Loading...
Loading...
Found 183 Skills
Read research outline, launch independent agent for each item for deep research. Disable task output.
Use when selecting, installing, configuring, smoke-testing, documenting, or troubleshooting MCP servers for academic search, arXiv, Semantic Scholar, OpenAlex, Crossref, PubMed, Zotero, Overleaf, Google Scholar, paper metadata, or scholarly source tooling.
Use when an academic research repository task could involve research design, sources, conversion, bibliography, SOTA, reviews, ethics, experiments, papers, reproduction, MCP tools, or project maintenance and the correct workflow is not obvious.
Use when choosing, comparing, or preparing for computer science venues, conferences, workshops, journals, tracks, deadlines, reviewer expectations, paper fit, or publication positioning.
Use when creating, repairing, refactoring, validating, or documenting an academic research repository structure, including wiki, sources, SOTA, outputs, agent docs, tests, and reproducibility folders.
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.
Organize research, constructs, design, samples, results, biases, conflicts, and gaps into a traceable evidence map. Use when the user asks for "create an evidence map", "organize research conflicts", "connect literature", or requests the rw-evidence-map 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.
Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis accordingly. Activated for "deep search", "multi-source search", or when high-quality research is needed.
Initialize Python Project (New or Fork). Use when the user wants to create a new production-ready Python/ML project structure, or fork and enhance an existing project. Uses uv for environment management.
Control a remote SSH server project from a local git repo with persistent project memory. Use when the user develops locally but runs remotely, wants the agent to understand remote repo mappings across sessions, needs safe local/remote git sync via GitHub, wants to inspect remote state, submit jobs, start interactive sessions, monitor logs, or recover project context at the start of a new coding session.
Maintain a paper-facing evidence board that aligns claims, experiments, figures, tables, sections, reviewer risks, and next actions during ML/AI paper writing. Use this skill whenever writing exposes missing experiments, new results require paper changes, reviewer simulation reveals evidence gaps, claims need support checks, figures/tables need mapping to claims, or the user wants a live paper evidence board before submission.