Research & Analysis Workflows

Search, verify, and map citations for CS/AI/ML papers. Produces VERIFIED/UNVERIFIED reference lists with Citation-to-Claim maps and Exemplar Sets. Use when: finding references for a paper section, verifying citation accuracy, building exemplar sets for introduction/related work learning, checking if existing citations are real and accurate, supplementing local literature library. Triggers on: 找引用, 文献检索, citation pass, find references, reference check, 补文献, citation verification, Exemplar Set, search papers, verify citation, 核验文献, 查引用, literature search, reference verification.

Audit, run, or verify experimental evidence for CS/AI/ML papers. Produces Evidence Inventory with evidencetype annotations (newlyrun/preexistingartifact/userclaim) and Protocol Risk assessments. Use when: checking if experiment results are reproducible, auditing existing experiment artifacts, running minimal reproducible commands, evaluating checkpoints without full retraining, documenting protocol risks like data leakage or missing baselines. Triggers on: 复核实验, run experiments, 实验结果, experiment evidence, verify results, 实验验证, evidence inventory, protocol risk, 跑实验, check results, reproduce experiments, 实验审计.

Create, revise, or audit academic figures for CS/AI/ML papers. Two paths: architecture figure prompting (tool-agnostic structured prompts) and data figure code generation (publication-ready Python scripts with matplotlib/seaborn). Use when: generating model architecture diagram prompts, creating publication-quality data plots from experiment results, auditing existing figures for publication standards, suggesting figure types for paper sections, revising figure colors/layouts/labels. Triggers on: 绘图, figure, chart, 画图, 实验图, 训练曲线, 消融实验, 对比图, 混淆矩阵, 架构图, model architecture, plot, publication figure, 数据可视化, generate plot, architecture diagram.

Use when working on academic paper LaTeX layout, figure/table float placement, draft-to-template LaTeX generation, existing .tex project layout repair, figures piling up, figures far from text, large blank areas, two-column figure/table placement, page-limit layout cleanup, or compiled PDF layout review.

Core orchestrator for writing CS/AI/ML papers from scratch. Coordinates evidence audit, citation search, experiment verification, prose polishing, peer review, and figure generation across 6 sub-skills. Uses section-by-section drafting with Draft→Quality Gate→Expansion→Self-Review→Revision→Verification closed loop. Use when: writing a full paper draft from research notes or code repo, drafting paper sections one-by-one, coordinating multi-skill paper writing workflow, managing evidence-to-citation closed loop. Triggers on: 写论文, paper draft, 初稿, write introduction, draft method, 论文起草, full paper outline, section-by-section drafting, 证据闭环, 分节起草, academic paper writing, research paper drafting, write CS paper, draft AI paper, 从零写论文, 逐节写作.

Polish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers. Executes Prose Quality Gate, Claim Strength Audit, and de-AI pass. Use when: removing AI writing patterns from paper text, adjusting claim strength to match evidence level, rewriting method sections with proper narrative flow, improving academic writing quality, checking for overclaiming. Triggers on: 润色, polish, improve writing, 去AI, de-AI, claim strength, 改写, rewrite method, prose quality, 降级表述, remove AI patterns, academic writing polish, 学术润色, 去AI化, 降级结论.

Self-review, audit, or verify CS/AI/ML paper drafts as a critical peer reviewer. Three-round review (evidence→argument→style) with Verification Status and debt tracking. Use when: reviewing a paper draft before submission, checking evidence compliance of claims, simulating peer reviewer feedback, verifying citation closure and evidence debts, performing cross-section consistency checks. Triggers on: 审修, self review, 自查, verification, revise, 修订, check draft, 审稿, evidence compliance, peer review, 论文审查, draft audit, 验证论文, 检查引用, cross-section review.

Research target venue requirements and writing style for CS/AI/ML papers. Produces venue-brief.md with submission requirements and detailed writing style analysis. Use when: researching target journal/conference requirements, analyzing writing style of target venue, generating venue brief for paper writing, checking submission guidelines. Triggers on: venue research, 期刊调研, 目标期刊, writing style analysis, 写作风格分析, venue requirements, submission guidelines, 投稿要求, journal style, conference format.