Research

Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, when the user asks for 'objectively best' or 'highest quality', or when the domain has tools/frameworks where marketing or popularity biases could mislead research agents. Also use when starting architecture decisions, evaluating tech stacks, or when the user mentions bias, vendor lock-in, hallucinated benchmarks, or wants research-backed decisions rather than default recomme...

Processes governor-provided expert sources into structured, tier-labeled insights that feed the hypothesis register as evidence. Use when governor provides a book, article, video, or podcast for processing.

Adversarially attacks the current register state through pre-mortem, red-team response, constraint inversion, evidence concentration analysis, and kill signal audit. Use when a gap pass requires adversarial validation of hypotheses and proposals.

Use when decomposing a vague problem into a structured problem statement, identifying who has the problem and why it matters, sizing the opportunity, mapping constraints, prioritizing across multiple problems, or producing a Problem Definition Document that feeds into Discovery, Competitive Analysis, or Spec Writing. Encodes Problem Definition Canvas, 5 Whys Root Cause, JTBD Problem Framing, Opportunity Sizing, Problem-Solution Fit Assessment, Constraint Mapping, Stakeholder Impact Matrix, an...

Use when synthesizing user research, analyzing interview data, conducting discovery sprints, evaluating evidence quality across sources, or building research-backed feature hypotheses

Curated index of official EU and national (member state) compliance sources, including directives, transposition laws, and regulatory guidance. ACTIVATE when answering questions about EU regulations or national implementations (NIS2, GDPR, DORA, AI Act, Cyberbeveiligingswet, etc.) — especially differences between EU directives and local laws, applicability, enforcement, timelines, or legal obligations. Also activate for conceptual or comparative questions ("what changed", "how does NL differ ...

Construction document review with PE judgment — RFI research, submittal analysis, coordination checking, scope gap detection. Use when reviewing drawings, specs, submittals, or RFIs. Triggers: 'review', 'coordination', 'what's missing'.

Scope-specific code gap analysis — extracts referenced codes from project docs, researches what should apply, surfaces the delta. Triggers: 'code research', 'what codes apply', 'code check', 'ADA requirements', 'egress'.

Autonomous deep research agent that reads all files in the active directory, performs exhaustive multi-round literature research using web search and Brightdata scraping tools, iterates through self-critique loops, and produces a novel, publication-quality research paper as a formatted PDF. Trigger on: "research this", "do a literature review", "write a research paper from these files", "find what's missing in the literature", "autonomous research", "deep research", "novel research", "investi...

长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。 触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」

长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。 单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解， 确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 `拆文库/{书名}/`。 触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」 「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。

Mine insights from comments and historical data to recommend the next worthwhile topics. Trigger words: 'topics', 'topic', '選題', '寫什麼'.

Use when the user wants to anticipate reviewer questions, select the strongest ablations to present, prepare rebuttals, or identify paper weaknesses before submission. Triggers on phrases like "reviewer questions", "anticipate reviewers", "rebuttal", "paper weaknesses", "defend the paper", or "strengthen the paper".

Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".

End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a paper from scratch, or pastes an arxiv URL with reproduction intent.

Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".

Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".

Use when the user wants to find related work, survey a research area, identify literature gaps, or discover open-source implementations. Triggers on phrases like "find papers on", "related work", "literature review", "what papers exist", "open source implementation", or "papers with code".

Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup. Use when the user asks to launch, kick off, start, restart, or kill a training run, or mentions launching a multi-hour or multi-day GPU job (python train, accelerate launch, torchrun, deepspeed, sbatch, tmux training).

Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive setup".

Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation strategies. Triggers on phrases like "design ablation", "plan experiment", "what experiments should I run", "baseline comparison", or "experiment matrix".

Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.

Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like "dataset bias", "stratified sample", "class imbalance", "data distribution", "fairness analysis", or "ethical review".

Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step (never current-vs-final-of-baseline) and separates proxy metrics from downstream targets. Use when the user asks to compare runs, check if a run is improving, track lag against a baseline, rank experiments, or evaluate run-vs-run performance.