Loading...
Loading...
Found 163 Skills
Compile LaTeX papers to PDF with automatic error detection, chktex style checking, and citation/reference validation. Runs the full pdflatex + bibtex pipeline. Use when the user wants to compile a paper, fix compilation errors, or debug LaTeX.
Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.
Write Related Work sections that compare and contrast prior work with your approach. Organize by theme, cite broadly, and explain how your work differs. Use when writing or improving the Related Work section of a paper.
Systematic retrieval expert covering all areas of Chinese law. ## Core Features - Supports user identity recognition (ordinary person/law student/lawyer/judge/prosecutor) - Provides differentiated services based on different identities - Complete legal source retrieval (laws/administrative regulations/judicial interpretations/guiding cases/typical cases) - Original legal article citation and cross-reference sorting ## Core Trigger Conditions (Trigger if any is met) **High Priority (Must Trigger)**: - Explicit request to find legal articles/regulations/judicial interpretations/regulatory documents - Request to determine legality/illegality ("Is it illegal?""Is it legal?""Am I liable?") - Request to find compensation standards/compensation amounts/liability determination/procedural requirements - Asking "Based on which law?""What does the law stipulate?""What is the legal basis?" **Medium Priority (Trigger based on context)**: - "What to do?""How to defend rights?""Can I sue?" - "What procedures are needed?""What conditions are required?" - "What else can I claim?""Where can I file a complaint?" ## Application Scenarios - Labor disputes: illegal termination, economic compensation, work-related injuries, social security, job transfer, etc. - Contract disputes: deposit, liquidated damages, breach of contract liability, sales contracts, etc. - Tort liability: traffic accidents, personal injury, medical accidents, environmental pollution, etc. - Marriage and family: divorce property, child custody, estate inheritance, etc. - Administrative/criminal/corporate finance, etc. ## Non-Triggering Scenarios - Only asking about legal concepts/terminology explanations (not retrieval-related) - Only requesting lawyer/legal service recommendations - Only discussing legal news/case stories (not involving specific regulations) - Only asking about legal examination/study questions **Note**: Even if the user does not explicitly request a "retrieval report", this skill will be triggered as long as the issue involves searching, organizing, interpreting, or applying legal norms.
Discover scientific equations from data using LLM-guided evolutionary search (LLM-SR). Multi-island algorithm with softmax-based cluster sampling, island reset, and LLM-proposed equation mutations. Use for symbolic regression and equation discovery.
Formal mathematical reasoning for research papers — derive equations, write proofs, formalize problem settings, select statistical tests, and generate LaTeX math notation. Use when the user needs mathematical derivations, theorem proofs, notation tables, or statistical analysis formalization.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
Use this skill for "write a literature review", "synthesize papers", "review the literature", "summarize research findings", "identify research trends", "gap analysis", "thematic review", "systematic review", "scoping review", "narrative review", "compare studies", "research synthesis", or when the user wants to synthesize multiple papers into a cohesive literature review.
Write structured experiment report documents from ML/research experiment notes, configs, logs, metrics, tables, and figures. Use this skill whenever the user asks to write an experiment report, research update, mentor update, weekly experiment summary, result analysis document, or presentation-ready experiment writeup, especially when the output should explain motivation, setup, algorithms, metrics, results, figures, interpretation, conclusions, limitations, and next steps.
Audit whether an academic paper cites the necessary classic, closest, and recent concurrent work before submission. Use this skill whenever the user worries that references are incomplete, wants missing citations found, needs related work coverage checked, asks whether a paper cites classic work or recent arXiv/OpenReview work, or wants a citation coverage report for ML/AI venues such as NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, or similar conferences.
Perform common Git operations safely with sandbox-aware failure handling. Use whenever the user wants to inspect or modify git state, especially for cherry-pick, merge, rebase, commit, branch, stash, or worktree workflows. Always use this skill when the user mentions a Git failure, conflict, cherry-pick, merge issue, worktree, branch checkout problem, lock file, permission denied, operation not permitted, or any case where a sandboxed agent might confuse an environment restriction with a real code conflict. Be proactive: if the task smells like Git state or Git write behavior, use this skill even if the user did not explicitly ask for a 'Git' workflow.
Plan and write strategic rebuttals after real paper reviews arrive. Use this skill whenever the user has OpenReview reviews, reviewer comments, scores, confidence ratings, meta-reviews, author response windows, or wants to decide which experiments to run, infer reviewer intent, draft point-by-point responses, prepare follow-up discussion replies, or improve wording after reviews for ML/AI venues such as NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, or similar conferences.