Agent skill
/ideate
Multi-phase research idea generation pipeline: landscape scan → dual-model brainstorm → filter & validation → write to wiki → pilot
OpenClawData & Analytics
duany0490
Agent skills
Reusable instructions for compatible AI agents.
Explore by field
Loading catalog totals…Counts cover every published resource in this section. A resource can belong to several fields and platforms.
Resources
24 resourcesAgent skill
/novelty
Multi-source novelty verification — WebSearch + Semantic Scholar + wiki + Review LLM cross-verify — outputs novelty score and recommendations. Optionally writes the score back to an idea page with --write.
OpenClawData & Analytics
duany0490
Agent skill
/ingest
Ingest a paper into the wiki — creates pages (papers + concepts + methods + people) and builds all cross-references and graph edges. Trigger whenever the user says "ingest", "add this paper", drops a `.pdf` / `.tex` / arXiv URL, or asks to fold a paper into the knowledge base.
OpenClawData & Analytics
duany0490
Agent skill
/daily-arxiv
运行或管理每日 arXiv 推荐 feed。用于手动获取新论文推荐、配置/检查/停用 GitHub Actions 定时任务、邮件 digest，以及显式高置信 auto-ingest。
OpenClawData & Analytics
duany0490
Agent skill
/exp-design
基于idea的实验设计（含迭代消融） — 方法候选生成（直接实现/混合融合/跨idea结合） → 基准选择 → 迭代消融（非线性：消融可触发方法简化与重新规划）→ 敏感度分析 → 主实验 → 可选泛化实验 → 中间量深度分析。在预实验评估后为idea设计完整实验套件时使用。
OpenClawData & Analytics
duany0490
Agent skill
/paper-plan
从 idea graph 编译论文大纲：编译 evidence map → 叙事结构 → 章节计划 + figure plan + citation plan，Review LLM review 必选
OpenClawEducation & Research
duany0490
Agent skill
/exp-eval
实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 linked idea 的 status / failure_reason 与 graph edges
OpenClawData & Analytics
duany0490
Agent skill
/paper-compile
LaTeX compile → PDF — latexmk compile + auto-fix + page count/anonymity/font/[UNCONFIRMED] checks + submission checklist
OpenClawEducation & Research
duany0490
Agent skill
/init
Bootstrap ΩmegaWiki from user sources plus optional discovery, then ingest the final paper set in parallel
OpenClawEducation & Research
duany0490
Agent skill
/exp-run
实验执行全流程：准备代码 → 部署运行(运行前需向用户确认，申请用户手动检查) → 监控状态 → 收集结果，支持三种运行模式
OpenClawData & Analytics
duany0490
Agent skill
/discover
基于 anchor 论文、topic 关键词或当前 wiki 状态，产出一份排好序的候选论文 shortlist，供用户或上游 skill 决定是否进一步 `/ingest`。当用户问 "接下来该读什么"、"找和这篇相似的论文"、"推荐相关工作"、"这个方向周围有什么" 时触发；`/ingest --discover` 也会内部调用本 skill。本身不 ingest，只提出候选。
OpenClawData & Analytics
duany0490
Agent skill
/survey
从 wiki 知识生成论文 Related Work 章节：主题分组 → 叙事结构 → LaTeX 输出，遵循 citation-verification 和 academic-writing
OpenClawData & Analytics
duany0490
No matching resources
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.