serdes-yaml-edit(serdes YAML 编辑)
io.github.metabase/metabase/serdes-yaml-edit
编辑 Metabase serdes YAML 文件(卡片、仪表盘、数据库),使用正确的可移植引用与结构约定。在修改导出的 YAML 内容时使用。
“Content” 共 444 个结果
io.github.metabase/metabase/serdes-yaml-edit
编辑 Metabase serdes YAML 文件(卡片、仪表盘、数据库),使用正确的可移植引用与结构约定。在修改导出的 YAML 内容时使用。
io.github.coreyhaines31/marketingskills/marketing-loops
当用户想设置周期性、自动运行的营销工作流——由 AI 代理按固定节奏(每周、每天或按触发器)重复执行的循环,而不是一次性任务——时使用。用户提到 marketing loop、recurring marketing workflow、automate my marketing、marketing on autopilot、weekly marketing review、ad fatigue check、content refresh loop、churn watch、ranking drop alert、always-on marketing、marketing automation workflow 或“每周都跑一次这个”等场景时也适用。用于选择、适配并排期一个持续运行的营销循环,由它编排其他营销技能。一次性营销点子见 marketing-ideas,实验循环见 ab-testing。
io.github.ruvnet/ruflo/browser-extract
通过已存储的 browser-templates 模板或一次性 DOM 查询提取结构化数据;在内容送入模型前强制执行 AIDefence 的 PII 与提示注入过滤。
io.github.affaan-m/ECC/prompt-caching-strategy
Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache reuse. TRIGGER when: user says "prompt cache", "cache hit rate", "reduce LLM cost", "optimize token usage", "cheaper LLM calls", or asks about prompt caching strategies for OpenAI/Anthropic/other providers. DO NOT TRIGGER when: user just wants to optimize a single prompt's quality (use prompt-optimizer instead), or asks about general caching infrastructure.
io.github.affaan-m/ECC/agent-security-hardening
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployment. Do not use for general web application security or offensive testing.
io.github.vercel/next.js/next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport, and intent prefetching. Requires Next.js 16.3+.
io.github.asgeirtj/system_prompts_leaks/library
Use ChatGPT Library when the user mentions their Library, asks to find or work with a Library-backed file, Site, or named file that may be in the Library, or wants to organize Library folders, restore a previous version, or share a native Library file or folder. Also use it when the user wants a user-facing file or reusable artifact created or updated, even if they do not mention the Library. It can search and read Library content, bring files into local workflows, save new deliverables, and update existing Library files while preserving their identity and version history.
io.github.thedaviddias/Front-End-Checklist/viewport-zoom
适用于 HTML 文档中任意 meta name=viewport 元素。检查 content 属性中的 user-scalable=no、user-scalable=0、maximum-scale=1 或小于 2 的 maximum-scale 取值。这是移动优先模板和 CSS 框架中的常见错误。
io.github.asgeirtj/system_prompts_leaks/document
Create, read, edit, or manipulate Word documents (.docx) and Word templates (.dotx). Use whenever a build task's artifact kind is document with the default docx output, or the task mentions a Word doc, .docx, or .dotx, extracts or reorganizes content from one, inserts or replaces images, does find-and-replace in one, or works with tracked changes (redlines) or comments. Covers python-docx generation, raw OOXML editing of existing files, document structure and formatting, and render verification. Not for PDFs, spreadsheets, or Google Docs.
io.github.affaan-m/ECC/santa-method
带收敛循环的多代理对抗校验。输出必须先通过两个独立评审代理才能交付。适用于交付前需由两个独立对抗评审者把关的产出。
io.github.supabase/supabase/ask-the-docs
基于文档化的架构、构建流水线与 review 模式回答关于 Supabase docs 应用(apps/docs)的问题,并在提议或评审改动时套用功能设计原则(代码库复用、极简编码)。当用户问“docs 应用里 X 是怎么工作的”“Y 在哪里”“这个方案在 docs 应用里合适吗”,或在 apps/docs/ 下做非平凡改动前使用——特别是涉及 MDX 流水线、markdown 生成、内容组件、联邦文档、贡献者写作模式的场景。必要时可用 Mermaid 图回答架构问题。
io.github.affaan-m/ECC/brand-voice
从真实的帖子、文章、发布说明、文档或站点文案中提炼出基于来源的写作风格画像,并在内容、触达和社媒工作流中复用。当用户希望语气统一、又不落 AI 写作的俗套时使用。
io.github.affaan-m/ECC/article-writing
根据提供的示例或品牌指引,以独特语气撰写文章、指南、博客、教程、newsletter 等长篇内容。当用户需要超过一段的成稿书面内容时使用,尤其在对语气一致性、结构和可信度有要求时。
io.github.affaan-m/ECC/x-api
X/Twitter API 集成,用于发布推文、推文串、读取时间线、搜索和数据分析。涵盖 OAuth 认证模式、速率限制和平台原生内容发布。适用于用户希望以编程方式与 X 交互时。
io.github.JCodesMore/ai-website-cloner-template/clone-website
Reverse-engineer and clone one or more websites in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a copy of this site", "rebuild this page", or "pixel-perfect clone". The request must include one or more target URLs.
io.github.emilkowalski/skills/mobile-native
Make a web app feel native on a phone — the small CSS and meta-tag fixes that separate "a website in a browser" from something that feels installed. Covers sticky hover states, tap highlight flashes, the 100vh bug, inputs that zoom the page, laggy taps, pull-to-refresh hijacking scroll, content under the notch, long-press selecting button text, carousels that scroll the wrong way, mismatched status bars, and the rule that you test on real hardware. Use when a web app is being built for or reviewed on mobile, when something "works in Chrome but feels wrong on my phone", when building a PWA, a bottom sheet, a carousel, a full-screen layout, or any touch interaction. For motion itself use animate; for React Native use animate-expo.
io.github.openstatusHQ/openstatus/openstatus-mcp
使用 openstatus MCP 服务器,从任意 Model Context Protocol 客户端(Claude、ChatGPT、Cursor 等)读取并更新状态页、状态报告与维护窗口。当 AI 助手需要在 openstatus 工作区发布事故、追加更新、完结报告或安排维护时使用。
io.github.microsoft/ai-agents-for-beginners/microsoft-docs
查询 Microsoft 官方文档,在 Azure、.NET、Agent Framework、Aspire、VS Code、GitHub 等范围内查找概念、教程与代码示例。默认使用 Microsoft Learn MCP;对 learn.microsoft.com 之外的内容使用 Context7 与 Aspire MCP。
io.github.affaan-m/ECC/counterparty-channel-discipline
Per-channel strict prompts, mention gating, silent observation, and a communication autonomy policy for agents that sit in shared channels with external counterparties. Use when an agent joins group chats, shared channels, or DMs where outsiders can read every message and you need it to speak only when addressed, never leak internal context, and route risky content to draft-only approval.
io.github.supabase/supabase/safe-sql-execution
只要代码会构建、返回、拉取或执行针对用户真实 Postgres 数据库的 SQL,就使用本 skill——即使需求读起来像普通功能或 bug 修复,完全没提“security”“injection”或“SafeSqlFragment”。覆盖:编写或修改任何构造/返回数据库对象(表、视图、函数、DB 触发器、索引、RLS 策略)SQL 的 pg-meta 函数、查询构造器或接口;把 schema/表/列/搜索词/路由参数插入 SQL 文本;存储、读取或重跑从数据库往返的 SQL(策略定义、函数/视图定义、片段保存内容);以及任何把 SQL 发到项目库的 Run/Apply/Execute 动作(SQL 编辑器执行选中、策略编辑器应用、片段执行器)。在动手写这类代码前就要加载,不要只在评审成品 diff 时才用。仅在改动完全不涉及 SQL 文本或执行时跳过——样式、无关的数据 hook、非 SQL 表单校验或 UI 布局工作。
io.github.openclaw/openclaw/telegram-e2e-userbot
在 Telegram 测试服务器上,用 Convex 租用的团队凭据验证用户可见的 OpenClaw Telegram 行为:驱动真实用户轮次,并记录消息、编辑、删除、表情回应、输入状态或富内容。
io.github.ai-dynamo/dynamo/dynamo-docs
在 Dynamo Fern 文档站上添加、更新、移动或删除内容——标准文档页面、目录驱动的配方与功能基准页面、示例、配方及翻译——始终保持与文档风格指南一致。适用于 docs/、recipes/ 或 examples/ 下的任何变更(新建页面、编辑、标签页或章节移动、重命名、移除、配方/基准页面、.zh-CN 翻译、版本切割),决定页面应归属的文档标签页(Kubernetes 指南 vs CLI 指南 vs 参考 vs 用例),以及任何需要修正 frontmatter、标题、链接、标注或术语的内容。
io.github.PostHog/posthog/exploring-llm-traces
使用 PostHog 的 MCP 工具调试并检查 LLM/AI 代理 trace。当用户粘贴 trace 或会话 URL(如 /ai-observability/traces/<id> 或 /ai-observability/sessions/<id>)、要求调试某个 trace、弄清哪里出了问题、检查代理是否正确使用了工具、验证上下文/文件是否被呈现、检查子代理行为、分析 LLM 决策,或研究 token 用量与成本时使用。当针对 `events.properties.$ai_input` / `$ai_output_choices` 的原始 SQL/HogQL 返回为空时也使用——消息内容只存在于专用的 `posthog.ai_events` 表中。
io.github.affaan-m/ECC/x-api
X/Twitter API 集成,用于发布推文、推文串、读取时间线、搜索和数据分析。涵盖 OAuth 认证模式、速率限制和平台原生内容发布。适用于用户希望以编程方式与 X 交互时。