研究与知识

研究、检索、摘要和知识工作

1098 个 Skills 可用

Skills 列表

seo-competitor-pages

seo-competitor-pages

12Kresearch-knowledge

生成针对 SEO 优化的竞品对比与替代方案页面。涵盖“X vs Y”对比布局、“X 的替代方案”页面、功能对比矩阵、Schema 结构化数据标记以及转化率优化(CRO)。当用户提到“对比页”、“竞品对比”、“对标页面”、“替代方案”、“X vs Y”、“versus”、“竞品分析”或“...的替代品”时使用。

agricidaniel avataragricidaniel
获取
react-expert

react-expert

12Kresearch-knowledge

Use when researching React APIs or concepts for documentation. Use when you need authoritative usage examples, caveats, warnings, or errors for a React feature.

reactjs avatarreactjs
获取
ml-paper-writing

ml-paper-writing

12Kresearch-knowledge

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.

orchestra-research avatarorchestra-research
获取
seo-coach

seo-coach

11Kresearch-knowledge

Enter a friendly OpenSEO coach mode that explains workflows, recommends next steps, and helps users use agents, web search, scraping, and MCP data effectively.

every-app avatarevery-app
获取
keyword-clustering

keyword-clustering

11Kresearch-knowledge

Cluster keywords by intent and map them to existing or proposed pages.

every-app avatarevery-app
获取
seo-project-setup

seo-project-setup

11Kresearch-knowledge

Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.

every-app avatarevery-app
获取
huggingface-paper-publisher

huggingface-paper-publisher

11Kresearch-knowledge

在 Hugging Face Hub 上发布和管理研究论文。支持创建论文页面、将论文链接到模型/数据集、声明作者身份,以及生成专业的基于 Markdown 的研究文章。

huggingface avatarhuggingface
获取
transformers-js

transformers-js

11Kresearch-knowledge

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

huggingface avatarhuggingface
获取
huggingface-papers

huggingface-papers

11Kresearch-knowledge

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.

huggingface avatarhuggingface
获取
geo-llmstxt

geo-llmstxt

11Kresearch-knowledge

Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content. Can validate existing llms.txt files or generate new ones from scratch by crawling the site.

zubair-trabzada avatarzubair-trabzada
获取
rag-architect

rag-architect

11Kresearch-knowledge

设计并实现生产级RAG系统,包括文档分块、生成嵌入向量、配置向量存储、构建混合搜索管道、应用重排序以及评估检索质量。在构建RAG系统、向量数据库或需要语义搜索、文档检索、上下文增强、相似性搜索或基于嵌入索引的知识驱动AI应用时使用。

jeffallan avatarjeffallan
获取
code-documenter

code-documenter

11Kresearch-knowledge

生成、格式化和验证技术文档——包括文档字符串、OpenAPI/Swagger 规范、JSDoc 注释、文档门户和用户指南。在需要为函数或类添加文档字符串、创建 API 文档、构建文档站点或编写教程和用户指南时使用。适用于 OpenAPI/Swagger 规范、JSDoc、文档门户、入门指南。

jeffallan avatarjeffallan
获取
kotlin-specialist

kotlin-specialist

11Kresearch-knowledge

提供惯用的 Kotlin 实现模式,包括协程并发、Flow 流处理、多平台架构、Compose UI 构建、Ktor 服务器设置和类型安全的 DSL 设计。在构建需要协程、多平台开发或 Android 与 Compose 的 Kotlin 应用程序时使用。适用于 Flow API、KMP 项目、Ktor 服务器、DSL 设计、密封类、挂起函数、Android Kotlin、Kotlin 多平台。

jeffallan avatarjeffallan
获取
code-reviewer

code-reviewer

11Kresearch-knowledge

分析代码差异和文件,识别错误、安全漏洞(SQL注入、XSS、不安全的反序列化)、代码坏味、N+1查询、命名问题和架构问题,然后生成结构化的审查报告,提供按优先级排序的可操作反馈。适用于审查拉取请求、进行代码质量审计、识别重构机会或检查安全问题。调用场景包括PR审查、代码质量检查、重构建议、审查代码、代码质量。通过一次遍历提供涵盖正确性、性能、可维护性和测试覆盖率的广泛审查,补充专业技能(如安全审查员、测试大师)。

jeffallan avatarjeffallan
获取
embedded-systems

embedded-systems

11Kresearch-knowledge

在开发微控制器固件、实现RTOS应用或优化功耗时使用。适用于STM32、ESP32、FreeRTOS、裸机、功耗优化、实时系统、配置外设、编写中断处理程序、实现DMA传输、调试时序问题。

jeffallan avatarjeffallan
获取
processize

processize

9.9Kresearch-knowledge

Turn a product idea into a manual-first process you can start delivering today. Use when you have an idea and want to figure out how to deliver value by hand before writing any code.

slavingia avatarslavingia
获取
kb-retriever

kb-retriever

9.9Kresearch-knowledge

面向本地知识库目录的检索和问答助手。核心流程:(1)分层索引导航 (2)遇到PDF/Excel时必须先读取references学习处理方法 (3)处理文件后再检索。按文件类型组合使用 grep、Read、pdfplumber、pandas 进行渐进式检索,避免整文件加载。用户问题涉及"从知识库目录回答问题/检索信息/查资料"时使用。

conardli avatarconardli
获取
zhangxuefeng-perspective

zhangxuefeng-perspective

9.9Kresearch-knowledge

张雪峰的思维框架与表达方式。基于5本著作、15+篇权威媒体深度采访、 30+条一手语录、11个关键决策记录和完整人生时间线的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为思维顾问,用张雪峰的视角分析教育选择、职业规划、阶层流动等问题。 当用户提到「用张雪峰的视角」「张雪峰会怎么看」「张雪峰模式」「雪峰视角」时使用。 即使用户只是说「帮我用张雪峰的角度想想」「如果张雪峰会怎么说」「切换到张雪峰」也应触发。

alchaincyf avataralchaincyf
获取
academic-research-suite

academic-research-suite

9.7Kresearch-knowledge

ARS-Codex workflows for research, academic writing, manuscript review, research-to-paper pipelines, and experiment planning. Use when the user asks for deep research, literature review, systematic review, meta-analysis, research question refinement, academic paper drafting, paper revision, citation or integrity checks, reviewer simulation, peer review, editorial decision letters, research-to-paper workflows, experiment execution planning, statistical interpretation, or human study protocol support. Korean triggers: 논문 심사, 논문 수정, 초록 작성, 체계적 문헌고찰, 연구부터 논문까지. Also use for Claude-style ARS command aliases such as /ars-plan, ars-plan, /ars-outline, /ars-abstract, /ars-lit-review, /ars-citation-check, /ars-disclosure, /ars-format-convert, /ars-3w, /ars-revision-coach, /ars-revision, /ars-reviewer, /ars-mark-read, /ars-unmark-read, /ars-cache-invalidate, /ars-rebuttal-audit, and /ars-full. This skill vendors ARS role prompts, references, templates, and shared handoff schemas under ars/.

imbad0202 avatarimbad0202
获取
sdf

sdf

8.3Kresearch-knowledge

SDFormat/SDF模型与世界生成、验证及模拟器交接。用于`.sdf`文件、SDFormat XML、Python `gen_sdf()`源码、模型、世界、链接、关节、位姿、框架、惯性、视觉/碰撞几何体、网格URI、传感器、灯光、物理、插件、包含、Gazebo、静态SDF审查或模拟器特定元数据。不用于符号距离场几何体。

earthtojake avatarearthtojake
获取
fireworks-tech-graph

fireworks-tech-graph

8.3Kresearch-knowledge

当用户想要绘制各类技术图表(如架构图、数据流图、流程图、时序图、Agent/内存架构图、概念图等)并导出为 SVG+PNG 格式时使用。触发词包括:"画图"、"帮我画"、"生成图"、"做个图"、"架构图"、"流程图"、"可视化一下"、"出图"、"generate diagram"、"draw diagram"、"visualize",或任何用户希望用图表展示的系统架构与流程描述。

yizhiyanhua-ai avataryizhiyanhua-ai
获取
dbs-decision

dbs-decision

8.2Kresearch-knowledge

dontbesilent 个人决策系统。把任何一个需要长期跟踪的领域(业务、关系、健康、职业、学习、投资……)做成一个本地知识工程:四层结构、来源标签、写完不改的快照、能炼出规律的概念库。 触发方式:/dbs-decision、/决策系统、/决策立案、/结果回填、/状态画像 Personal decision system. Turns any long-running domain into a local knowledge project with four layers, source tags, immutable snapshots, and a concept library that learns patterns over time. Trigger: /dbs-decision, /决策系统, /决策立案, /结果回填, /状态画像

dontbesilent2025 avatardontbesilent2025
获取
writing-plans

writing-plans

8.1Kresearch-knowledge

当你有规格说明或需求用于多步骤任务时使用,在动手写代码之前

jnmetacode avatarjnmetacode
获取
no-mistakes

no-mistakes

7.9Kresearch-knowledge

Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach the configured push target. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.

kunchenguid avatarkunchenguid
获取