Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

Bring Claude Code–style sub-agents to any MCP-compatible tool.

LLM Reasoning Framework for Scientific Research

Detect hardcoded secrets, shell injections, remote-code execution, over-privileged filesystems, and unpinned supply-chain risks across , , , and before they run.

MCP server for Flux UI component references

MCP (Model Context Protocol) server that exposes Perplexity AI search, research, and reasoning capabilities as tools.

A Model Context Protocol (MCP) server that lets AI assistants use Go’s LSP (gopls) for navigation, diagnostics, testing, coverage, and more.

修复了mcp连接zemax3秒超时自动崩溃的问题,zemax冷启动超过3秒导致mcp无法正常连接已修复,并且添加了实现光学系统的设计、分析与优化。本次新增四个工具:ExportAnalysisTool 支持 17 种分析类型的 BMP 图像及 TXT 数据导出,含二维数据网格的分析(PSF、波前图等)自动渲染为热力图;GeometricImageAnalysisTool 提供 25+...

- search, transcribe, compare, and cite YouTube and public social video. - import once, then search transcripts, comments, frames, and OCR without fetching the same video again.

MCP server for Klever blockchain smart contract development

MCP server that enables AI assistants to interact with Salesforce orgs through the Salesforce CLI, providing tools for Apex execution, SOQL queries, metadata management, code analysis, and...

A secure, hardened MCP (Model Context Protocol) server for Inkscape operations, providing both CLI actions and DOM manipulation capabilities.

Documentation | Try with Claude | Try with Goose
Agent Skills

📄 bruce-doc-converter - Office/PDF 与 Markdown 双向转换,自动渲染 Mermaid 图表,让 AI 轻松读懂你的文档

dsh-agent-teams turns the current DeepSeek Harness session into a captain that can assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate work through direct messages.

Documentation • 中文文档 • Live Examples • Tutorials

所以做了这个可以蒸馏任意账号/作者写作风格的 agent skill,让写作不再痛苦,不再从 0 开始难产。

High-fidelity AI image prompt reverse-engineering skill for Codex

Agent skills for Railway, following the Agent Skills format.

Built by a physician-researcher, tested on real publications.

一行命令,让你的 AI 助手学会查文献、写综述、跑回归、管引文、写基金—— 科研龙虾 (Research-Claw) 的内置技能库,同时兼容 40+ 主流 Agent 框架。

- 简历精修(针对 AI / Agent 岗位优化) - 项目包装(这是最核心的,根据你过往的工作/实习和项目经历,定制化包装成agent项目,尽量多地融入agent主流技术,以及给你一份面试时口述的逐字稿) - 模拟面试(结合你的项目经历和大厂常问的问题进行深挖) - 全程陪跑(从投递到拿 offer)

다이소(제품/매장/재고), 상품 가격 비교, 주변 음식점/카페, 주유소/유가, 개발자 요청 제출, 롯데마트(매장/상품), GS25(매장/상품/재고), 세븐일레븐(상품/매장/재고/인기검색어/카탈로그), CU(매장/재고), 이마트24(매장/상품/재고), 올리브영(매장/재고), 메가박스(지점/영화/시간표/좌석), 롯데시네마(지점/영화/좌석),...

Bring your Entire context to your agents with cross-agent skills.

把一句「把这个流程做成 Skill」,变成一个真正能被发现、能稳定触发、能通过验证、还能一键开源的 Skill。