All authors
Claude Skills by Lambenthan
github.com/Lambenthan70 skills2 installs92 views
- Ask对 wiki 提问，综合检索相关页面后回答，好的回答可 crystallize 回 wikiVotes: 0GitHub stars: 82
- Check扫描全 wiki 发现健康问题，生成修复建议报告（覆盖全 9 种 entity + graph 一致性）Votes: 0GitHub stars: 82
- Daily Arxiv每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新Votes: 0GitHub stars: 82
- 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。Votes: 0GitHub stars: 82
- Edit根据用户要求增删 raw sources 或更新 wiki 内容Votes: 0GitHub stars: 82
- Empirical Design基于已摄取文献和本地数据，生成经管实证研究设计：问题、机制、变量、模型、识别、机制、异质性、稳健性Votes: 0GitHub stars: 82
- Empirical Ingest将一篇经管实证论文摄取为实证研究 wiki：论文卡片 + 变量 + 数据 + 模型 + 机制 + 识别 + 稳健性 + 异质性 + 表格线索Votes: 0GitHub stars: 82
- Exp DesignClaim-driven 实验设计：界定目标 claims → 设计实验块（baseline/validation/ablation/robustness）→ 构建执行顺序 → 可选 Review LLM review → 写入 wikiVotes: 0GitHub stars: 82
- 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 claims confidence、ideas status、graph edgesVotes: 0GitHub stars: 82
- Exp Run实验执行全流程：准备代码 → 部署运行 → 监控状态 → 收集结果，支持三种运行模式Votes: 0GitHub stars: 82
- Exp Status查看所有运行中实验的状态，可选自动收集已完成实验并推进流水线Votes: 0GitHub stars: 82
- Ideate多阶段研究 idea 生成管道：景观扫描 → 双模型脑暴 → 初筛 → 深度验证 → 写入 wikiVotes: 0GitHub stars: 82
- Ingest把一篇论文 ingest 进 wiki —— 建立 papers + concepts + people + claims 页面，并完成所有双向交叉引用与 graph edge。当用户说 "ingest"、"加入这篇论文"、丢 `.pdf` / `.tex` / arXiv URL 或要求把论文折叠进知识库时触发。Votes: 0GitHub stars: 82
- Init基于用户素材与可选外部发现搭建 ΩmegaWiki，并用并行 `/ingest` 完成最终论文集的消化Votes: 0GitHub stars: 82
- Novelty多源 novelty 验证：WebSearch + Semantic Scholar + wiki + Review LLM cross-verify，输出 novelty 评分与建议Votes: 0GitHub stars: 82
- Paper CompileLaTeX 编译 → PDF：latexmk 编译 + 自动修复 + 页数/匿名/字体/[UNCONFIRMED] 检查 + 提交清单Votes: 0GitHub stars: 82
- Paper Draft从 PAPER_PLAN 起草 LaTeX 论文：逐 section 从 wiki 取材撰写 + 生成 figures/tables + BibTeX 验证 + de-AI polishVotes: 0GitHub stars: 82
- Paper Plan从 claim 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Votes: 0GitHub stars: 82
- Prefill用领域基础知识填充 wiki/foundations/，避免后续 /ingest 为教科书材料创建重复的 concept 页面Votes: 0GitHub stars: 82
- Rebuttal解析审稿意见 → 原子化 concerns (Rvx-Cy) → 映射到 wiki claims → 检查 evidence → Review LLM stress-test → 生成 rebuttalVotes: 0GitHub stars: 82
- Refine通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标Votes: 0GitHub stars: 82
- Research端到端研究编排器：idea 发现 → 实验设计 → 执行 → 判决 → 论文撰写，带人工门控和状态恢复Votes: 0GitHub stars: 82
- Reset按 scope 重置 wiki 到干净 scaffold（wiki / raw / log / checkpoints / all）。适用于开发迭代或 setup 失败后的无痛重启。Votes: 0GitHub stars: 82
- Review通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议Votes: 0GitHub stars: 82
- Setup交互式 API key 配置引导 — 检测当前 .env 状态，逐步引导配置 Semantic Scholar、DeepXiv 和 Review LLMVotes: 0GitHub stars: 82
- Stata Plan将实证研究设计转成 Stata 执行计划或 do 文件骨架，包含数据合并、变量构造、描述统计、回归和稳健性Votes: 0GitHub stars: 82
- 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-writingVotes: 0GitHub stars: 82
- Theory Ingest将一篇理论建模论文摄取为理论研究 wiki：论文卡片 + 假设/原语 + 命题/定理 + 解概念 + 可检验推论，并与实证层在同一张 graph 上接桥Votes: 0GitHub stars: 82
- Variable Map汇总某个经管实证变量在文献中的测算口径、数据来源、模型角色和项目可用性Votes: 0GitHub stars: 82
- AskAsk the wiki a question, retrieve and synthesize relevant pages, optionally crystallize the answer back into the wikiVotes: 0GitHub stars: 82
- CheckScan the full wiki to detect health issues and produce a tiered fix-recommendation report (covers all 9 entity types + graph consistency)Votes: 0GitHub stars: 82
- Daily ArxivDaily arXiv pull, relevance filtering, auto-ingest of high-priority papers, and SOTA update detectionVotes: 0GitHub stars: 82
- DiscoverBuild a ranked shortlist of candidate papers (anchor-driven, topic-driven, or derived from current wiki state) that the user — or an upstream skill — may decide to feed into `/ingest`. Use whenever the user asks "what should I read next", "find papers similar to this one", "recommend related work", "what's around this topic", or whenever `/ingest` is invoked with `--discover`. Does not ingest; only proposes.Votes: 0GitHub stars: 82
- EditAdd or remove raw sources, or update wiki content, per user requestVotes: 0GitHub stars: 82
- Empirical DesignGenerate an empirical research design from ingested literature and local project data: question, theory, variables, data, model, identification, mechanisms, heterogeneity, and robustnessVotes: 0GitHub stars: 82
- Empirical IngestIngest an empirical social-science paper into the wiki: paper card plus variables, datasets, models, mechanisms, identification, robustness, heterogeneity, and tablesVotes: 0GitHub stars: 82
- Exp DesignClaim-driven experiment design — scope target claims → design experiment blocks (baseline/validation/ablation/robustness) → build run order → optional Review LLM review → write to wikiVotes: 0GitHub stars: 82
- Exp EvalExperiment verdict gate — Review LLM independently judges results → 4 verdict paths → auto-update claims confidence, ideas status, graph edgesVotes: 0GitHub stars: 82
- Exp RunFull experiment execution pipeline — prepare code → deploy → monitor → collect results, supporting three run modesVotes: 0GitHub stars: 82
- Exp StatusView the status of all running experiments; optionally auto-collect completed experiments and advance the pipelineVotes: 0GitHub stars: 82
- IdeateMulti-phase research idea generation pipeline: landscape scan → dual-model brainstorm → first-pass filter → deep validation → write to wikiVotes: 0GitHub stars: 82
- IngestIngest a paper into the wiki — creates pages (papers + concepts + people + claims) 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.Votes: 0GitHub stars: 82
- InitBootstrap ΩmegaWiki from user sources plus optional discovery, then ingest the final paper set in parallelVotes: 0GitHub stars: 82
- NoveltyMulti-source novelty verification — WebSearch + Semantic Scholar + wiki + Review LLM cross-verify — outputs novelty score and recommendationsVotes: 0GitHub stars: 82
- Paper CompileLaTeX compile → PDF — latexmk compile + auto-fix + page count/anonymity/font/[UNCONFIRMED] checks + submission checklistVotes: 0GitHub stars: 82
- Paper DraftDraft a LaTeX paper from PAPER_PLAN — write each section from wiki sources + generate figures/tables + BibTeX verification + de-AI polishVotes: 0GitHub stars: 82
- Paper PlanCompile a paper outline from the claim graph — evidence map → narrative structure → section plan + figure plan + citation plan, Review LLM review mandatoryVotes: 0GitHub stars: 82
- PrefillSeed wiki/foundations/ with domain background knowledge so subsequent /ingest does not create duplicate concept pages for textbook materialVotes: 0GitHub stars: 82
- RebuttalParse review comments → atomize concerns (Rvx-Cy) → map to wiki claims → check evidence → Review LLM stress-test → generate rebuttalVotes: 0GitHub stars: 82
- RefineGeneral-purpose multi-round iterative improvement — repeatedly calls /review on any research artifact, parses feedback, applies fixes, updates wiki, until the target score is reachedVotes: 0GitHub stars: 82