Fzkuji

Autonomous research agent: literature, ideas, experiments, writing, review, rebuttal, presentation, theory. Triggers: 'research', 'write paper', 'survey', 'polish', 'translate', 'review', 'rebuttal', 'slides', 'poster', '写论文', '文献调研', '润色', '翻译', '去AI味', '审稿'.

Run GPTZero AI detection on one or more review files via the app.gptzero.me dashboard. Requires Chrome running with --remote-debugging-port=9222 and the user logged into GPTZero. Use when user says "check ai rate", "gptzero", "检测AI率", "run gptzero", or wants to verify that review prose passes AI detection.

Write a venue-form peer review of someone else's paper. Humanization is automatic. Thin shim over the `research-review` CLI. The CLI runs three steps internally for every paper: (1) codex writes a long detailed free-form draft, no template constraint; (2) extract_judgment compresses the draft into a structured judgment dict (numerics + per-field bullets); (3) prose is regenerated under real-human sentence templates, with numerics preserved from step 1. No draft input, no draft option. Every paper goes through the same three-step pipeline. For self-critique with no AI-detection concern, use /self-review.

Critically review your own paper to find real weaknesses before submission. Output is meant to be read by you (the author) and fed into a revision loop, not submitted to a venue. So: no AI-rate constraint, no corpus-template humanization, no GPTZero verification. The skill optimizes for harsh, specific, paper-grounded critique instead of polite peer-review-ese. Sibling skill: - peer-review: write a venue-form review with prose humanized via corpus templates. Use when you are reviewing someone else's paper and need GPTZero <=cap. Also handles "humanize an existing review draft" via the --draft option.

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

Write, edit, validate, save, and run Agentic Programming functions (@agentic_function) directly with your own file-editing tools. Covers next-step decision making — letting the LLM pick the next function/value via decision.make or runtime.exec(choices=). No dedicated meta functions — just follow the rules in this skill. Triggers: 'write an agentic_function', 'create a function', 'edit a function', 'improve a function', 'fix this function', 'add a function that', 'add a tool that', 'run a function', 'let the model decide', 'make the model pick', 'decision.make', 'next-step decision'.

Write, edit, validate, save, and run Agentic Programming functions (@agentic_function) directly with your own file-editing tools. Covers next-step decision making — letting the LLM pick the next function/value via decision.make or runtime.exec(choices=). No dedicated meta functions — just follow the rules in this skill. Triggers: 'write an agentic_function', 'create a function', 'edit a function', 'improve a function', 'fix this function', 'add a function that', 'add a tool that', 'run a function', 'let the model decide', 'make the model pick', 'decision.make', 'next-step decision'.

GUI automation via visual perception. Screenshot → detect → click → verify. Use when asked to operate a desktop app, interact with a VM, or complete an OSWorld benchmark task.

Maintain a wiki vault — ingest source material into structured pages, enrich existing pages with visual components, browse / search / lint the vault. Top-level dispatcher; routes via decision.make to wiki_ingest, wiki_enrich, browse, lint, or search. Triggers: 'add to wiki', 'save these notes', 'ingest into wiki', 'enrich the page', 'visualize the docs', 'browse the vault', 'search the wiki', 'check broken links', 'wiki health'.