全部 Agent Skills
41,263 个结果
- Cloudinary Reactcloudinary-devsProvides opinionated React SDK patterns for configuration, common integration scenarios, and troubleshooting for frequent errors and TypeScript pitfalls. Use when writing code or answering questions related to the Cloudinary React SDK.
- Code To Catalogevent-catalogTurns a codebase into EventCatalog documentation through an evidence-based interview. Scans the code first, proposes an architectural model (domains, services, agents, messages, channels), grills the user on the structural decisions, produces a reviewable plan file, then hands off to catalog-documentation-creator.
- Codex CliAmirkia RAFIEI OSKOOEIUse Codex CLI as a subagent. Lets the main agent prompt Codex CLI from the terminal in headless mode with the `codex` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Codex CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.
- Content BriefSearch FitGenerate a detailed content brief for a specific article or page. Use when the user asks to "create a content brief", "write a brief", "article outline", "blog brief", "writing brief", "content outline", or wants a structured plan before writing content.
- Content StrategySearch FitDevelop a content strategy for SEO and organic growth. Use when the user asks to "plan content", "content strategy", "content calendar", "what should I write about", "content gap analysis", "topic research", "editorial plan", or wants to plan what content to create for their website.
- Content TranslationSearch FitTranslate and localize website content for international SEO. Use when the user asks to "translate content", "localize my site", "multilingual SEO", "translate to [language]", "international SEO", "hreflang", "multi-language website", or wants to expand content to new languages and markets.
- Copilot CliAmirkia RAFIEI OSKOOEIUse GitHub Copilot CLI as a subagent. Lets the main agent prompt GitHub Copilot CLI from the terminal in headless mode with the `copilot` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to GitHub Copilot CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.
- Cursor CliAmirkia RAFIEI OSKOOEIUse Cursor CLI as a subagent. Lets the main agent prompt Cursor CLI from the terminal in headless mode with the `agent` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Cursor CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.
- Daily Hot Newsone-box-u每日热榜技能 - 查询微博、知乎、B站、抖音等54个平台的热榜数据，支持定时推送和分类浏览。
- Data AnalysismeirmPerform data analysis tasks including data cleaning, statistical analysis, visualization, and insight generation. Use when the user asks to analyze data, perform statistical analysis, create visualizations, or extract insights from datasets.
- Deepagents CodeAmirkia RAFIEI OSKOOEIUse Deep Agents Code as a subagent. Lets the main agent prompt Deep Agents Code from the terminal in headless mode with the `dcode` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Deep Agents Code, when a task needs a second independent agent, or when a plan needs a fresh perspective.
- DeslopinspirepanRemove AI-generated code slop from files or diffs. Use this skill when reviewing AI-generated code to clean up unnecessary comments, defensive code, type hacks, and style inconsistencies. Triggers include "deslop", "remove slop", "clean up AI code", "review for slop".
- Devin CliAmirkia RAFIEI OSKOOEIUse Devin CLI as a subagent. Lets the main agent prompt Devin CLI from the terminal in headless mode with the `devin` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Devin CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.
- Devsandbox Configzekker6Answer devsandbox configuration and setup questions from the published documentation instead of from memory - which TOML key to set, what values it accepts, which file it belongs in, and how the files merge.
- Direct AdsaxisrowНаписание рекламных объявлений для Яндекс.Директ. Используется когда пользователь просит написать, улучшить или проверить текст объявления, заголовки, или тексты для контекстной рекламы.
- Docyrus API DevdocyrusDevelop applications using the Docyrus API with @docyrus/api-client and @docyrus/signin libraries. Use when building apps that authenticate with Docyrus OAuth2 (PKCE, iframe, client credentials, device code), make REST API calls to Docyrus data source endpoints, construct query payloads with filters, aggregations, formulas, pivots, and child queries, or integrate with external connectors…
- Docyrus Cli AppdocyrusUse the Docyrus CLI (`docyrus`) to interact with the Docyrus platform from the terminal. Use when the user asks to authenticate, list apps, query or manage data records (`ds`), manage dev app data source schema objects (`studio`) including data sources, fields, enums, data views, forms, webforms, HTML/PDF export templates, and email templates, manage automations and their triggers/action nodes…
- Flow Wizardevent-catalogGuides users through documenting business flows step-by-step in EventCatalog, including services, agents, messages, actors, and external systems. Use when user asks to "document a flow", "map a business process", "create a flow diagram", "walk through a process", "document an end-to-end flow", "map an agent workflow", or "map out how something works in my architecture".
- Gemini CliAmirkia RAFIEI OSKOOEIUse Gemini CLI as a subagent. Lets the main agent prompt Gemini CLI from the terminal in headless mode with the `gemini` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Gemini CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.
- GenomicsjustaddcoffeeGenomics and transcriptomics analysis strategies
- Giasip DispatchGiaSip多模型调用器 — 把任务或 prompt 派发给其他 AI 模型（Codex / Gemini / Kimi / DeepSeek / 豆包 / Qwen / GLM / MiniMax）执行并取回结果。当你想用某个或某几个其他模型跑任务、需要多模型交叉对比验证、或想用更便宜的模型省钱时触发。提供两类调用通道：API 直调（只需 API key）和 CLI 调用（需本地装对应 CLI）。触发信号：「用 Kimi/Codex/Gemini 跑一下」「交给其他 AI」「换个模型试试」「让几个模型都看看」「这个不用最贵的模型」。
- Giasip DispatchGiaSip“Multi-model dispatcher -- sends a task or prompt to other AI models (Codex / Gemini / Kimi / DeepSeek / Doubao / Qwen / GLM / MiniMax) and retrieves results. Triggers when you want to run a task on a specific model, need multi-model cross-validation, or want to use a cheaper model.”
- Giasip ResearchGiaSipUse when the user asks to research, investigate, compare competitors, study a market or industry, check the current status of a regulation or policy, search literature, or simply look something up that needs external sources. Any question that requires fetching outside information triggers this skill. To verify specific claims in an existing report, use a dedicated verification pass instead.
- GiaSip/giasip-skillsGiaSip技能合集Turn research questions into reports with source links and open questions: Research for Codex and Claude Code, plus multi-model dispatch tooling for Claude Code.