Loading...
Loading...
Found 160 Skills
Use when verifying citations, bibliography, manuscript claims, source support, factual accuracy, numerical results, citation drift, or evidence provenance in academic work.
Use when responding to academic reviewers, planning revisions, writing rebuttals, mapping reviewer concerns, deciding concede/defend/reframe actions, or preparing camera-ready changes.
Use when building research dashboards, annotation tools, data browsers, paper-supporting demos, SOTA explorers, experiment viewers, or frontend interfaces for academic projects.
Paper Analyst — Responsible for in-depth paper reading, extracting method details, and building comparison tables. Activated when assigned to analyze papers by research supervisors or literature investigators. Conduct structured analysis on the Top 20 core papers, generate paper analysis cards and cross-paper comparison tables.
Determine the stage of a research task and route it to a main workflow. Use when the user asks for "beginner's guide", "start research process", "what should I use for this research task", "help me choose a research skill", or requests the rw-research-router workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Select available tools based on research tasks, data, and operating environment; works without a preset local research-lab. Use when the user asks for "which tool to use for research tasks", "help me choose research tools", "is this repo useful", or requests the rw-research-lab-router workflow. Runs without a private local workspace or preset research-lab; uses user-provided materials and bundled public-source methods.
Check the evidence, biases, alternative explanations, and reporting boundaries required for research conclusions before implementation or submission. Use when the user asks for “review my research design”, “act as a strict reviewer”, “challenge this conclusion”, or requests the rw-research-referee workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Organize scientific research text based on user-provided research materials and verifiable sources, determine the writing functions of chapters, sections, and paragraphs, and fill in the gaps between evidence, explanations, significance, and research questions. Use when the user asks for “write PhD chapters”, “revise paper arguments”, “write academic paragraphs based on sources”, “revise scientific writing according to supervisor feedback”, or requests the rw-phd-write workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.
Prepare and publish a research code repository for public release alongside a paper (arXiv, conference, GitHub). Use when the user wants to open-source code, create a GitHub release, package a code submission, make code public, or prepare a reproducibility release.
Diagnose surprising, negative, unstable, or ambiguous ML/AI experiment results and decide whether to debug implementation, rerun experiments, change metrics or baselines, revise the algorithm, narrow the paper claim, park, or kill a direction. Use this skill whenever results do not match expectations, a method fails, metrics conflict, seeds vary, baselines beat the method, plots look suspicious, or the user asks what to do next after experimental results.
Read research outline, launch independent agent for each item for deep research. Disable task output.