Business & Operations

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。

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 wiki

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

Claim-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 wiki

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

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

根据用户要求增删 raw sources 或更新 wiki 内容

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。

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

对 wiki 提问，综合检索相关页面后回答，好的回答可 crystallize 回 wiki

ElevenLabs multi-speaker dialogue generation - create conversations with different voices in a single audio file via inference.sh CLI. Capabilities: multi-voice dialogue, script-based generation, voice direction, conversation audio. Use for: podcasts, audiobooks, explainers, tutorials, character dialogue, video scripts. Triggers: elevenlabs dialogue, eleven labs dialogue, multi speaker, conversation audio, dialogue generation, text to dialogue, multi voice, voice acting, podcast dialogue, cha...

--- name: dependency-management description: Manage project dependencies including installation, updates, conflict resolution, and security audits ---

Interact with Linear project management - query issues, update status, create tickets, and manage workflows using the Linear GraphQL API. Use when working with Linear tickets, sprints, or project tracking.

Score code migration quality based on coverage and correctness. Evaluates how well target code represents source functionality.

Generate a comprehensive migration report summarizing quality scores and providing recommendations. Use after scoring a migration project.

Create a transformation guide for replacing mainframe-specific COBOL constructs with standard COBOL equivalents. Use when preparing COBOL code for local execution or migration.

This skill should be used when the user requests brand analysis, brand guidelines creation, brand audits, or establishing brand identity and consistency standards. It provides comprehensive frameworks for analyzing brand elements and creating actionable brand guidelines based on requirements.

---

Leverage Org-mode for productivity, task management, note-taking, and project management. Trigger on phrases like "org-mode workflow", "org-mode help", "org-mode setup", "org-mode configuration", "org-agenda", "org-capture".

Structure productive discussions and decision-making processes. Trigger on phrases like "meeting facilitation", "meeting structure", "discussion facilitation", "run a meeting", "meeting agenda".

Git and version control guidance from basic commands to complex workflows. Trigger on phrases like "git help", "version control", "git workflow", "git troubleshooting", "git tips".

Manage and organize Emacs Lisp projects with proper structure, dependencies, and testing. Trigger on phrases like "elisp project", "emacs package project", "elisp project management", "organize elisp code", "elisp project structure".

Human-centered design thinking guidance through empathy, ideation, prototyping, and testing. Trigger on phrases like "design thinking", "design thinking process", "human-centered design", "user research", "design sprint".

Analyze options, evaluate trade-offs, and make informed decisions. Trigger on phrases like "decision making", "decision support", "analyze options", "pros and cons", "help me decide".