Deep-review-first audit for Chinese and English academic papers across LaTeX, Typst, and PDF formats. Use whenever the user wants reviewer-style paper critique, pre-submission readiness checks, pass/fail gate decisions, structured revision roadmaps,…
Scaffold a PyTorch Lightning project for classification, regression, or timeseries research. Triggers on "新建项目", "initialize project", "scaffold", "create PL project". Not for LLM/PEFT/RAG/agent stacks.
Design ablation studies from a reviewer's perspective. Preferred use is upfront (after method is confirmed, before experiments run) to avoid post-hoc rationalization. Can also be used after result-to-claim to add supplementary ablations. Agent sub-agent leads…
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology…
Background experiment monitor — generates native bash script, launches via Bash(run_in_background=True). Adaptive polling, keyword detection, stale/error/done states, zero main-thread context. Triggers on "monitor", "watch experiment", "后台监控", or after any…
Autonomous multi-round research review loop. Repeatedly reviews via Agent self-review, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous…
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an…
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or…