seilk

Deprecated alias for /teleport-update. Pushes local Claude Code changes to your private hub.

Beam your Claude Code setup across machines. Routes to the appropriate teleport command.

Update already-pushed private/public repos with local changes that haven't been synced yet

First-time setup: create private hub repo, scan and export your Claude Code environment

Import configs from another user's public teleport repo

Pull configs from your hub to this machine

Publish safe configs to a public repo for other users to import

Quality-driven feedback loop that pushes a paper draft toward genuinely strong A+ through two independent evaluator agents (Reviewer Simulator, Persuasion Analyst). Each round proposes concrete improvements; the main agent applies the best ones. The goal is not convergence but maximizing quality. Use when the user says 'feedback loop', 'evaluate paper', 'improve paper', 'A+ loop', or wants iterative quality improvement on a paper draft.

Finalize a paper draft for submission. Runs the full pre-submission QA pipeline: format audit, adversarial red-team attack, iterative quality improvement loop, optional LaTeX build, and final readiness report. Use when the user says 'finalize', 'prepare for submission', 'final check', 'last pass', or any variation of making a paper ready to submit. MUST be used before submitting a paper to any venue.

Instant on-the-fly harness assembler. Discovers available skills, agents, and commands on the current platform, reasons about the optimal combination, and executes with progressive disclosure. Works on Claude Code, Hermes, and OpenClaw. Trigger on: "popcorn", "assemble harness for", or "use your skills to".

English coach for a Korean user. Two modes — (1) critique mode for English input, suggests one tighter/natural rephrasing with rationale; (2) translation mode for non-English input (Korean, Japanese, etc.), renders it into natural register-matched English. Use when user types /english-check, /engco, /engco:engco, /engco:english-check, /english, asks "check my English", "fix my English", "translate to English", "영어로 바꿔줘", "이 문장 어색해?", "더 자연스럽게", or pastes any sentence and asks for English feedback or translation.

Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.

Save important information into long-lived searchable memory using the /remem command. Use when the user explicitly asks to remember, save to memory, keep this for later, or preserve important content/details with high fidelity. Triggers may include English and Korean phrases like "remember this", "take memory on", "don't forget", "까먹지마", "기억해놔", "메모리에 저장해", and requests to preserve a document, summary, note, or prior material in memory. Prefer preserving the original content in detail rather than aggressively summarizing.