本地 FAISS 向量库 MCP
v0.2.0-rc.3
io.github.nonatofabio/local-faiss-mcp
面向 RAG 的本地 FAISS 向量数据库,支持文档摄取、语义搜索与 MCP 提示。
“Document Processing” 共 842 个结果
v0.2.0-rc.3
io.github.nonatofabio/local-faiss-mcp
面向 RAG 的本地 FAISS 向量数据库,支持文档摄取、语义搜索与 MCP 提示。
v3.0.0
io.github.MusaddiqueHussainLabs/mhlabs_mcp_tools
提供文本预处理、NLP 组件与文档分析能力的 MCP 服务器。
v0.4.4
io.github.NeerajG03/vector-memory
基于 Redis 向量存储的语义文档记忆,用自然语言保存与召回文件。
v0.1.2
io.github.copyleftdev/fabric-atelier
AI 驱动的内容处理,内置 226 个 Fabric 模式,用于写作、分析与代码生成。
v1.0.0
io.github.ptyagiegnyte/egnyte-mcp-server
官方 Egnyte MCP 服务器,用于 AI 集成的文档搜索、分析与协作。
v1.0.0
io.github.huoshuiai42/huoshui-file-converter
提供文档格式转换功能的 MCP 服务器。
io.github.anthropics/skills/xlsx
当电子表格文件是主要输入或输出时使用本技能。包括:打开、读取、编辑或修复现有 .xlsx、.xlsm、.xltx、.csv、.tsv 文件(如加列、计算公式、格式化、图表、清洗脏数据);从零或其他数据源创建新电子表格;在表格文件格式间转换。当用户按名称或路径引用电子表格文件(哪怕是随口一提,如“下载目录里那个 xlsx”)并要对它做处理或从中产出内容时触发;也适用于把脏乱的表格数据文件(畸形行、错位表头、垃圾数据)整理成规范电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库流水线或 Google Sheets API 集成时不要触发,即使涉及表格数据。
io.github.anthropics/skills/xlsx
当电子表格文件是主要输入或输出时使用:打开、读取、编辑或修复现有 .xlsx、.xlsm、.xltx、.csv、.tsv 文件(如加列、计算公式、格式化、图表、清洗数据);从零或其他数据源新建表格;在表格格式之间转换。用户按名称或路径引用表格文件并提出处理要求时同样触发,也包括把结构混乱的表格数据(错位表头、脏数据)整理为规范表格。交付物必须是表格文件;当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets API 集成时不要触发。
io.github.wshobson/agents/rag-implementation
使用向量数据库与语义搜索,为 LLM 应用构建检索增强生成(RAG)系统。在实现知识锚定的 AI、构建文档问答系统或将 LLM 与外部知识库集成时使用。
io.github.github/spec-kit/add-community-extension
依据 GitHub issue 提交,把社区扩展加入 Spec Kit 目录。适用:处理扩展提交 issue、校验目录条目、更新 catalog.community.json 与 docs/community/extensions.md、创建 PR。不适用:从零新建扩展或第一方扩展工作。
io.github.asgeirtj/system_prompts_leaks/xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
io.github.asgeirtj/system_prompts_leaks/pdf
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing. Routes automatically by document type and supports reports, posters, papers, resumes, extraction, merging, splitting, and form filling. Use this skill for any conversion whose output is a PDF: Office → PDF (.docx/.doc/.pptx/.ppt/.xlsx/.xls/.odt/.odp/.ods/.rtf/.csv/.txt → PDF), HTML → PDF, and LaTeX/.tex → PDF; also PDF → images, PDF → text, and PDF → tables when reading a PDF apart. Trigger when the user asks to convert, export, render, print, or turn a file into a PDF, or to merge/split/extract from one — including phrasings like 'Word转PDF', 'PPT转PDF', 'Excel转PDF', 'html转pdf', '导出为PDF', 'save/export as PDF', or 'PDF转图片/文字'.
io.github.asgeirtj/system_prompts_leaks/pptx
Use this skill any time a presentation file is the primary input or output. Covers: creating new .pptx decks from scratch or from an outline/document (pptxgenjs / python-pptx); editing and restyling an existing .pptx; reading and extracting text/structure from a deck (markitdown); and rendering a deck to PDF (LibreOffice) or to per-slide PNG images (pdftoppm) for previews, thumbnails, or visual review. Trigger when the user references a .pptx file by name or path, says 'make/build a deck, slides, presentation, PPT, 幻灯片, 演示文稿, 汇报/路演材料', or asks to convert, export, render, or preview slides as PDF or images (e.g. 'PPT转PDF', 'ppt导出图片', 'turn these slides into a PDF').
io.github.Stirling-Tools/Stirling-PDF/feature-walkthrough
端到端讲解当前分支的完整逻辑与流程,让毫无前置知识的人也能理解、审查并复现。从分支 diff 界定变更范围,追踪其触达的每一层流程(前端工具/hook/组件、Java controller/service/endpoint、Python 引擎、配置、i18n、测试),产出带 Mermaid 图(时序/流程/架构)、可点击引用的带注释文件地图、前后行为对比、涉及 UI 时的截图、「本地试跑」章节与边界情况/风险的自包含走查文档。当被要求做功能或分支走查、「解释这个分支做了什么」、设计/逻辑说明、PR 审查者上手或交接文档时使用。加 --html 可同时输出渲染的 HTML 版;--no-screens 跳过截图。
skillsmp.nidhinjs-prompt-master-skill-md
为 AI 工具生成优化后的提示词。仅在用户明确要求为某个具体 AI 工具(LLM、Cursor、Midjourney、图像 AI、视频 AI、编码 agent 等)撰写、修复、改进或改写提示词时激活。不响应一般对话、编码任务、文档撰写或其他非提示词工程工作。
io.github.vercel/next.js/sandbox-bench
在 Vercel Sandbox VM 上以配对 A/B 统计对 React 或 Next.js 改动做基准测试:react PR/commit 对比 base,或 Next.js PR/commit 对比 base,经由 bench/render-pipeline 应用做端到端测量(rps、延迟、p95;如 Next 侧采集则含 TTFB、RSS 及 document/Flight 字节),React 改动还会走 react 仓库的 flight-ssr-bench fixture(Node 与 Edge web-streams 路径、Fizz 与 Flight+Fizz)。当用户要求 bench、性能测试或 A/B 一个 React PR、react-server-dom / Flight / vendored React 改动、或 Next.js PR(如“这个 PR 更快吗”“会不会让 RSC 退化”“量化 <commit> 的性能影响”)时即可使用——凡是量化两个版本间服务端性能差异的请求都属于此场景。远端运行(不占用笔记本),测量前先过正确性闸门,并给出 boot 级别的置信区间。
io.github.anomalyco/opencode/figma-generate-library
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. Also use when the user asks to create or generate any component in Figma — even a single one — since components require proper variable foundations, variant states, and design token bindings to be production-quality. This skill teaches WHAT to build and in WHAT ORDER — it complements the `figma-use` skill which teaches HOW to call the Plugin API. Both skills should be loaded together.
io.github.pytorch/pytorch/triaging-issues
Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.
io.github.mattpocock/skills/handoff
把当前对话压缩成交接文档,供另一个代理接手。
io.github.microsoft/TypeScript/security-report-check
你在对本仓库做安全研究吗?本文说明仓库能提供和不能提供哪些保障。在上报安全问题或开展安全研究之前请先阅读。
io.github.thedaviddias/Front-End-Checklist/no-unchecked-indexed-access
审计 tsconfig.json 是否缺少安全标志、审查数据处理流水线中用到数组索引访问的代码,或排查 TypeScript 未捕获的运行时 undefined 错误时使用。
io.github.thedaviddias/Front-End-Checklist/doctype
适用于所有 HTML 文档。务必查看原始 HTML 源码的第一行(view-source: 或 DevTools > Network > Response)。在 SSR 框架中查看根 HTML 模板(如 Next.js 的 _document.tsx、Vite/Vue 的 index.html、Rails 的 application.html.erb)。doctype 不是标签而是声明,不需要闭合标签。
io.github.asgeirtj/system_prompts_leaks/pdf
Build, revise, or manipulate a fixed-layout PDF (report, guide, one-pager, printable document). Use whenever a build task's artifact kind is pdf, a document build's output format is pdf, or the task reads, merges, splits, crops, or fills an existing PDF, including fillable AcroForms. Covers authoring the print-CSS HTML source, rendering, the geometry and validation gates, existing-PDF manipulation and form filling, and delivery under workspace/your_files.
io.github.pytorch/pytorch/triaging-issues
对 GitHub issue 进行分诊:路由到值班团队、打标签并关闭咨询类问题。在处理新的 PyTorch issue 或被要求分诊 issue 时使用。