Automatic and end-to-end scientific research workflow enabled by OpenClaw. Produces state-of-the-art level research results.
Skill Claude CodeCodex
Use this when the user needs to choose between multiple ML routes after survey but before committing to implementation. Compares candidate approaches, selects one, records rejected routes, and keeps a fallback.
Skill Claude CodeCodex
Use this when the user wants a draft paper, figure bundle, README, release page, or experiment artifact reviewed before sharing. Checks evidence binding, claim scope, captions, layout clarity, and release readiness.
Skill Claude CodeCodex
Use this when the project needs real baseline results before or alongside the main model. Runs classical or literature-aligned baselines under the same protocol and writes a reproducible baseline summary.
Skill Claude CodeCodex
Use this when the project needs a dedicated data-quality review before model review. Checks data reality, split correctness, label health, leakage risk, shape consistency, and mock-data disclosure.
Skill Claude CodeCodex
Use this when the user wants to improve chart quality, standardize plotting style, regenerate release figures, or add captions/protocol notes. Normalizes fonts, colors, legends, units, and scope notes across Scientify figures.
Skill Claude CodeCodex
Use this when the user wants research ideas, innovation points, or to find research gaps (找研究方向, 生成创新点). Generates 5 ideas from collected papers, identifies gaps, proposes novel methods with citations. Requires papers in workspace.
Skill Claude CodeCodex
Knowledge metabolism: Day 0 init (discuss + baseline survey) or daily cycle (incremental search + update knowledge + generate hypotheses). Triggered by bootstrap and daily cron.
Skill Claude CodeCodex
Download academic papers: arXiv source/PDF by ID, DOI papers via Unpaywall open access. Supports batch download.
Skill Claude CodeCodex
Use this when the user wants to improve README, docs pages, or microsites so a new reader can understand what the project is, how to use it, what artifacts exist, and what the scope boundaries are within one screen.
Skill Claude CodeCodex
Skill "research-collect" from tsingyuai/scientify, covering literature survey, output structure, workflow, phase 1: 准备 and phase 2: 增量搜索-筛选-下载（循环）.
Skill Claude CodeCodex
Skill "research-experiment" from tsingyuai/scientify, covering research experiment, prerequisites, output, workflow and step 1: full training.
Skill Claude CodeCodex
Skill "research-implement" from tsingyuai/scientify, covering research implement, prerequisites, output, workflow and step 1: 读取计划.
Skill Claude CodeCodex
Use this skill when the user wants to research a topic, analyze papers, build ML models, or run experiments. Orchestrates the full pipeline: paper search → analysis → planning → implementation → review → experiments.
Skill Claude CodeCodex
Skill "research-plan" from tsingyuai/scientify, covering research plan, prerequisites, output, workflow and step 1: 读取上下文.
Skill Claude CodeCodex
Skill "research-review" from tsingyuai/scientify, covering research review, prerequisites, output, workflow and step 1: 审查代码.
Skill Claude CodeCodex
Skill "research-survey" from tsingyuai/scientify, covering research survey (deep analysis), prerequisites, output, workflow and step 1: 收集论文列表.
Skill Claude CodeCodex
Use this when the user wants a systems paper, experiment paper, technical report, or extended abstract drafted from existing Scientify artifacts. Builds a claim-bounded paper draft from experiment outputs, figures, and supporting notes.
Skill Claude CodeCodex
Use this when the user wants to write a literature review, survey paper, or thesis chapter from existing papers. Guides reading strategy, note-taking, synthesis, and academic writing. NOT for searching new papers (/research-collect) or generating ideas (/idea-generation).