-server |
| description | Use when managing remote dev server EC2 instances — starting, stopping, connecting, creating new instances, or troubleshooting the `dev` CLI. Also use when the user mentions "dev server", "dev instance", "remote development", or asks to spin up a cloud dev environment. |
The dev CLI (~/.dotfiles/bin/dev.ts, Bun script) manages multi-profile remote EC2 dev servers.
| Command | Description |
|---|---|
dev | SSH into default profile (with tmux) |
dev connect [profile] | SSH with tmux, syncs Claude creds, runs setup script if needed |
dev start [profile] | Start EC2 instance, scale up EBS IOPS, update SSH config |
dev stop [profile] | Scale down EBS IOPS, stop EC2 instance |
dev status [profile] | Check SSH reachability and EC2 state |
dev create <name> | Create a new EC2 instance and profile |
dev list | List all profiles with instance state |
dev run [profile] <cmd> | Run a command on the server via SSH |
dev sync-creds [profile] | Manually sync Claude OAuth credentials |
dev -n / dev connect -n | SSH without tmux |
~/.config/dev/profiles.json~/.ssh/config (markers: # dev-managed: <name>)~/.ssh/dev-server-aws.pem (key pair name: dev-server-key)~/.cache/dev-creds-sync-<profile> (30-min interval){
"default_profile": "default",
"profiles": {
"<name>": {
"name": "<name>",
"instance_id": "<i-xxx>",
"volume_id": "<vol-xxx>",
"region": "<aws-region>",
"ssh_host": "<ssh-alias>",
"ssh_user": "<user>",
"instance_type": "<type>",
"setup_script": "<script-url or null>",
"setup_completed": true
}
}
}
These were on the friend's AWS account in us-west-2. Preserved here for reference when recreating:
| Profile | Instance Type | SSH Host | SSH User | Setup Script | Notes |
|---|---|---|---|---|---|
| default | m7i.xlarge | dev | michael | none | General-purpose dev server, 100GB gp3 |
| flywheel | m7i.xlarge | dev-flywheel | ubuntu | agentic_coding_flywheel --yes --mode vibe | Agentic coding flywheel setup |
dev create has hardcoded values that need updating for the new AWS account (636160605813).
In ~/.dotfiles/bin/dev.ts, the create subcommand hardcodes:
| Value | Current (old account, us-west-2) | Needs update to (new account, us-east-1) |
|---|---|---|
| region | us-west-2 | us-east-1 |
| AMI | ami-0cf2b4e024cdb6960 | Find Ubuntu 24.04 arm64 or x86 AMI for us-east-1 |
| Security group | sg-0f155dd58de85c2ae | Create or use existing SG on new account |
| Subnet | subnet-0989be4d1cc95616c | Use a public subnet in new account VPC |
Before using dev create, update these values in dev.ts or the command will fail (old account resources).
The dev CLI scales EBS IOPS on start/stop to save costs:
dev connect automatically syncs Claude Code OAuth credentials from the local macOS Keychain (Claude Code-credentials) to ~/.claude/.credentials.json on the remote instance. This runs at most every 30 minutes.