Monitor Claude
Run a read-only Claude Code process health check — shows active sessions, cmd/node counts, anomalies, and copy-pasteable kill commands.
Reel
Analyze an Instagram Reel into an action report — deep mode (-h, default) does yt-dlp download, Whisper transcription, frame extraction, comments, and web research; fast mode (-l) does a Firecrawl + Playwright visual read only. Use when you want to know what a reel is about and whether it is worth acting on.
Orient
Drop into a project you haven't touched in a while and get oriented fast — what it is, the stack, entry points, recent activity, and where to start. For context-switching between many repos.
Ship
Pre-deploy gate, deploy, and smoke-test in one pass — runs build/checks, deploys (Vercel by default), then verifies the live URL actually works. For shipping with confidence.
What Breaks
Pre-mortem — assume the plan already failed and hunt the reasons before you commit. Adversarial failure-mode analysis ranked by likelihood and impact, with concrete mitigations. For pressure-testing an idea, change, or plan.
Clone Website
Reverse-engineer and rebuild a website as a pixel-perfect clone in one pass — extracts assets, CSS, animations, and content section-by-section and dispatches parallel builder agents in worktrees as it goes. Use whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any web page. Provide the target URL as the argument.
Sanity Check
Post-implementation audit — checks codebase against the goal, runs stack-specific checks, security, performance, logic edge cases, and tests, then produces a PASS/WARN/FAIL report with severity tiers.
Yt Tran
Analyze a YouTube video into an action report — deep mode (-h, default) synthesizes transcript, description, chapters, top comments, thumbnail, and key frames; fast mode (-l) returns transcript + key points only. Use to extract the substance of a video without watching it.
Braindump
Turn a messy voice ramble into clean, structured output — fixes transcription slips and organizes stream-of-consciousness into a spec, task list, outline, or decision.
Catch Up
Cross-project command center — scans every project's saved session states and checkpoints and shows all your open work and next actions in one dashboard. For when you've lost track of what's in flight across everything.
Double Check
Rigorously review the work for defects, fix what's safely fixable, verify, and end with a confidence rating out of 10. Hunts careless slips, code-quality issues, logic gaps, intent-vs-execution mismatches, and edge cases. An audit-and-fix pass over existing work, not a fresh build.
Heavy
Launch a pre-engineered "heavy prompt" from your local library in the current interactive session — big self-contained research/build/optimize jobs that write line-addressable structured output. /heavy lists the library; /heavy NN launches or resumes run NN.
Explain For Grandma
Re-explain the previous response in plain, beginner-friendly language — decode the jargon, buzzwords, and technical concepts.
Make Prompt
Craft a high-quality, ready-to-paste prompt for whatever you describe. Adapts to the target — LLM/chat prompt, image-gen, or system/agent prompt — and applies the right prompt-engineering best practices. Produces the prompt, not advice about prompts.
Biz Validate
Validate a business idea before you invest time or money — problem research, market sizing, competitive landscape, persona simulation (how target customers actually react), unit economics, red flags, and a GO / PIVOT / STOP verdict. Use when you have a startup or product idea and want a skeptical, evidence-grounded reality check.
Save Session
Save current session state to project memory (session_state_[topic].md), discoverable via /catch-up and /resume. Archives stale states; keeps MEMORY.md uncluttered.
Heavy Build
Author a new heavy prompt for your heavy/library/. Interviews you for the goal and shape, decomposes it into phases → idempotent steps with anchored output sections, encodes defaults so the run never needs to ask, assigns the next ID, writes the file, and updates the library INDEX. Run /heavy-review after.
Heavy Review
Adversarially review a heavy prompt in heavy/library/ before it is run. Hunts logical gaps, missing defaults, unattended-safety violations, resumability holes, output-spec errors, guardrail gaps, and cost-realism issues. Produces a severity-tagged report (BLOCKER / SHOULD / NICE) and a PASS / NEEDS-FIX verdict, then offers to apply fixes.
Overnight
Schedule the current task to run unattended overnight (default 2 AM) via headless `claude -p`, isolated on a git branch, with results auto-surfaced in your next morning session. Use when the user says "do this at 2am", "run this while I sleep", or "queue this for tonight".