Dave AI

AI prompts.
Agent skills.

Reusable instructions for the work you do.
Find them by field and AI platform.

55,059 published resources

Explore by field

Loading full catalog…
Browse full catalog

Whole-catalog totals. A resource can belong to multiple fields and platforms.

Resources

21 resources
Data & Analytics

/ideate

Agent skillOpenClaw

Multi-phase research idea generation pipeline: landscape scan → dual-model brainstorm → filter & validation → write to wiki → pilot

Data & Analytics

/novelty

Agent skillOpenClaw

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.

Data & Analytics

/ingest

Agent skillOpenClaw

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.

Data & Analytics

/daily-arxiv

Agent skillOpenClaw

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。

Data & Analytics

/exp-design

Agent skillOpenClaw

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。

Education & Research

/paper-plan

Agent skillOpenClaw

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

Data & Analytics

/exp-eval

Agent skillOpenClaw

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

Education & Research

/paper-compile

Agent skillOpenClaw

LaTeX compile → PDF — latexmk compile + auto-fix + page count/anonymity/font/[UNCONFIRMED] checks + submission checklist

Education & Research

/init

Agent skillOpenClaw

Bootstrap ΩmegaWiki from user sources plus optional discovery, then ingest the final paper set in parallel

Data & Analytics

/exp-run

Agent skillOpenClaw

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

Data & Analytics

/discover

Agent skillOpenClaw

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。

Data & Analytics

/survey

Agent skillOpenClaw

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

Platform labels describe intended use. Check each resource's original source, license and installation instructions.

Add to the collection.

Share a useful prompt or agent skill.
Include the creator, original source and license.

Submit a resource

Using Dave AI

Prompts: open a resource, customize its optional fields and copy the instructions into your preferred AI conversation.

Skills: open a resource and choose a listed compatible agent. Its page offers an install command and a complete ZIP package with source and license notices.

Claude, Codex, OpenClaw, Cursor, ChatGPT and Gemini labels indicate intended use. Dave AI does not run a model on your behalf.

Read the full guideDirectory