В каталоге 183 730 навыков в 14 категориях.
PDF/이미지를 Claude vision으로 OCR하여 마크다운 변환. MUST use this skill when user: (1) asks to convert PDF/image to markdown, (2) as...
Processes documents through case.dev OCR for text and table extraction. Supports PDF and image files up to 500MB with pa...
Comprehensive guide to ocr. Master the concepts, implementation, best practices, and real-world applications of ocr in p...
AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives....
Extract text from local images, screenshots, scanned PDFs, receipts, forms, and mixed Chinese-English documents with the...
Use when extracting text and fields from photographed or scanned documents (letters, receipts, forms), including Japanes...
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:...
Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker...
Extract text from PDFs/scans (pymupdf, marker-pdf).
从PDF、扫描文档、arXiv论文中智能提取文本、表格、公式和图像,支持本地轻量引擎与高精度OCR双模方案,解决文档解析、内容复用及批量处理需求。
Extract text from a PDF or a scanned document, with or without OCR.
Use when converting scanned PDFs, image-heavy books, technical textbooks, music books, OCR output, or rough Markdown int...
Comprehensive guide to PaddleOCR implementation for multi-language text recognition, table extraction, and document layo...
Use when extracting text from PDFs or images before document classification ג€” Hebrew OCR, layout-aware parsing, scanne...
Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR structure, table reconstr...
Optical character recognition pipelines — engine choice, preprocessing, and accuracy — use when extracting text from ima...
高精度光学字符识别(OCR)服务。支持多语言、多格式图像的文字检测与提取,并提供文本区域坐标与置信度评分,适用于文档数字化与图像内容分析。
Extract text from images or PDF documents using the OCR.space API. Use this skill whenever the user needs to recognize t...
Comprehensive guide to Optical Character Recognition (OCR) using Tesseract OCR engine with Python
Adds a searchable text layer to a scanned PDF with ocrmypdf. Installs the toolchain at runtime in ~18s. Use when a PDF's...
OCR 文字提取:对扫描件、图片、无文字层的 PDF 进行 OCR,提取可编辑文本
Create a program's OCS support chatbot from the ACE template with a RAG collection built from the PDD and app docs, or r...
Change a live OCS chatbot's system prompt, tools or pipeline, then republish and smoke-test it. Use when someone asks to...
Grade OCS chatbot transcripts (LLM-as-judge): --quick 1-dim smoke, --deep / --monitor 5-dim calibrated. Needs a transcri...
Chat with an OCS chatbot through its public widget and capture a transcript with structural checks (--quick / --deep / -...
Build and QA an OCS Coach bot that a supervisor triggers from Labs to coach a flagged worker. Never messages a real work...
Ocsp reference tool. Use when working with ocsp in security contexts.
Generate hard-SF-inflected, technically dense, multi-format documents that blend cutting-edge science with literary expe...
Use this skill when working with Laravel Octane, a long-running PHP worker server (Swoole, FrankenPHP, RoadRunner) where...
Integrate with Octav API for cryptocurrency portfolio tracking, transaction history, and DeFi analytics across 50+ block...
Specialized workflow for transforming verbose natural language into semantic OCTAVE structures. REQUIRES octave-literacy...
Advanced semantic vocabulary and architectural patterns for the OCTAVE format. REQUIRES octave-literacy to be loaded fir...
Ultra-high density compression using mythological atoms and semantic shorthand. Preserves soul and constraints at 60% co...
Cheatsheet for reading and replying to PR review comments with octo.nvim on the Nuro monorepo. Use for octo, "Octo pr",...
Use when Octo.nvim shows "You are not logged into any accounts on <host>", "error connecting to github", "Could not reso...
Coordinate OctoArmor, HYDRA swarm extensions, Hugging Face model deployment, and governed multi-agent task completion ac...
Handles git and GitHub operations using the gh CLI. Use when the user asks about pull requests (PRs), GitHub issues, rep...
Use this skill whenever the prompt contains any `github.com` URL, even if the user only pastes a link and gives no GitHu...
OctoClaw is the TypeScript-first policy, delegation, status, and operator layer for OpenClaw. Use it when a turn should...
Semantic code research across GitHub repositories for finding implementations, patterns, and conducting PR/security revi...
GitHub repository analytics and insights.
Complete OctoPrint management skill for Raspberry Pi with Creality Ender 3D printers. Control prints, monitor temperatur...
Octal dump of files in various formats
制作杂志风长文章阅读页(大标题、章节、引用、配图区)。用户提到博客长文、公众号文章、专题报道时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作博客 / 长文阅读页(标题、作者信息、正文排版)。用户提到博客页、文章页时使用。先读 open-design 总控,再按本技能清单执行。
对已有设计稿或 HTML 做创意总监式审稿(层级、节奏、品牌一致性与改稿清单)。内部辅助技能,用户明确要求「帮我审稿 / 改设计」时使用。先读 open-design 总控再执行。
制作带侧边栏的数据看板或管理后台首页,含关键指标卡片与图表区域。用户提到后台、仪表盘、数据面板时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作数据汇报或分析摘要页面(结论先行、图表、建议行动)。用户提到数据报告、分析摘要、季度复盘时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作杂志风横向翻页汇报或路演稿(多页、每页一屏、可键盘翻页)。用户提到演示稿、汇报幻灯片、路演时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作瑞士国际主义风格 HTML 演示稿(16 列网格、单一强调色、锁死版式)。用户提到瑞士风 deck、国际主义幻灯网页时使用。先读 open-design 总控,再按本技能清单执行。
制作产品文档或帮助中心单页(侧栏目录 + 正文)。用户提到文档站、帮助文档页时使用。先读 open-design 总控,再按本技能清单执行。
制作可在邮件客户端展示的活动或新品通知版面(标题区、主图、正文、按钮)。用户提到邮件模板、活动邮件、电子报时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作常见问题与帮助中心页面,支持搜索、分类与折叠展开。用户提到 FAQ、帮助中心、客服问答时使用。先读取 open-design 总控流程,再按本技能清单执行。
通过已配置的 Figma MCP 工具读取文件结构、提取设计信息并执行自动化操作。
制作财务 / 经营摘要报告页(指标卡、图表区、说明)。用户提到财务报告页、经营看板摘要时使用。先读 open-design 总控,再按本技能清单执行。
制作游戏化产品界面示意(等级、任务、奖励反馈)。用户提到游戏化、积分成长界面时使用。先读 open-design 总控,再按本技能清单执行。
制作 HR 新人入职引导页(步骤、清单、联系人)。用户提到入职引导、onboarding 页面时使用。先读 open-design 总控,再按本技能清单执行。
按描述生成图片文件(png/jpg)并保存到项目中,适合海报、封面、插画、营销图。
制作看板任务板页面(多列状态、卡片、优先级标签)。用户提到看板、Kanban、任务板时使用。先读 open-design 总控,再按本技能清单执行。
制作会议纪要展示页(议题、决议、行动项与负责人)。用户要「会议纪要页 / 纪要排版」时使用。先读 open-design 总控,再按本技能清单执行。
制作手机应用界面示意,可单屏或多屏并排(含手机外框)。用户提到 App 界面、手机页面、移动端产品时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作新用户首次打开应用的引导画面,通常 3 屏(欢迎、价值说明、登录或开始)。用户提到新手引导、首次使用、开屏引导时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作产品规格 / PRD 展示页(背景、需求、验收)。用户提到产品规格页、PRD 页面时使用。先读 open-design 总控,再按本技能清单执行。
制作竖版宣传海报或朋友圈分享长图(强视觉冲击、要点列表、品牌与二维码区)。用户提到海报、活动图、分享图时使用。先读取 open-design 总控流程,再按本技能清单执行。
Review pull requests to the OpenDesigner repo and merge the ones that pass. Checks for malicious code, prompt injection,...
制作产品定价与套餐对比页面(多档价格、功能对比、常见问题)。用户提到定价、套餐、收费时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作升级会员、付费解锁或套餐推荐页面,侧重转化与对比。用户提到付费墙、升级页、开通会员时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作个人求职简历页面(经历、技能、项目、联系方式)。用户提到简历、求职、个人介绍页时使用。先读取 open-design 总控流程,再按本技能清单执行。
为企业或产品制作官网、落地页、介绍页(首屏、功能说明、价格或试用入口、页脚联系)。用户提到官网、落地页、产品介绍时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作多张可左右滑动的社媒图文卡片(干货要点、统一视觉系列)。用户提到小红书风格、轮播图、多张配图时使用。先读取 open-design 总控流程,再按本技能清单执行。
制作 X(Twitter)金句或数据分享卡(适合配推文截图)。用户提到推特卡、X 分享图时使用。先读 open-design 总控,再按本技能清单执行。
制作团队 OKR / 目标跟踪页(季度横幅、目标、关键结果进度条、负责人与状态)。用户提到 OKR、关键结果时使用。先读 open-design 总控,再按本技能清单执行。
按描述生成视频文件(mp4)并保存到项目中,适合宣传片段、概念演示和动态视觉稿。
制作产品预发布 / 候补名单落地页(品牌、一句话价值、邮箱收集与成功态)。用户提到 waitlist、即将上线、早鸟报名时使用。先读 open-design 总控,再按本技能清单执行。
制作高保真网页原型(导航、核心页面区块、关键交互示意)。用户要「原型 / 高保真 HTML 示意」时使用。先读 open-design 总控,再按本技能清单执行。
制作手机多屏流程线框(灰盒结构、关键标注)。用户要细化手机流程线框时使用。先读 open-design 总控,再按本技能清单执行。
制作灰块线框示意页,用于先确认页面结构与模块位置,再细化视觉。用户提到线框、草图、先搭结构时使用。先读取 open-design 总控流程,再按本技能清单执行。
以“成事而不妄为”为准则处理通用任务。用户点名 odai,或任务模糊、复杂、高风险、前提可疑、易漏项时使用;简单任务直做。
Odai 的可选多能力编排。用户要求分工、独立规划或审查、并行制作,或为 Codex、Claude Code、Copilot 配置模型路由时使用;治理技能 odai 独立可用。
Share data between Mendix apps over OData — published services, view entities as an abstraction layer, consumed clients...
Converts betting odds between formats and removes bookmaker margin to find true implied probabilities. Use when user ask...
Multi-book odds comparison, best price identification, vig calculation, line shopping, and line movement analysis for NH...
Solve ordinary differential equations (initial and boundary value problems). Supports stiff/non-stiff systems, event det...
Orchestration doctrine for the Architecture workflow — gather structural context when it is not established, draft the a...
Project conventions for reusable UI components, file placement, naming, and deduplication in Odin Reporters App. Use whe...
Orchestration doctrine for the Deliberation Council workflow — parallel perspective-lens deliberation, synthesized into...
Odin programming language development workflow. Use when:- Writing or modifying Odin code (.odin files)- Building Odin p...
Orchestration doctrine for the Software Engineering workflow — optional business analysis and arc42-structured architect...
Odin Inspector & Serializer — SerializedMonoBehaviour, validation attributes, custom drawers, editor windows. Enhances U...
Install and configure the Odin programming language. Use when:- Setting up Odin on a new machine- Updating Odin to lates...
Orchestration doctrine for the user-triggered operations that write to Yggdrasil Memory — Remember (promotion), Dream (c...
Orchestration doctrine for the Research workflow — the strategist role manages the research task across one or more boun...
Orchestration doctrine for the TDD workflow — gather behavioral context when it is not established, plan the packages, t...
Use whenever you run a Makefile target (e.g. `make travis_build`, `make test`, `make reasoned.ofn`) or any one-off ROBOT...
Odoo integration via Apideck's CRM, Accounting unified API — same methods work across every connector in CRM, Accounting...
Build enterprise-grade Odoo 19 ERP using OCA community modules instead of Enterprise licenses. Scaffold modules, vendor...
Operate Odoo across CRM, sales, inventory, purchasing, and accounting with module-aware planning, read-before-write chec...
Odoo 16 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and v...
Odoo 17 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and v...