メニュー
SkillsMP は ai-workspace-lab/xworkspace-core-skills から 52 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 52 件中 40 件を表示しています。
AI Workspace Infra Config-as-Code and Ansible standards. Use when changing playbooks, roles, inventories, variables, templates, scripts, migration/ restore logic, or CI/CD delivery of Ansible configuration in playbooks, platform-ops-toolkit, or…
原文の言語: 複数言語
AI Workspace Infra Terraform, topology, rendering, state and CMDB standards. Use when changing iac_modules, GitOps topology declarations, Terraform-backed workflows, provider modules, resource resizing, or IaC-to-Ansible handoffs. Covers YAML/Jinja rendering,…
原文の言語: 中国語
AI Workspace Infra multi-environment delivery, Vault OIDC, release and secret-isolation rules. Use when changing GitHub Actions environment routing, Vault roles/policies, CI secret reads, workflow_dispatch inputs, release tags, or deployment paths in…
原文の言語: 英語
Govern Vault policies and roles, OIDC workload identity, least privilege, secret ownership, rotation, audit, emergency revocation, and environment isolation. Use when creating or changing access, onboarding a pipeline or service, rotating credentials,…
原文の言語: 英語
AI Workspace Infra 人机协作与安全执行纪律。用于维护 artifacts、docs、gitops、playbooks、iac_modules、observability.svc.plus、platform-ops-toolkit 时的仓库发现、权限边界、脏工作树、PR、部署和破坏性操作决策；涉及代码合入、多环境部署或越权风险时必须遵守。
原文の言語: 中国語
Agent Harness 工作流核心技能。定义了“工程闭环 × 小步快跑”的核心逻辑，并将工程标准与运营管理（协作规范、项目开发、CI/CD、配置/基础设施即代码、多环境发布、workflow dispatch、资源生命周期、Vault、DNS、观测和故障闭环）串联入该循环中。
原文の言語: 中国語
AI Workspace Infra branching, PR, release, tagging and incident standard. Use whenever changing one of its independent repositories, creating or reviewing a PR, choosing a target branch, handling dirty worktrees, coordinating a cross-repo change, cutting a…
原文の言語: 英語
Dispatch and observe operational GitHub Actions workflows (infrastructure provisioning, deploys, snapshots, migrations, credential rotation) from a conversational agent. Use before calling workflow_dispatch on any operational pipeline, and whenever a…
原文の言語: 英語
Design, implement, or review a Zero-driven XConnect overlay network spanning XConnect Zero/Accounts, Gateway, One clients, GitOps, Playbooks, Vault, IaC, and deployment workflows. Use for WireGuard-over-VLESS, signed enrollment/configuration, Gateway/One…
原文の言語: 英語
General CI/CD workflow standards for AI Workspace Infra pipelines and external scripts. Use when creating, refactoring, or auditing CI, CD, promotion, deployment, or GitHub Actions workflows in platform-ops-toolkit, artifacts, gitops, playbooks, iac_modules,…
原文の言語: 英語
Manage production incidents, emergency changes, rollout freezes, recovery decisions, incident timelines, blameless postmortems, and corrective-action closure. Use when a service is degraded, a deployment or infrastructure change fails, an urgent change is…
原文の言語: 英語
拉取一条 TikTok / 抖音短视频，逐镜识别画面内容、镜头运动、转场与音画节奏，产出带时间戳的脚本与高光节点时间轴（beat sheet）。只做理解，不做生成；供 XWorkmate「爆款视频复刻」插件的 ingest / beat-sheet 步骤消费。触发：拆解爆款视频、beat sheet、逐镜理解、视频脚本提取、竞品视频分析。
原文の言語: 中国語
需求事实来源（Source of Truth）与 Issue/PR 溯源关联标准。用于确定"这次要做什么"的权威载体、把 Issue → 分支 → commit → PR → CI → 部署 → tag 串成双向可导航的溯源链、约束 Agent 自行取用上下文（而不是要人类粘贴需求与报错日志）、以及处理范围漂移与跨仓需求扇出。任何"派发一个任务就自主开工"的闭环执行都必须先遵守本标准。
原文の言語: 中国語
Plan, implement, test, and audit backups, disaster recovery, VPS or cloud migrations, restore drills, RPO/RTO targets, data consistency, and retirement of old resources. Use before any recovery, replacement, resize, cross-cloud move, backup policy change, or…
原文の言語: 英語
Assess capacity, cost, resource ownership, VPS resizing, replacement, snapshots, reserved IPs, retirement, and cleanup. Use before changing cloud plans, disks, instance types, autoscaling, reservations, tags, budgets, snapshots, or lifecycle state.
原文の言語: 英語
Plan and operate DNS, TLS certificates, ACME, Caddy/Ingress/reverse proxies, edge routing, TTL, cutovers, validation, and rollback. Use before changing a public hostname, certificate, load-balancer route, ingress, proxy, firewall exposure, or DNS provider…
原文の言語: 英語
Define and operate SLIs, SLOs, error budgets, dashboards, alerts, telemetry correlation, and deployment verification. Use when onboarding a service, changing monitoring, tuning alerts, reviewing reliability, diagnosing a production issue, or deciding whether…
原文の言語: 英語
Create or review service catalog records, ownership metadata, dependency maps, operational runbooks, deployment records, backup and recovery references, and retirement documentation. Use when onboarding a service, changing ownership or dependencies, writing…
原文の言語: 英語
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling…
原文の言語: 英語
Convert PPT screenshots, academic images, UI mockups, and report pages into a high-fidelity SVG intermediate, then reconstruct a mixed editable PowerPoint file with SVG/PNG fallbacks and optional VBA helpers.
原文の言語: 英語
use when users want XiaoBei skill / xiaobei-skill / 小北在读研 style academic image-to-vba reconstruction: convert academic figures, scientific diagrams, slides, screenshots, or other images into vba, office drawing code, powerpoint/excel/word shapes, editable…
原文の言語: 英語
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used…
原文の言語: 英語
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
原文の言語: 英語
Create, inspect, and edit Microsoft PowerPoint presentations and PPTX decks with reliable layouts, templates, placeholders, notes, charts, and visual QA. Use when (1) the task is about PowerPoint or `.pptx`; (2) layouts, placeholders, notes, charts, comments,…
原文の言語: 英語
图文 PDF 工作流：将主题或文章拆成章节，为每章生成配图，并汇总排版为真实 PDF。Workflow skill for turning a topic or article request into a chaptered PDF with one image per chapter; use for illustrated PDF reports, chapter images, and final PDFs assembled from text plus generated images.
原文の言語: 英語
研究到幻灯片工作流：将研究资料、来源和主题 brief 转成可验证的演示文稿。Workflow skill for turning research notes, sources, or a topic brief into a verified slide deck; use for PPT, PPTX, slides, research presentations, briefing decks, or source-backed presentations.
原文の言語: 英語
选题拆解与图文连载生成 Skill。适用于系列主题拆分、图文标题规划、长文标题规划、每日排期、周计划、周总结、图文关键词提炼、图文内容概要、文章结构大纲、批量生成图文提示词、按模板风格生成图片；每批不超过 10 张图文。
原文の言語: 中国語
生成 IT 基础设施系列连续风格 PNG 图片。适用于一图看懂、长图信息图、IT基础设施演进、平台工程、网络/存储/安全/监控/AI 共进化主题；支持根据用户输入图片或详细描述输出 1-N 张独立的 1024x1536 蓝白科技风竖版 PNG，并产出可供 it-infra-evolution-video skill 消费的素材 manifest。
原文の言語: 中国語
用于制作 AI 科技资讯快报视频。包含：新闻检索与筛选、真实素材下载、edge-tts 口播、HyperFrames 画面编排、音频与字幕同步、最终渲染导出。触发词：AI快报、科技资讯视频、AI新闻视频、news flash video、weekly AI digest。
原文の言語: 複数言語
制作 IT 基础设施系列长图讲解视频。适用于 IT基础设施演进史、一图看懂视频、长图讲解视频、平台工程视频、网络/存储/安全/监控演进视频。默认使用 HyperFrames + edge-tts + 真实用户图/信息图素材，生成 1920x1080 横屏视频、中文口播、逐句字幕、BGM、章节 timeline tag，并完成 lint/inspect/snapshot/render/ffprobe 验证。
原文の言語: 中国語
从 it-infra-continuous-png 的真实 PNG manifest 生成 IT 基础设施长图讲解视频。强制执行 manifest -> video.config.json -> index.html -> audio -> HyperFrames acceptance -> MP4 -> ffprobe 的闭环。
原文の言語: 中国語
制作产品介绍视频。默认使用中文介绍产品，除非用户明确要求其他语言。流程：访问官网→获取素材(VL验证)→Web搜索补充→用户确认→HyperFrames渲染。支持任意比例。触发：产品视频、product video、官网视频、intro video、产品介绍。
原文の言語: 中国語
文章转图片系列工作流：将文章、提纲或主题序列转成风格一致的多图系列。Workflow skill for converting an article, outline, or topic sequence into a coherent multi-image series; use for one image per chapter, article illustrations, infographic series, Xiaohongshu-style cards, or manifest-backed…
原文の言語: 英語
根据用户指定的任意演进主线，输出公众号、小红书、X、头条号等 Markdown 软文矩阵。
原文の言語: 英語
采集最新 AI 资讯并输出 Markdown 文件。Use when the user asks to collect recent AI/AI Agent/news items and save them as md artifacts.
原文の言語: 英語
使用 AutoGLM Web Search 接口进行网络信息搜索。当用户需要联网搜索、查询最新资讯、检索网页内容或获取实时信息时使用此 skill。 Token 通过本地服务 http://127.0.0.1:53699/get_token 自动获取，无需手动配置环境变量。
原文の言語: 中国語
AI image generation and photo editing powered by CellCog. Text-to-image, image-to-image, consistent characters, product photography, reference-based generation, style transfer, sets of images, social media visuals, brand assets, stickers, comics, GIFs.…
原文の言語: 英語
图片尺寸调整和压缩工具技能。用于按指定像素宽高、比例或最大尺寸限制调整图片大小，并支持智能压缩到指定文件大小。适用于需要批量处理图片、生成特定尺寸缩略图、压缩图片以满足文件大小限制等场景。
原文の言語: 中国語
Self-reflection + Self-criticism + learning from corrections. Agent evaluates its own work, catches mistakes, and improves permanently.
原文の言語: 英語
Scan a third-party Claude Code skill for security risks before enabling it. Use when user wants to audit, check, or verify the safety of a skill.
原文の言語: 英語